Henry's public source catalogue
# Henry's public source catalogue
Content revision ea31a3343577b30cee4337cf2fef2b0864a5741341f27598e9108766c486fb2d
165 sources
## Places I've Studied
Education
Section education
Source ID education:overview
Original https://www.henryw.me/#/education
Read https://ask-henry.whenry6688.workers.dev/agent/sources/education%3Aoverview?format=text
Living and studying in different places has given me different perspectives on the world.
## The University of Hong Kong
Education
Section education
Source ID education:the-university-of-hong-kong
Original https://www.henryw.me/#/education#the-university-of-hong-kong
Read https://ask-henry.whenry6688.workers.dev/agent/sources/education%3Athe-university-of-hong-kong?format=text
September 2022 - Present The University of Hong Kong Bachelor of Arts and Sciences in Applied Artificial Intelligence I'm a fourth-year student at the University of Hong Kong , majoring in Applied Artificial Intelligence . My coursework spans machine learning, deep learning, data science, algorithms, software engineering, probability, statistics, linear algebra, and multivariable calculus.
## The University of Melbourne
Education
Section education
Source ID education:the-university-of-melbourne
Original https://www.henryw.me/#/education#the-university-of-melbourne
Read https://ask-henry.whenry6688.workers.dev/agent/sources/education%3Athe-university-of-melbourne?format=text
February 2025 - June 2025 The University of Melbourne Semester Exchange I spent one semester at The University of Melbourne through the HKU Worldwide Student Exchange Programme. Relevant coursework: Optimisation, Machine Learning, and Principles of Finance.
## Shanghai High School International Division
Education
Section education
Source ID education:shanghai-high-school-international-division
Original https://www.henryw.me/#/education#shanghai-high-school-international-division
Read https://ask-henry.whenry6688.workers.dev/agent/sources/education%3Ashanghai-high-school-international-division?format=text
September 2017 - June 2022 Shanghai High School International Division International Baccalaureate I completed junior high and high school at Shanghai High School International Division , where I took the International Baccalaureate Diploma Programme. For the IB Diploma, I studied computer science, mathematics, economics, physics, English, and Chinese.
## Havelock North High School
Education
Section education
Source ID education:havelock-north-high-school
Original https://www.henryw.me/#/education#havelock-north-high-school
Read https://ask-henry.whenry6688.workers.dev/agent/sources/education%3Ahavelock-north-high-school?format=text
July 2019 - August 2019 Havelock North High School Visiting Student I spent two months as a visiting student at Havelock North High School in Hawke's Bay, New Zealand, attending regular classes with local students. I studied English, calculus, statistics, chemistry, and physics.
## Roles I've Had
Experience
Section experience
Source ID experience:overview
Original https://www.henryw.me/#/experience
Read https://ask-henry.whenry6688.workers.dev/agent/sources/experience%3Aoverview?format=text
My work has ranged from open-ended research to delivery-focused industry projects.
## Cloud, Data & AI Consulting Intern
Experience
Section experience
Source ID experience:pwc
Original https://www.henryw.me/#/experience#work-pwc
Read https://ask-henry.whenry6688.workers.dev/agent/sources/experience%3Apwc?format=text
At PwC, I design and build AI and data systems for financial-services and public-sector clients. I develop solution architectures around each client’s business needs and technical constraints, then implement them through custom pipelines and integrations with existing systems. I designed and implemented an AI workflow that analyses long reports for different types of risk.
## Part-time Student Research Assistant
Experience
Section experience
Source ID experience:slr
Original https://www.henryw.me/#/experience#work-slr
Read https://ask-henry.whenry6688.workers.dev/agent/sources/experience%3Aslr?format=text
I work with Dr. Stephen Lee on computational models of human learning and cognition, studying how people form knowledge through experience and how learned representations support behaviour across tasks and situations. I develop computational models to examine possible cognitive processes behind experimental results. My work has included generalisation, transfer, and explicit and implicit learning.
## Digital Transformation Intern
Experience
Section experience
Source ID experience:hsbc
Original https://www.henryw.me/#/experience#work-hsbc
Read https://ask-henry.whenry6688.workers.dev/agent/sources/experience%3Ahsbc?format=text
At HSBC, I worked with business specialists, regional product teams, engineers and UI/UX designers to turn product knowledge into shared requirements. I designed a reusable framework that linked these requirements to design and implementation decisions, then built tools to automate configuration across products and markets.
## Web Developer, Digital Content Support
Experience
Section experience
Source ID experience:kiwiview
Original https://www.henryw.me/#/experience#work-kiwiview
Read https://ask-henry.whenry6688.workers.dev/agent/sources/experience%3Akiwiview?format=text
At Kiwiview, I developed the company’s website and created digital content for its study-tour and travel programmes. I designed, developed, deployed and maintained the company website. I created website copy, branding materials and promotional content for its study-tour and travel programmes.
## How AI changes the course of writing
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:overview
Original https://www.henryw.me/#/research/ai-writing-interview
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Aoverview?format=text
Journalist and editor Tequia Burt interviewed me for a book she is reporting on what writers bring to their work when AI can produce fluent prose. She had read my paper, Early Epistemic Settlement in AI-Assisted Writing , and was interested in how a useful answer might change the inquiry through which a writer develops an argument.
## How did you arrive at the concept of early epistemic settlement? Was there a particular writing experience or limitation in the existing research that led you to it?
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:origins
Original https://www.henryw.me/#/research/ai-writing-interview#origins
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Aorigins?format=text
Henry Wang I started from a fairly simple observation about what AI changes in writing. Writing has often been treated as part of thinking, not just a way of recording thought after the thinking is finished. Menary's Writing as Thinking captures this well (Menary, 2007).
## In professional writing, how might an AI response shape the direction of an inquiry even when the writer understands the response and continues thinking productively? Could you walk me through an example of the questions, connections, or alternative frames that might become less likely to emerge?
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:professional-writing
Original https://www.henryw.me/#/research/ai-writing-interview#professional-writing
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Aprofessional-writing?format=text
Henry Wang Imagine a journalist has two interviews about hybrid work. One person says they are more productive at home because they can concentrate. Another says their team became less productive because coordination became harder. The journalist has not yet worked out what to do with those two observations. AI gives her a clean frame: hybrid work involves a trade-off between individual focus and team collaboration.
## What determines whether an AI suggestion settles an inquiry too early or becomes useful material the writer actively works through? How much depends on timing, the writer’s expertise, or the nature of the task?
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:timing-and-expertise
Original https://www.henryw.me/#/research/ai-writing-interview#timing-and-expertise
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Atiming-and-expertise?format=text
Henry Wang I think this depends on what the writer is doing at the moment the suggestion arrives. Timing matters. If I already understand a relation and just cannot phrase it well, AI may be helping me say something I already know. If trying to write the sentence is how I am still figuring out the relation, the same answer can do something quite different. Expertise probably matters too.
## Editors and other collaborators can also provide a solution before a writer has completed the underlying thinking. What makes language models different, beyond the speed and frequency with which they can intervene?
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:models-and-collaborators
Original https://www.henryw.me/#/research/ai-writing-interview#models-and-collaborators
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Amodels-and-collaborators?format=text
Henry Wang What seems different to me is how much independent structure tends to enter the exchange. When another person works with my material, they are processing it through their own understanding. In the hybrid-work example, an editor might notice that one interviewee's work depends much more heavily on coordination than the other's.
## What would an empirical study need to observe or capture to test this framework? How might researchers distinguish an avenue of inquiry that was foreclosed from one the writer simply considered and rejected?
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:studying-inquiry
Original https://www.henryw.me/#/research/ai-writing-interview#studying-inquiry
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Astudying-inquiry?format=text
Henry Wang I'm still working this one out. I think there are two different questions hiding inside it. One is whether early settlement happened. The other is whether it was a bad trade. The first seems more straightforward to study. You could follow what a writer was doing immediately before and after assistance arrived. What were they trying to work out? Which notes or sources were they using?
## Are there practices that could help writers use AI without bypassing the work that expands what they are able to question, defend, or develop?
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:designing-assistance
Original https://www.henryw.me/#/research/ai-writing-interview#designing-assistance
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Adesigning-assistance?format=text
Henry Wang I think there are two separate parts of the interaction that matter here. One is what the AI contributes. If I am stuck between two ideas, it can give me the connection needed to move forward. But it could also surface other relations around the problem that are not necessary for solving the immediate difficulty and might open up other directions. The other is how that contribution is presented.
## References
How AI changes the course of writing
Section research
Source ID research-ai-writing-interview:references
Original https://www.henryw.me/#/research/ai-writing-interview#references
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research-ai-writing-interview%3Areferences?format=text
Danry, V., Pataranutaporn, P., Mao, Y., & Maes, P. (2023). Don’t just tell me, ask me: AI systems that intelligently frame explanations as questions improve human logical discernment accuracy over causal AI explanations. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 1–13. Read paper Doshi, A. R., & Hauser, O. P. (2024).
## Research I've Been Part Of
Research
Section research
Source ID research:overview
Original https://www.henryw.me/#/research
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3Aoverview?format=text
I study how people and AI systems learn from experience, represent knowledge and use it to think and act. As AI becomes part of everyday thinking, I investigate how it shapes the understanding, judgement and abilities people develop. I study how people learn from experience and use what they know.
## The Resolving Power of Transfer Experiments: When Can Designs Distinguish Accounts of Generalization?
Research
Section research
Source ID research:transfer
Original https://www.henryw.me/#/research#transfer
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3Atransfer?format=text
We developed a framework that links models of human generalisation to the design of experiments. I construct models by varying both how a learner represents information and how the learner uses it to respond. The same representation can support rule application, comparison with a category prototype or retrieval of remembered examples.
## BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
Research
Section research
Source ID research:bright
Original https://www.henryw.me/#/research#bright
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3Abright?format=text
Finding a useful document can depend on first understanding what a problem requires. We developed BRIGHT to evaluate this reasoning-intensive retrieval, using 1,384 real queries across domains including economics, psychology, mathematics and coding. I contributed biology and psychology data and reproduced programming examples to work through the questions and the material needed to answer them.
## Early Epistemic Settlement in AI-Assisted Writing
Research
Section research
Source ID research:fittedAssistance
Original https://www.henryw.me/#/research#structure-settles-thought
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3AfittedAssistance?format=text
In trying to finish a passage, a writer may connect her material in ways that change both the argument she can make and the demands it needs to meet. I examined what happens when AI supplies a passage that resolves the immediate difficulty while this work is still unfolding. The writer can understand the answer, judge it adequate, and move on before discovering what her own attempt could have made possible.
## Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning
Research
Section research
Source ID research:functionVector
Original https://www.henryw.me/#/research#functionVector
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3AfunctionVector?format=text
I studied how a language model carries out a task inferred from examples in its prompt. Function vectors capture this task information through the combined outputs of attention heads. Among candidate function-vector heads, I identified writers that support the answer specified by the demonstrated rule and cancellers that systematically suppress it.
## Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation
Research
Section research
Source ID research:humansDisengage
Original https://www.henryw.me/#/research#humansDisengage
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3AhumansDisengage?format=text
I studied how people and large reasoning models allocate effort once a problem becomes difficult. Across visual abstraction, intuitive physics and relational reasoning, I analysed human response times alongside the length and content of reasoning traces, the text models generate before answering. Comparing attempts on the same problems let me separate sensitivity to difficulty from the allocation of further effort.
## Functional Encoding and Representational Binding in Componential Transfer
Research
Section research
Source ID research:encoding
Original https://www.henryw.me/#/research#encoding
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3Aencoding?format=text
Why can a learner demonstrate a rule during training yet fail to use it on a new item? We built a computational account in which transfer depends on how useful components are encoded and bound together. Functional encoding determines which components enter the representation used to generate a response.
## Things I've Built
Builds
Section projects
Source ID projects:overview
Original https://www.henryw.me/#/projects?to=overview
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Aoverview?format=text
I like working through a problem and figuring out how the pieces could fit together. I enjoy trying different ideas and gradually building up a structure of my own.
## AI × Self
Builds
Section projects
Source ID projects:searchstory
Original https://www.henryw.me/#/projects?to=searchstory
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Asearchstory?format=text
Visitors can ask AI a question about my work, ideas or experiences. AI connects material from this site into a View, an illustrated article that answers their question and includes the original work. Each View also becomes an exhibition visitors can walk through, and the Gallery brings shared exhibitions together.
## SlidePoise
Builds
Section projects
Source ID projects:slidepoise
Original https://www.henryw.me/#/projects?to=slidepoise
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Aslidepoise?format=text
SlidePoise combines the visual freedom of image generation with an editable PowerPoint workflow. The Agent develops the content, retrieves relevant visual references, icons, logos and native component previews, and explores compositions through image generation. Reconstruction combines the Agent’s interpretation with measurements from the computer-vision library OpenCV to build editable objects.
## Cathay Flex
Builds
Section projects
Source ID projects:cathayflex
Original https://www.henryw.me/#/projects?to=cathayflex
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Acathayflex?format=text
Cathay Flex is Team Globe’s project for the Cathay Pacific Hackathon. An airline-managed marketplace lets travellers earn Flex credits by accepting suitable changes or releasing eligible unused services. They can use the credits for different travel needs on the same journey or a later one.
## Risk Assessment Across Long Documents
Builds
Section projects
Source ID projects:pwcDocumentReview
Original https://www.henryw.me/#/projects?to=pwcDocumentReview
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3ApwcDocumentReview?format=text
Henry translated risk definitions into evidence requirements and decision rules. Optional source guidance identifies report sections likely to contain useful context. He separated reading the report from assessing what its evidence means. An evidence-record schema preserves each observation, its context, source location and potential relevance to different risks.
## AI for IT Operations
Builds
Section projects
Source ID projects:pwcItOps
Original https://www.henryw.me/#/projects?to=pwcItOps
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3ApwcItOps?format=text
Knowledge Management serves the platform’s RAG question-answering assistant. Acquisition begins with unanswered user questions and model-predicted knowledge gaps. Related questions are clustered into coverage objectives. Seed discovery and focused crawling find authoritative evidence, using the original questions as minimum coverage and the objective to guide broader acquisition.
## Insurance Product Configuration Engine
Builds
Section projects
Source ID projects:insurance
Original https://www.henryw.me/#/projects?to=insurance
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Ainsurance?format=text
One banking app supported many insurance products, each with different screens, fields, and conditional follow-ups. Business requirements described what a product needed to collect, design libraries described reusable screens and UI components, and engineering needed an executable configuration. The key dependency was the mapping between those representations across products and markets.
## Interactive Scrollytelling Deck
Builds
Section projects
Source ID projects:scrollytelling
Original https://www.henryw.me/#/projects?to=scrollytelling
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Ascrollytelling?format=text
For a course presentation about the electricity and water demands of AI infrastructure, I built a web narrative whose charts develop as the reader scrolls. Figures stay in view while the explanation introduces new relationships. A shared scene schema and reusable D3 renderers separate the presentation’s content from the code that draws it.
## A Structure-Preserving RAG Ingestion Pipeline
Builds
Section projects
Source ID projects:pwcRag
Original https://www.henryw.me/#/projects?to=pwcRag
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3ApwcRag?format=text
The architectural risk appeared before retrieval began. If ingestion separated a passage from the note it refers to or reduced a flowchart to disconnected text, no later ranking or generation step could reliably restore the missing relationship. MinerU rejoined paragraphs and tables across page breaks. Its OCR-based path recovered merged cells but missed nested tables in the tests.
## Stride Support
Builds
Section projects
Source ID projects:stride
Original https://www.henryw.me/#/projects?to=stride
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Astride?format=text
Stride Support combines retrieval-augmented generation (RAG), recommendations and tool use in a customer-support conversation. Hybrid retrieval blends BM25 word matching with BGE embeddings to find relevant products and policy passages. Recommendations combine product similarity with purchase patterns, while a fine-tuned multilingual BERT (mBERT) classifier supplies a sentiment cue for the response.
## Dealtracker
Builds
Section projects
Source ID projects:dealtracker
Original https://www.henryw.me/#/projects?to=dealtracker
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Adealtracker?format=text
During my exchange in Melbourne, outdoor brands I liked were often cheaper than in Hong Kong, but finding the right offer meant repeatedly checking long sale pages. I built Dealtracker to scan two retailers on a schedule and match their listings against my brand, size, gender, and discount preferences. Store-specific request handling and data normalisation account for differences between the sites.
## How I Started Building with Code
Builds
Section projects
Source ID projects:early
Original https://www.henryw.me/#/projects?to=early
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Aearly?format=text
Seeing a teacher automate folder creation with a batch script made me curious about what else I could make a computer do. During junior high and high school, I taught myself Java and Python and treated code like building blocks, trying combinations and exploring the possibilities.
## Travels
Travels
Section travels
Source ID travels:overview
Original https://www.henryw.me/#/travels
Read https://ask-henry.whenry6688.workers.dev/agent/sources/travels%3Aoverview?format=text
Drag to spin · pinch to zoom · tap a point
## Insurance Product Configuration Engine
Insurance Product Configuration Engine
Section playbook
Source ID playbook:overview
Original https://www.henryw.me/#/playbook
Read https://ask-henry.whenry6688.workers.dev/agent/sources/playbook%3Aoverview?format=text
Mapping insurance requirements to the app’s screens and fields At HSBC , I built an Excel/VBA tool that determines which screens and fields a banking app needs for each insurance product. The team can enter a product’s specifications, generate its configuration and update the shared rules as products and requirements change. 00 Context
## Configuring the app for different insurance products
Insurance Product Configuration Engine
Section playbook
Source ID playbook:first-the-problem
Original https://www.henryw.me/#/playbook#first-the-problem
Read https://ask-henry.whenry6688.workers.dev/agent/sources/playbook%3Afirst-the-problem?format=text
Across dozens of insurance products in multiple markets, the app needed different screens and questions. Travel insurance might need trip dates, motor insurance might need vehicle details, and an earlier answer could determine which follow-up question appeared. The team needed a way to express those differences and generate the corresponding configuration.
## Making the configuration rules reusable
Insurance Product Configuration Engine
Section playbook
Source ID playbook:the-idea
Original https://www.henryw.me/#/playbook#the-idea
Read https://ask-henry.whenry6688.workers.dev/agent/sources/playbook%3Athe-idea?format=text
The required interface depended on combinations of product choices and conditions. I represented each relevant combination as a business scenario and defined rules for the components it required. This gave the engine a sequence it could evaluate, first establishing which scenarios applied, then selecting their screens and fields. Many products reuse the same definitions, conditions and components.
## Try the rules on a trip
Insurance Product Configuration Engine
Section playbook
Source ID playbook:try-it
Original https://www.henryw.me/#/playbook#try-it
Read https://ask-henry.whenry6688.workers.dev/agent/sources/playbook%3Atry-it?format=text
Change a trip’s details and trace the result through the highlighted rules to its packing list. The example below shows how conditional questions and separate decision tables work together. 03 Automation
## Automating product configuration
Insurance Product Configuration Engine
Section playbook
Source ID playbook:from-the-packing-demo-to-the-production-tool
Original https://www.henryw.me/#/playbook#from-the-packing-demo-to-the-production-tool
Read https://ask-henry.whenry6688.workers.dev/agent/sources/playbook%3Afrom-the-packing-demo-to-the-production-tool?format=text
In the production Excel/VBA tool, users entered specifications through a dynamic form. A compact notation in each field definition determined when follow-up questions appeared. The roughly 32 KB engine evaluated these inputs against the decision tables and generated the required UI-component configuration.
## Lexaday
Lexaday
Section lexaday
Source ID lexaday:overview
Original https://www.henryw.me/#/lexaday
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Aoverview?format=text
Related words, memorable images, and reviews by email I built Lexaday to teach related words through a shared root and an AI-generated image. Daily emails introduce new roots and revisit earlier ones on a personalised schedule. The project explores whether one visual memory can help learners recognise meaning across a family of words. 01 Words & images
## Remembering roots through images
Lexaday
Section lexaday
Source ID lexaday:a-small-lesson-generated-fresh-each-morning
Original https://www.henryw.me/#/lexaday#a-small-lesson-generated-fresh-each-morning
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Aa-small-lesson-generated-fresh-each-morning?format=text
A vivid image seemed a promising way to make a word’s meaning easier to recall. Giving every word its own picture, though, would create a new association to learn each time. I was interested in whether the same memory could help with several words, including ones I had not encountered yet. Roots offered a more compact starting point. Many words share an underlying idea such as speaking, hearing or sending.
## Scheduling new roots and reviews
Lexaday
Section lexaday
Source ID lexaday:the-learning-loop
Original https://www.henryw.me/#/lexaday#the-learning-loop
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Athe-learning-loop?format=text
I built spaced repetition into the daily emails so earlier roots would return alongside new material. Reviews are scheduled after one, two, four, eight and progressively more daily runs. Each learner needs a separate schedule because the roots they have seen and their last review dates differ. A saved progress record lets the job select one unseen root alongside any reviews due that day, before generating the lesson.
## Due today
Lexaday
Section lexaday
Source ID lexaday:pick
Original https://www.henryw.me/#/lexaday#pick
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Apick?format=text
The learner's record determines which root is new and which earlier roots need another look. 2
## Words in context
Lexaday
Section lexaday
Source ID lexaday:write
Original https://www.henryw.me/#/lexaday#write
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Awrite?format=text
A language model writes the introduction and example sentences for the root's related words. 3
## A visual cue
Lexaday
Section lexaday
Source ID lexaday:imagine
Original https://www.henryw.me/#/lexaday#imagine
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Aimagine?format=text
The root's meaning guides an image prompt, which an image model uses to create the mnemonic. 4
## The daily email
Lexaday
Section lexaday
Source ID lexaday:send
Original https://www.henryw.me/#/lexaday#send
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Asend?format=text
The lesson and images are assembled into an HTML email, and the progress record is saved for the next run. 03 Daily lesson
## The daily lesson
Lexaday
Section lexaday
Source ID lexaday:what-the-reader-receives
Original https://www.henryw.me/#/lexaday#what-the-reader-receives
Read https://ask-henry.whenry6688.workers.dev/agent/sources/lexaday%3Awhat-the-reader-receives?format=text
I packaged the new root and due reviews into a daily email. The complete example here shows how the image, related words and example sentences form a lesson, followed by earlier roots returning for another review. I used GitHub Actions for the scheduled runs and a JSON file for each learner’s progress. The file stores the run count, introduction date, last review, and current interval for every root encountered.
## Stride Support
Stride Support
Section stride
Source ID stride:overview
Original https://www.henryw.me/#/stride
Read https://ask-henry.whenry6688.workers.dev/agent/sources/stride%3Aoverview?format=text
Customer support with retrieval, recommendations and tool use A customer asking about a return needs the policy applied to their purchase and a way to take the next step. For this course project, we built a support assistant that uses the selected order throughout a conversation. It retrieves product and policy information, recommends suitable products and carries out actions such as filing a complaint. 01 Context
## Keeping the order in context
Stride Support
Section stride
Source ID stride:keeping-the-order-in-context
Original https://www.henryw.me/#/stride#keeping-the-order-in-context
Read https://ask-henry.whenry6688.workers.dev/agent/sources/stride%3Akeeping-the-order-in-context?format=text
“When will this arrive?” depends on which order the customer means. The interface lists ongoing and past orders and lets the customer select one. It sends that order’s status, items and delivery context with each message. Switching the selection changes the context supplied for the next turn. The backend supplies the active customer’s identity to the relevant tools.
## Connecting retrieval to support actions
Stride Support
Section stride
Source ID stride:giving-the-model-access-to-the-application
Original https://www.henryw.me/#/stride#giving-the-model-access-to-the-application
Read https://ask-henry.whenry6688.workers.dev/agent/sources/stride%3Agiving-the-model-access-to-the-application?format=text
Some requests need a passage from a policy. Others need a current order record or a change to a complaint. We exposed these operations through five Model Context Protocol (MCP) servers, which describe the tools and the inputs they accept. Policy search retrieves documents, customer and complaint tools work with SQLite records, and catalogue and recommendation tools find suitable products.
## Interpreting the customer’s request
Stride Support
Section stride
Source ID stride:matching-language-to-the-support-domain
Original https://www.henryw.me/#/stride#matching-language-to-the-support-domain
Read https://ask-henry.whenry6688.workers.dev/agent/sources/stride%3Amatching-language-to-the-support-domain?format=text
Product names and policy terms can be useful exact matches, while a customer’s description of what they need may use quite different words. We combined BM25, which ranks word matches, with BGE embeddings, numerical representations that capture related meaning. Product and policy search normalise and blend the two scores, making the balance between wording and meaning adjustable.
## Dealtracker
Dealtracker
Section dealtracker
Source ID dealtracker:overview
Original https://www.henryw.me/#/dealtracker
Read https://ask-henry.whenry6688.workers.dev/agent/sources/dealtracker%3Aoverview?format=text
Outdoor clothing sale alerts matched to my preferences During my exchange in Melbourne, I noticed that outdoor brands I liked, including Arc’teryx and Patagonia, were often cheaper than in Hong Kong and frequently discounted. Finding the right item still meant checking long sale pages before an offer ended. Dealtracker automates those checks and emails me when it finds a new match for my saved preferences.
## A shortlist in my inbox
Dealtracker
Section dealtracker
Source ID dealtracker:from-noisy-sale-pages-to-a-short-inbox-digest
Original https://www.henryw.me/#/dealtracker#from-noisy-sale-pages-to-a-short-inbox-digest
Read https://ask-henry.whenry6688.workers.dev/agent/sources/dealtracker%3Afrom-noisy-sale-pages-to-a-short-inbox-digest?format=text
I set filters for brands, sizes, gender, and minimum discounts. A scheduled job checks selected stores against those filters, turning their sale listings into a shortlist. The configuration shown here covers two Australian retailers and seven brands. 2 Australian stores 7 brands I track 29-39% minimum discount 02 The digest
## Enough information to decide
Dealtracker
Section dealtracker
Source ID dealtracker:the-email-output
Original https://www.henryw.me/#/dealtracker#the-email-output
Read https://ask-henry.whenry6688.workers.dev/agent/sources/dealtracker%3Athe-email-output?format=text
A useful alert lets me assess the offer before opening the store’s page. I designed the digest to group items by brand and sort them by discount, showing a photograph and the original and sale prices beside each product link. The examples below show how that information comes together in the email. Arc'teryx and The North Face digest Patagonia and Icebreaker digest 03 Collection
## Reading the stores' product data
Dealtracker
Section dealtracker
Source ID dealtracker:what-happens-behind-the-email
Original https://www.henryw.me/#/dealtracker#what-happens-behind-the-email
Read https://ask-henry.whenry6688.workers.dev/agent/sources/dealtracker%3Awhat-happens-behind-the-email?format=text
WildEarth and Find Your Feet express similar products and filters differently. Applying my preferences consistently meant first accounting for each store’s URL format, page loading, and product labels. I kept the store-specific handling at the point of collection, then normalised the listings so the same filtering and email logic could work across both retailers. The stages below follow a listing into the digest.
## Remembering what I have already seen
Dealtracker
Section dealtracker
Source ID dealtracker:the-control-layer
Original https://www.henryw.me/#/dealtracker#the-control-layer
Read https://ask-henry.whenry6688.workers.dev/agent/sources/dealtracker%3Athe-control-layer?format=text
A product can stay on sale across many scheduled checks. Without a record of earlier results, a successful search would keep filling my inbox with the same items. I added a history file so the job could distinguish a new match from one it had already reported. A run with nothing new finishes quietly. Sometimes I want to see the current selection again, including items I previously passed over.
## Scrollytelling Engine
Scrollytelling Engine
Section scrollytelling
Source ID scrollytelling:overview
Original https://www.henryw.me/#/scrollytelling
Read https://ask-henry.whenry6688.workers.dev/agent/sources/scrollytelling%3Aoverview?format=text
A web presentation whose charts unfold as you scroll For a course presentation about the electricity and water demands of AI infrastructure, I needed to explain relationships through maps, distributions, and flows. Showing a complete chart on a slide asked the audience to absorb its structure while following the argument.
## The presentation in motion
Scrollytelling Engine
Section scrollytelling
Source ID scrollytelling:see-it-as-a-story
Original https://www.henryw.me/#/scrollytelling#see-it-as-a-story
Read https://ask-henry.whenry6688.workers.dev/agent/sources/scrollytelling%3Asee-it-as-a-story?format=text
The embedded deck shows the engine in use. A line chart develops the comparison between electricity demand and grid capacity, while a map places water scarcity in its geographic context. Scroll inside the frame to follow the complete presentation. 02 Renderers
## Defining scenes with reusable D3 renderers
Scrollytelling Engine
Section scrollytelling
Source ID scrollytelling:describe-a-scene-once-then-let-the-engine-build-it
Original https://www.henryw.me/#/scrollytelling#describe-a-scene-once-then-let-the-engine-build-it
Read https://ask-henry.whenry6688.workers.dev/agent/sources/scrollytelling%3Adescribe-a-scene-once-then-let-the-engine-build-it?format=text
Each scene describes its text, figure type, and rendering settings in a data object with a shared schema. A renderer registry connects that figure type to the appropriate D3 builder, which draws and animates the visual using the supplied data. Adding a new line-chart scene, for example, means supplying another set of content and settings to the existing line-chart builder.
## Keeping the scenes consistent
Scrollytelling Engine
Section scrollytelling
Source ID scrollytelling:under-the-hood
Original https://www.henryw.me/#/scrollytelling#under-the-hood
Read https://ask-henry.whenry6688.workers.dev/agent/sources/scrollytelling%3Aunder-the-hood?format=text
Shared settings control layout, typography, and reveal timing across a deck. Individual scenes supply their own background, navigation label, and rendering properties. This keeps the presentation consistent while allowing each chart to express the relationships its part of the story needs.
## See Henry through your own lens
Views
Section views
Source ID views:overview
Original https://www.henryw.me/#/views
Read https://ask-henry.whenry6688.workers.dev/agent/sources/views%3Aoverview?format=text
See Henry through your own lens A note from Henry Start with what you’d like to explore about Henry. The site’s AI will create a View around your question or perspective. You can follow the links to explore the original work in more detail, and share your View here if you’d like others to read it too. Compose your own View Views ✦ See how other visitors have looked across Henry’s work, experiences, and ideas.
## How I started building with code
How I Started Building with Code
Section early
Source ID early:overview
Original https://www.henryw.me/#/early
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Aoverview?format=text
Downloaders, browser extensions, and an economics graph generator During junior high and high school, programming felt like playing with building blocks. I could combine a few pieces, change something and see what the computer would do. Curiosity led me to try desktop apps, browser extensions, websites and automation.
## My first desktop programs
How I Started Building with Code
Section early
Source ID early:how-it-started
Original https://www.henryw.me/#/early#how-it-started
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Ahow-it-started?format=text
My interest began at thirteen, when a teacher demonstrated a batch script that created folders automatically. Seeing a few lines make the computer do something made me curious about what else I could get it to do. I started teaching myself Java and Python, trying small desktop applications, including a contact notebook and a number-guessing game with user accounts and a history stored in text files.
## Taking Scientific American podcasts with me
How I Started Building with Code
Section early
Source ID early:batch-downloading-scientific-american-episodes
Original https://www.henryw.me/#/early#batch-downloading-scientific-american-episodes
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Abatch-downloading-scientific-american-episodes?format=text
In my first year of junior high school, I started using Scientific American podcasts to practise English. I listened on an MP3 player that could also display images and text, so I built a desktop application that downloaded episode audio, transcripts, and images in batches.
## Chrome extension experiments
How I Started Building with Code
Section early
Source ID early:chrome-extension-experiments
Original https://www.henryw.me/#/early#chrome-extension-experiments
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Achrome-extension-experiments?format=text
In my second year of junior high school, I began exploring Chrome extensions. Tools that could change a page’s behaviour, such as dimming the screen around a YouTube video, made me want to understand how they worked. I learned to develop and publish extensions, then made several of my own. Easy QR Code generated a QR code for the current page or for custom text and links.
## Music streaming hacks
How I Started Building with Code
Section early
Source ID early:music-streaming-hacks
Original https://www.henryw.me/#/early#music-streaming-hacks
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Amusic-streaming-hacks?format=text
In my first year of high school, I spent several months developing a music downloader for Chinese streaming services. Users could paste a song-page link into one interface to download music across several services. The technical work involved web scraping and reverse engineering how the services exposed media URLs. The interface accepted song-page links from QQ Music, NetEase Cloud Music, KuGou, and KuWo.
## Building Kiwiview's website
How I Started Building with Code
Section early
Source ID early:building-kiwiviews-website
Original https://www.henryw.me/#/early#building-kiwiviews-website
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Abuilding-kiwiviews-website?format=text
In my second year of high school, I began building a website for Kiwiview International Limited, a New Zealand company co-owned by my parents and a local business partner. The company was new, and they gave me the opportunity to design and develop its first website. I taught myself HTML, CSS, JavaScript, and SQL as I built the site.
## A script that played arithmetic games
How I Started Building with Code
Section early
Source ID early:simple-automation
Original https://www.henryw.me/#/early#simple-automation
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Asimple-automation?format=text
In my third year of high school, our school ran online mental-arithmetic and 24-point games. I built a script that recognised the questions on screen, solved them algorithmically, and entered the answers automatically. Each answer brought up another question, and the script kept going until the game timer ended.
## Drawing economics diagrams in Word
How I Started Building with Code
Section early
Source ID early:econographer-an-economics-graphs-generator
Original https://www.henryw.me/#/early#econographer-an-economics-graphs-generator
Read https://ask-henry.whenry6688.workers.dev/agent/sources/early%3Aeconographer-an-economics-graphs-generator?format=text
Econographer, a Microsoft Word add-in In my third year of high school, I wondered whether the economics diagrams we used in AP and IB coursework could be generated and adjusted in the document where we needed them. I could not find a suitable tool, so I made Econographer as a Microsoft Word add-in.
## AI × Self
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:overview
Original https://www.henryw.me/#/aipersonalarchive
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aoverview?format=text
An AI-driven personal archive Visitors can ask AI a question about my work, ideas or experiences. AI connects material from this site into a View, an illustrated article that answers their question and includes the original work. Each View also becomes an exhibition visitors can walk through, and the Gallery brings shared exhibitions together. 00 The project
## An archive open to different perspectives
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:one-archive-three-ways-to-explore
Original https://www.henryw.me/#/aipersonalarchive#one-archive-three-ways-to-explore
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aone-archive-three-ways-to-explore?format=text
A personal site usually reflects how its author has organised their life. Work goes under projects, an experience under a date, a thought into a piece of writing. A visitor’s question can cross those boundaries and connect things I recorded years apart and for different reasons. AI can read across these records and develop connections around someone’s question.
## System architecture
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:system-architecture
Original https://www.henryw.me/#/aipersonalarchive#system-architecture
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Asystem-architecture?format=text
At build time, the site prepares passages, embeddings and a component catalogue. Search runs in the browser. Cloudflare Workers supply context to Gemini for Ask answers and View compositions. MiniLM creates the search embeddings locally through Transformers.js, and Fish Audio provides narration in my AI voice. The text API makes the public material available to visitors’ own agents.
## Find a passage in its original context
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:find-a-passage-in-its-original-context
Original https://www.henryw.me/#/aipersonalarchive#find-a-passage-in-its-original-context
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Afind-a-passage-in-its-original-context?format=text
As the site grew, I added Search so visitors could quickly find relevant material across its pages. Each result shows a matching passage and opens its place on the original page. Search combines lexical and semantic retrieval. Word matching finds names and technical terms, while embeddings find passages with related meaning.
## The archive as a space
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:seeing-the-archive-as-a-space
Original https://www.henryw.me/#/aipersonalarchive#seeing-the-archive-as-a-space
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aseeing-the-archive-as-a-space?format=text
The embedding map gives the archive a spatial form. Projects, research and personal writing appear together as a field of points. Their positions make patterns of similarity visible across material that lives on separate pages. UMAP, a dimensionality-reduction method, arranges these embeddings in two or three dimensions. Each dot represents a passage. Nearby dots tend to represent passages with similar meanings.
## Ask brings related passages into one answer
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:ask-brings-related-passages-into-one-answer
Original https://www.henryw.me/#/aipersonalarchive#ask-brings-related-passages-into-one-answer
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aask-brings-related-passages-into-one-answer?format=text
I built Ask to let the site respond directly to visitors’ questions. It uses retrieval-augmented generation (RAG), giving a language model relevant material from my work, ideas and experiences to draw on. The model returns a structured response, which the interface presents as an answer with a linked source list and follow-up questions.
## How does Ask handle different kinds of questions?
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:how-does-ask-handle-different-kinds-of-questions
Original https://www.henryw.me/#/aipersonalarchive#how-does-ask-handle-different-kinds-of-questions
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Ahow-does-ask-handle-different-kinds-of-questions?format=text
Ask classifies questions to choose an appropriate response. For questions about using the site, it offers a link or action. For questions about my work and ideas, it explains the relevant material and can offer a View for a fuller interpretation. 03 View
## View reorganises the site around a question
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:view-reorganises-the-site-around-a-question
Original https://www.henryw.me/#/aipersonalarchive#view-reorganises-the-site-around-a-question
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aview-reorganises-the-site-around-a-question?format=text
A View brings together my work, ideas and experiences around a visitor’s question. AI connects the selected material into a narrative and places the original works within it for visitors to explore. Different questions bring out different relationships in the same archive. A reading about learning might connect a research study with an education project, revealing something neither piece explains on its own.
## How does AI build an interpretation around a question?
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:how-does-ai-build-an-interpretation-around-a-question
Original https://www.henryw.me/#/aipersonalarchive#how-does-ai-build-an-interpretation-around-a-question
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Ahow-does-ai-build-an-interpretation-around-a-question?format=text
I registered written passages, image groups and working demos as reusable components. The model selects and places them within the narrative, explaining how each supports its interpretation. Visitors can read, examine and interact with the original work as they follow the argument. The model can use ideas beyond the archive to interpret my material.
## A reading to save and share
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:a-reading-to-save-and-share
Original https://www.henryw.me/#/aipersonalarchive#a-reading-to-save-and-share
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aa-reading-to-save-and-share?format=text
A saved View brings together its question, narrative, sources, illustrations and audio. Its permanent link lets the creator return to that version or share it with someone else. Creators can also publish a View in the shared collection. Other visitors can explore these readings and see the archive through someone else’s perspective. 04 Gallery
## Every View becomes an exhibition
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:every-view-becomes-an-exhibition
Original https://www.henryw.me/#/aipersonalarchive#every-view-becomes-an-exhibition
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aevery-view-becomes-an-exhibition?format=text
I turned each View into an exhibition so visitors could explore its perspective by moving among the original works. The narrative guides the visit, and visitors can pause to explore a photograph, passage or project and make connections of their own. Each section becomes a room, with photographs on walls, writing on reading stands and places on a globe.
## On desktop and phone
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:available-across-the-site
Original https://www.henryw.me/#/aipersonalarchive#available-across-the-site
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aavailable-across-the-site?format=text
Visitors can open Search, Ask, View and the embedding map from the header on any page. Home also has a question field, and wide screens add a search control beside the page. The Gallery and Exhibitions use different camera views, reading panels and controls on desktop, portrait phones and landscape phones. The demonstrations below show these layouts alongside the ways visitors can open the site’s tools.
## Exploring with your own agent
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:exploring-with-your-own-agent
Original https://www.henryw.me/#/aipersonalarchive#exploring-with-your-own-agent
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aexploring-with-your-own-agent?format=text
Visitors can give their agent henryw.me to explore my work, ideas and experiences. A reading guide and public text API provide the archive and links to the original pages, so the agent can read, connect and cite the material in its own response. How agents read the archive I export the site’s public writing as complete text and JSON records at build time.
## What can I learn from a website about myself?
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:what-the-case-gives-back
Original https://www.henryw.me/#/aipersonalarchive#what-the-case-gives-back
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Awhat-the-case-gives-back?format=text
Some things in my own life are easier to see through someone else’s questions. The experiences are familiar to me, yet the relationships a visitor asks about may be ones I have never considered. AI can develop those relationships into a reading I can follow, giving me a chance to reconsider what I already know about myself. My own perspective also changes with time.
## A Structure-Preserving RAG Ingestion Pipeline
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:overview
Original https://www.henryw.me/#/ragflow-pipeline
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Aoverview?format=text
Preserving document structure when preparing PDFs for an AI assistant At PwC, I evaluated and combined document-processing tools for an AI assistant that answers public enquiries using a client’s documents.
## Understanding what the client needed
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:understanding-the-client-requirements
Original https://www.henryw.me/#/ragflow-pipeline#understanding-the-client-requirements
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Aunderstanding-the-client-requirements?format=text
The assistant would find relevant passages in the client’s documents and give them to a language model to help answer a question, an approach known as retrieval-augmented generation (RAG). My task was to prepare the documents for that process. The requirements covered paragraphs and tables continuing across pages, complex table structures, references to distant notes and remarks, and flowcharts stored as images.
## Keeping a paragraph or table together across pages
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:why-one-pdf-needed-several-ways-of-reading
Original https://www.henryw.me/#/ragflow-pipeline#why-one-pdf-needed-several-ways-of-reading
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Awhy-one-pdf-needed-several-ways-of-reading?format=text
A page boundary can fall halfway through a paragraph or table. If extraction treats the next page as a fresh start, the resulting fragments may separate a passage from its continuation. I first tested how much an existing parser could recover. MinerU, a tool for converting PDFs into structured content, rejoined the interrupted paragraphs and tables in the test document.
## Preserving the structure inside a table
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:complex-tables
Original https://www.henryw.me/#/ragflow-pipeline#complex-tables
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Acomplex-tables?format=text
A merged cell can make one heading apply to several rows or columns. A nested table introduces a smaller set of relationships inside a single cell, such as the booking rules in this example. Flattening either into a sequence of words makes it harder to determine which condition governs which value.
## Retrieving a passage with the note it refers to
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:notes
Original https://www.henryw.me/#/ragflow-pipeline#notes
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Anotes?format=text
A sentence could cite Note (4) several pages before the note appeared. Extracting both passages accurately still left retrieval with two separate pieces. A question might match the citing passage closely while giving the search little reason to return the note it refers to. I needed to make their explicit reference part of the material being indexed.
## Making a flowchart’s decision logic searchable
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:mermaid
Original https://www.henryw.me/#/ragflow-pipeline#mermaid
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Amermaid?format=text
Many client documents used flowchart images to explain a procedure. An answer might depend on following a “Yes” branch through several conditions. OCR could recover the words in each box while losing the arrows that made them a decision. I also tested free-form VLM descriptions, which conveyed the overall process with varying levels of detail.
## Bringing the four requirements into one pipeline
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:what-i-tested-before-recommending-it
Original https://www.henryw.me/#/ragflow-pipeline#what-i-tested-before-recommending-it
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Awhat-i-tested-before-recommending-it?format=text
The recommended architecture combined MinerU with its built-in VLM, a post-parsing reference linker, and LlamaIndex. Parsing recovered document continuity and represented tables and diagrams in structured text. The linker attached referenced notes and remarks before LlamaIndex formed chunks for retrieval.
## Judging the whole solution
A Structure-Preserving RAG Ingestion Pipeline
Section ragflow-pipeline
Source ID ragflow-pipeline:judging-the-whole-solution
Original https://www.henryw.me/#/ragflow-pipeline#judging-the-whole-solution
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ragflow-pipeline%3Ajudging-the-whole-solution?format=text
Part of my role was deciding what would count as meeting a requirement. “Support complex tables” leaves several possibilities open. A tool might reproduce a table’s appearance, recover its hierarchy, or make that hierarchy available to the model answering a question. The client’s purpose determines which of these matters.
## Risk Assessment Across Long Documents
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:overview
Original https://www.henryw.me/#/document-review
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Aoverview?format=text
Reading long reports and connecting the evidence behind each finding At PwC, I designed and built an AI pipeline that reads long reports, extracts individual evidence records and combines them to assess different risks. Reviewers can inspect the reasoning and open the original source pages behind each finding. 01 Task and workflow
## A risk judgement can depend on evidence across the whole report.
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:prepare-the-evidence-for-a-decision
Original https://www.henryw.me/#/document-review#prepare-the-evidence-for-a-decision
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Aprepare-the-evidence-for-a-decision?format=text
The team needed to assess a defined set of risks in reports spanning hundreds of pages. Relevant observations appeared in the text, tables and appendices. A finding could depend on facts from several sections, each carrying its own context. I designed a workflow that reads every page, builds a shared collection of evidence and assesses each risk against that material.
## Assessment guidance defines what to collect and how to judge it
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:designing-around-delivery-constraints
Original https://www.henryw.me/#/document-review#designing-around-delivery-constraints
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Adesigning-around-delivery-constraints?format=text
I translated each risk’s definition into evidence requirements and decision rules. The requirements guide what the model extracts. The rules explain how those observations should be interpreted together. Optional source guidance identifies sections likely to contain useful context. 02 Evidence extraction
## Page-level extraction gives scattered observations a shared structure.
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:designing-reusable-evidence-records
Original https://www.henryw.me/#/document-review#designing-reusable-evidence-records
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Adesigning-reusable-evidence-records?format=text
I use the table of contents (TOC) and section headings to divide the report into chunks, capped at eight pages. This keeps related material together and makes each reading task manageable. The pages are rendered as images so a vision-language model (VLM) can read the layout of tables and visual material alongside the report’s text. Each chunk can produce several evidence records.
## Each risk is assessed against the collected evidence.
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:reusing-evidence-across-assessments
Original https://www.henryw.me/#/document-review#reusing-evidence-across-assessments
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Areusing-evidence-across-assessments?format=text
Each risk has a separate synthesis pass. It applies the decision rules to the relevant records, connects observations across pages and explains how they support or qualify a finding. Separating this judgement from extraction lets the assessment reason over the evidence gathered across the report. The model also receives the document index.
## Parallel processing makes full-report assessment practical
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:implementing-the-review-workflow
Original https://www.henryw.me/#/document-review#implementing-the-review-workflow
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Aimplementing-the-review-workflow?format=text
Independent chunks are read in parallel, followed by parallel risk assessments that reuse the shared ledger. Source-page checks can also run together when more context is needed. Across three sample reports of a few hundred pages, the estimated average was about five minutes and US$0.68 in model calls. The estimate combines measured page rendering with recorded model timings and usage. 04 Presenting the assessment
## The review interface keeps each finding beside its source.
Risk Assessment Across Long Documents
Section document-review
Source ID document-review:reviewing-findings-against-the-source
Original https://www.henryw.me/#/document-review#reviewing-findings-against-the-source
Read https://ask-henry.whenry6688.workers.dev/agent/sources/document-review%3Areviewing-findings-against-the-source?format=text
I organised the workspace around a finding list, an interpretation panel and a continuous report viewer. Selecting an interpretation opens its cited page while keeping the reasoning visible. This makes the evidence and the conclusion easy to compare. The Evidence Explorer shows which pages support the final assessment and what other context was considered. The interactive example below uses a fictional report.
## AI for IT Operations
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:overview
Original https://www.henryw.me/#/ai-it-operations
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Aoverview?format=text
Maintaining technical knowledge and carrying out service requests At PwC, I designed a system that uses AI to identify gaps in an IT assistant’s knowledge, research the missing information and keep its knowledge base up to date. I also built a browser agent that interprets service tickets and automates tasks in web applications. 00 Context
## Where AI can help in IT operations
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:ai-in-it-operations
Original https://www.henryw.me/#/ai-it-operations#ai-in-it-operations
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Aai-in-it-operations?format=text
Keeping an organisation’s technology running involves maintaining systems, investigating faults and supporting the people who use them. An IT team works across many products and has to keep up as their software and documentation change. At PwC, I researched how AI could help with this work, including making technical knowledge easier to consult and automating tasks in existing applications.
## Keeping the assistant’s knowledge useful
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:knowledge-management
Original https://www.henryw.me/#/ai-it-operations#knowledge-management
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Aknowledge-management?format=text
The IT assistant answers questions about using and maintaining systems. It retrieves relevant passages from technical documents and supplies them to a language model when composing an answer. This approach is known as retrieval-augmented generation (RAG). That collection, its knowledge base, needs continuing attention. Useful information may be missing, and documents already collected can become outdated.
## Where does the assistant need more knowledge?
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:where-does-the-assistant-need-more-knowledge
Original https://www.henryw.me/#/ai-it-operations#where-does-the-assistant-need-more-knowledge
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Awhere-does-the-assistant-need-more-knowledge?format=text
I used specific questions to identify gaps in the knowledge base. Guidance on renewing a security certificate, for example, might omit the steps that make an application use the replacement. Checking each question against the collected documents gives the next search a precise target. Unanswered user questions reveal immediate needs.
## Researching gaps in technical guidance
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:researching-gaps-in-technical-guidance
Original https://www.henryw.me/#/ai-it-operations#researching-gaps-in-technical-guidance
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Aresearching-gaps-in-technical-guidance?format=text
Several knowledge gaps can concern the same problem. Certificate expiry, renewal and a replacement that fails to take effect all concern the certificate lifecycle. I grouped related gaps into a shared research objective, giving the agent a reason to explore their connections. The individual questions stayed attached to the objective as concrete checks on what the research needed to cover.
## What happens when the guidance changes?
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:what-happens-when-the-guidance-changes
Original https://www.henryw.me/#/ai-it-operations#what-happens-when-the-guidance-changes
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Awhat-happens-when-the-guidance-changes?format=text
Adding a document to the knowledge base creates an ongoing maintenance task. The vendor may revise its instructions while the assistant still draws on the earlier copy. To check for those changes, the system needs to know where each document came from. I retained the original source URL when collecting the material so it could be revisited later.
## Processing and maintaining source material
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:from-a-source-to-maintained-knowledge
Original https://www.henryw.me/#/ai-it-operations#from-a-source-to-maintained-knowledge
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Afrom-a-source-to-maintained-knowledge?format=text
The crawler research covered Crawl4AI Adaptive, SiteOne, Mdream/crawl, Browsertrix, and Firecrawl OSS across Azure, SAP, ServiceNow, and Oracle documentation. The results informed the separation between deciding what knowledge to acquire and the mechanics of fetching and processing pages.
## Carrying out a service ticket in the browser
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:browser-control
Original https://www.henryw.me/#/ai-it-operations#browser-control
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Abrowser-control?format=text
The second area concerned service requests that an IT operator carries out in a browser. A ticket such as “Please give Alex Chen editor access to the Analytics workspace” describes an outcome. The operator still has to find the right account, workspace and permission in the application.
## Turning the request into actions
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:turning-the-request-into-actions
Original https://www.henryw.me/#/ai-it-operations#turning-the-request-into-actions
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Aturning-the-request-into-actions?format=text
Even a familiar task can unfold differently when an application shows a validation message or an operator edits a form. The agent needs to see the effect of each action before choosing the next one. I used an observation loop that reads the current page, chooses an action in relation to the ticket, and reads the result.
## Why a browser extension?
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:why-a-browser-extension
Original https://www.henryw.me/#/ai-it-operations#why-a-browser-extension
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Awhy-a-browser-extension?format=text
The agent needed access to internal applications and a place for the operator to work alongside it. A remote browser would need its own access to internal systems and a way for the operator to intervene. A local automation service could use the operator’s environment, but it would need separate installation and maintenance.
## Checking the result and keeping a task record
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:a-place-to-start-intervene-and-look-back
Original https://www.henryw.me/#/ai-it-operations#a-place-to-start-intervene-and-look-back
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Aa-place-to-start-intervene-and-look-back?format=text
After executing a request, the agent checks the application’s confirmation and records the outcome alongside the actions and human decisions that led to it. The operator can return to the ticket on the dashboard to review the completed work. Inside Browser Control Planning, browser actions, and task history +
## The browser agent’s execution loop
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:from-planning-to-a-browser-action
Original https://www.henryw.me/#/ai-it-operations#from-planning-to-a-browser-action
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Afrom-planning-to-a-browser-action?format=text
A FastAPI service manages browser tasks. LangGraph retains the request, page observations, action history, and human decisions as the planner moves between steps. Pausing for approval or manual input preserves the same task so it can resume afterwards. Playwright sends structured actions through a relay to the browser extension.
## What to automate, and how
AI for IT Operations
Section ai-it-operations
Source ID ai-it-operations:where-judgement-changes-hands
Original https://www.henryw.me/#/ai-it-operations#where-judgement-changes-hands
Read https://ask-henry.whenry6688.workers.dev/agent/sources/ai-it-operations%3Awhere-judgement-changes-hands?format=text
Across both parts of the platform, I approached automation at the level of individual decisions within a task. Researching a question, proposing an update, accepting the guidance and applying the change each require different information and judgement.
## Fragments
Fragments
Section fragments
Source ID fragments:overview
Original https://www.henryw.me/#/fragments
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aoverview?format=text
I write down thoughts and memories before they fade, so I can return to what I was thinking and how life felt at the time. You’re welcome to look through them and get to know me a little beyond my work.
## The Projection of Thought
Fragments
Section fragments
Source ID fragments:the-projection-of-thought
Original https://www.henryw.me/#/fragments#the-projection-of-thought
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Athe-projection-of-thought?format=text
I used to think of expression mainly as compression. A thought is larger than a sentence, so putting it into words means choosing an order, making some relations explicit, and leaving other things out. That still feels true, but compression alone makes the thought sound too fixed, as if it were a complete object that language merely made smaller.
## Rebuilding Another State Inside Me
Fragments
Section fragments
Source ID fragments:rebuilding-another-state-inside-me
Original https://www.henryw.me/#/fragments#rebuilding-another-state-inside-me
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Arebuilding-another-state-inside-me?format=text
I cannot enter another person's internal state directly. Their body, memory, history, habits, fear, shame, desire, and the way a particular event touches all of these remain inside them. What reaches me is what comes out: words, facial expression, tone, silence, movement, posture, the story they tell, what they avoid saying, and the situation around them. These are traces from a system I cannot open from the inside.
## The Visible Part of the Mind
Fragments
Section fragments
Source ID fragments:visible-part-of-the-mind
Original https://www.henryw.me/#/fragments#visible-part-of-the-mind
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Avisible-part-of-the-mind?format=text
Sometimes what I consciously think feels much smaller than what is moving inside my mind. A thought appears clearly enough for me to hold, say, or write down, and because it is the part I can reach, I may take it for the whole thought.
## Before Defining Understanding
Fragments
Section fragments
Source ID fragments:understanding-before-definition
Original https://www.henryw.me/#/fragments#understanding-before-definition
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aunderstanding-before-definition?format=text
I do not want to define understanding too early. The word clearly points to something important, but it gathers many questions before they have been separated. Sometimes understanding means giving the right answer. Elsewhere it means explaining, transferring, generalising, correcting, compressing, using, grounding, experiencing, or being conscious of something. These may be related, but they are not identical.
## Expression, Recording, and the Compressed Version of Thought
Fragments
Section fragments
Source ID fragments:expression-recording
Original https://www.henryw.me/#/fragments#expression-recording
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aexpression-recording?format=text
When a thought is still in my head, it is usually not a complete sentence. It is closer to a mixture of feeling, direction, memory, and relations that I cannot yet explain. To express it, I have to choose words, divide what was mixed together, and put the parts in an order. This makes the thought available to other people and to my later self.
## Rich Traces and Open Paths
Fragments
Section fragments
Source ID fragments:rich-traces-and-open-paths
Original https://www.henryw.me/#/fragments#rich-traces-and-open-paths
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Arich-traces-and-open-paths?format=text
I often use voice input when I talk to AI. The obvious reason is speed. I can keep speaking before a thought disappears. But voice also preserves more of the process by which the thought is forming. A typed prompt is often already cleaned up. Before typing, I tend to choose a direction, remove hesitation, and turn the thought into something that resembles a well-defined request.
## Labels, Goals, and Rules as Ways of Shaping People
Fragments
Section fragments
Source ID fragments:labels-goals-rules
Original https://www.henryw.me/#/fragments#labels-goals-rules
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Alabels-goals-rules?format=text
If language can compress thought, labels can compress people. A person contains experiences, habits, desires, fears, abilities, contradictions, and tendencies that do not naturally arrive in neat categories. We are not born already divided into personality type, occupation, research direction, hobbies, values, and life stages.
## Memory Compresses Time, but the Self Is Changed by Passing Through It
Fragments
Section fragments
Source ID fragments:memory-time-self
Original https://www.henryw.me/#/fragments#memory-time-self
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Amemory-time-self?format=text
Life does not arrive already divided into chapters. While I am living it, one day follows another and many changes have no visible border. Only later do I describe one period as high school, another as university, one year as a turning point, or one city as the place where I changed. Memory helps create those divisions because it cannot preserve continuous life at the same resolution forever.
## Satisfaction Is Not a Fixed Reward
Fragments
Section fragments
Source ID fragments:satisfaction-signal
Original https://www.henryw.me/#/fragments#satisfaction-signal
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Asatisfaction-signal?format=text
I sometimes wonder whether happiness can be understood partly through satisfaction. This is not meant as a complete definition. Happiness may also involve meaning, relationships, value, security, and many other things. But satisfaction becomes more useful to think with once it is not reduced to immediate pleasure.
## Oysters and Black Truffle Toast at Queen Victoria Market
Fragments
Section fragments
Source ID fragments:queen-victoria-market-toast-oysters
Original https://www.henryw.me/#/fragments#queen-victoria-market-toast-oysters
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aqueen-victoria-market-toast-oysters?format=text
Queen Victoria Market in Melbourne gave me one of those food memories I still think about after leaving the city. The oysters were fresh, cold, and clean, and a squeeze of lemon made the taste even sharper and clearer. The black truffle toast was unexpectedly good too. It was warm, rich, fragrant, and straightforward. What fixes it in my memory is that I went with my sister on my last day of the Melbourne exchange.
## Chaoshan Beef Hot Pot in Guangzhou
Fragments
Section fragments
Source ID fragments:guangzhou-chaoshan-beef-hot-pot
Original https://www.henryw.me/#/fragments#guangzhou-chaoshan-beef-hot-pot
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aguangzhou-chaoshan-beef-hot-pot?format=text
When I travelled to Guangzhou with my father, we went for Chaoshan beef hot pot. I especially liked the beef balls and diaolong, a tender sliced cut commonly served in Chaoshan hot pot. The beef balls were springy and strongly beefy, while the diaolong was softer and cleaner in flavour. I usually ate both without dipping sauce because I preferred tasting the beef and broth directly.
## AI-Generated Kitten Videos and Manufactured Cuteness
Fragments
Section fragments
Source ID fragments:ai-generated-kitten-videos
Original https://www.henryw.me/#/fragments#ai-generated-kitten-videos
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aai-generated-kitten-videos?format=text
I have seen a lot of AI-generated videos on social media where kittens interact with people, along with more surreal ones, like a plush watermelon being opened to reveal little kittens inside. I find them very cute, and clearly plenty of other people do too. These videos interest me because synthetic scenes can trigger real emotion.
## A Conversation About Identity
Fragments
Section fragments
Source ID fragments:identity-interview-reflection
Original https://www.henryw.me/#/fragments#identity-interview-reflection
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aidentity-interview-reflection?format=text
I once took part in an interview about identity and about growing up with a Taiwanese family background while living mostly in Shanghai. I had not planned to write about it publicly, but the conversation helped me organize a lot of scattered feelings that had sat in the background for a long time. Identity does not have to be a single answer.
## Napier Seaside with My Mother
Fragments
Section fragments
Source ID fragments:napier-seaside-with-my-mother
Original https://www.henryw.me/#/fragments#napier-seaside-with-my-mother
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Anapier-seaside-with-my-mother?format=text
Napier seaside is one of the places I connect with my mother. She lives around Hastings and Havelock North, and when I went back to New Zealand she would sometimes drive me to Napier. It was not a big trip, just a short drive to the water. I still remember it quite clearly: the car ride, the road, arriving near the sea, walking for a while, maybe not even talking much.
## My Mother’s Cooking Across Places
Fragments
Section fragments
Source ID fragments:mothers-cooking-across-places
Original https://www.henryw.me/#/fragments#mothers-cooking-across-places
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Amothers-cooking-across-places?format=text
My mother has always been good at making food that is both healthy and tastes good. When we were still living together in Shanghai, this felt completely normal. She cooked at home and I ate what she made, and at the time I did not think of it as anything worth remembering. It was just part of home. Later, after life became more scattered and she spent more time in New Zealand, her cooking started to feel different.
## Trying Golf with My Mother in New Zealand
Fragments
Section fragments
Source ID fragments:golf-with-my-mother-in-new-zealand
Original https://www.henryw.me/#/fragments#golf-with-my-mother-in-new-zealand
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Agolf-with-my-mother-in-new-zealand?format=text
When I visited my mother in New Zealand, she sometimes brought me along to play golf. It is one of her hobbies, and I could tell she enjoyed the whole rhythm of it: the open grass, the slow walking, choosing a club, taking her time before a shot. It suited her. I tried a few times, but I never felt I had much talent for it.
## Racket Games with the SLR Lab
Fragments
Section fragments
Source ID fragments:slr-lab-racket-games
Original https://www.henryw.me/#/fragments#slr-lab-racket-games
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aslr-lab-racket-games?format=text
Our principal investigator at the Speech, Language and Reading Lab once took another research assistant and me to play badminton and table tennis. We played, missed shots, picked up balls, laughed a bit, and drifted between the two games. I liked spending time together away from papers, meetings and tasks. That afternoon made the lab feel warmer to me.
## The Sea in My Early Hong Kong Years
Fragments
Section fragments
Source ID fragments:kennedy-town-seaside-hku-years
Original https://www.henryw.me/#/fragments#kennedy-town-seaside-hku-years
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Akennedy-town-seaside-hku-years?format=text
I have not been to Kennedy Town's waterfront much lately, which feels strange because it was much more present during my first years at HKU. I lived closer to that side of the city then, and the sea was somewhere I could reach without turning the visit into a plan. I do not remember every walk clearly now. Those walks have probably settled into a general feeling.
## Ferry Rides Across Sydney Harbour
Fragments
Section fragments
Source ID fragments:sydney-harbour-ferry-rides
Original https://www.henryw.me/#/fragments#sydney-harbour-ferry-rides
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Asydney-harbour-ferry-rides?format=text
One of my strongest memories of Sydney is travelling through the harbour by ferry. The public ferries were inexpensive, so we used them repeatedly to travel between different stops. Seeing the city from the water made it feel less like a fixed map and more like a sequence of changing views. Some routes passed the Opera House and Harbour Bridge, where the city looked as beautiful as its photographs suggest.
## Gold Coast, Water, and the City Line
Fragments
Section fragments
Source ID fragments:gold-coast-water-and-city-line
Original https://www.henryw.me/#/fragments#gold-coast-water-and-city-line
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Agold-coast-water-and-city-line?format=text
Gold Coast is one of the places where I remember the sea as something I entered rather than only looked at. We went kayaking, jet skiing, snorkelling, and parasailing. What I remember most is the physical side of it, especially the speed, wind, noise, and the feeling that the water had moved from the background into the activity itself. I also remember going up to an observation deck and seeing the coast from above.
## A Road Trip Along the Great Ocean Road
Fragments
Section fragments
Source ID fragments:great-ocean-road-melbourne-friends
Original https://www.henryw.me/#/fragments#great-ocean-road-melbourne-friends
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Agreat-ocean-road-melbourne-friends?format=text
The easiest thing to say about the Great Ocean Road is that it was beautiful, but the road matters to me because of the people who took me there. During my Melbourne exchange, friends rented a car and brought us along. Without them, it might have remained a place I knew I should visit. Because of them, it became part of my life during that semester.
## A Birthday Somewhere Along Taiwan’s East Coast
Fragments
Section fragments
Source ID fragments:taiwan-east-coast-family-road-trip
Original https://www.henryw.me/#/fragments#taiwan-east-coast-family-road-trip
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Ataiwan-east-coast-family-road-trip?format=text
One of my happiest recent family memories is a road trip along Taiwan's east coast. It was the four of us, my father, my mother, my sister, and me. My father drove, and we made our way down the eastern side of the island, stopping in different places along the way. I do not remember every exact turn now, and maybe that is fine. What I remember most is the feeling of the four of us being together in one car.
## The Tomatoes of August 29
Fragments
Section fragments
Source ID fragments:tomatoes-of-august-29
Original https://www.henryw.me/#/fragments#tomatoes-of-august-29
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Atomatoes-of-august-29?format=text
On August 29, I opened the fridge before leaving home and saw the tomatoes my father had given me two weeks earlier. We had met in Shenzhen while he was there for work. I had hesitated when he first offered them because I rarely eat fruit and always find washing it inconvenient. He listened, washed a box himself, and gave it to me ready to carry back to Hong Kong. Half of them were already gone.
## Athens, Ruins, and a Rare Family Trip
Fragments
Section fragments
Source ID fragments:athens-ruins-and-family-trip
Original https://www.henryw.me/#/fragments#athens-ruins-and-family-trip
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aathens-ruins-and-family-trip?format=text
Our family trip to Greece stayed with me partly because the four of us rarely have two uninterrupted weeks together now. We spent most of the time around Athens, walking through the city, visiting historical sites, and eating together. The place felt different from cities I knew because the past was not contained in a museum. It remained visible in the stone, streets, and landscape around ordinary life.
## Swimming in the Mediterranean
Fragments
Section fragments
Source ID fragments:swimming-in-the-mediterranean
Original https://www.henryw.me/#/fragments#swimming-in-the-mediterranean
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Aswimming-in-the-mediterranean?format=text
One of my clearest memories from Greece is swimming in the Mediterranean. We went out by boat, with the sun above us, open water around us, and my family nearby. Before that trip, the Mediterranean had mostly been a name from maps, history, and photographs of Greece. Then I was in the water rather than looking at it from the shore. I think it was the only time I swam there, which may be why the memory feels so fixed.
## Rainy Days as Permission to Stay In
Fragments
Section fragments
Source ID fragments:rainy-days-permission-to-stay-in
Original https://www.henryw.me/#/fragments#rainy-days-permission-to-stay-in
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Arainy-days-permission-to-stay-in?format=text
I do not actually like rainy days that much. Rain is inconvenient. The ground gets wet, the sky turns grey, and going anywhere becomes a little more annoying. But there is one thing I do like about it, which is that it gives me a reason not to go out. On a sunny day, staying inside can feel like wasting the day.
## The Mental Map of a Small Room
Fragments
Section fragments
Source ID fragments:mental-map-of-small-room
Original https://www.henryw.me/#/fragments#mental-map-of-small-room
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Amental-map-of-small-room?format=text
My mother sometimes says my room is messy, and she is probably not entirely wrong. From the outside it can look like things are scattered everywhere. But to me the room is not simply messy, because I usually know where everything is. There is a map of it in my head. That map is not visible to anyone else. A book on one side, a cable somewhere else, a camera lens near the window, some small thing on the desk.
## My First Camera and Another Way of Seeing
Fragments
Section fragments
Source ID fragments:first-camera-another-way-of-seeing
Original https://www.henryw.me/#/fragments#first-camera-another-way-of-seeing
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Afirst-camera-another-way-of-seeing?format=text
My Nikon Zfc was my first real camera. At the start I did not even need to go far. I would stand in the apartment and shoot through the small window, trying different angles and looking for things outside that I would not normally notice. After I got a longer lens it became even more interesting, since the lens could pull distant things closer and turn a random view out the window into something worth looking at.
## Music That Became More Spacious
Fragments
Section fragments
Source ID fragments:music-that-became-more-spacious
Original https://www.henryw.me/#/fragments#music-that-became-more-spacious
Read https://ask-henry.whenry6688.workers.dev/agent/sources/fragments%3Amusic-that-became-more-spacious?format=text
My music taste has changed quite a bit. In high school I was more drawn to music with strong rhythm, EDM and rap and beats that moved quickly and gave a direct kind of energy. I still understand why I liked it. That kind of music pushes you forward, and it is useful when you want intensity or speed or just a clear hit of momentum. These days I find myself drawn to music that feels more spacious.
## Profile
CV
Section cv
Source ID cv:profile
Original https://www.henryw.me/#/cv#profile
Read https://ask-henry.whenry6688.workers.dev/agent/sources/cv%3Aprofile?format=text
Fourth-year Applied Artificial Intelligence student at the University of Hong Kong. I’m interested in how people form and use knowledge, how representations and internal processes support behaviour in AI systems, and how learning and thinking change when people work with AI.
## Education
CV
Section cv
Source ID cv:education
Original https://www.henryw.me/#/cv#education
Read https://ask-henry.whenry6688.workers.dev/agent/sources/cv%3Aeducation?format=text
University of Hong Kong Sep 2022 – Present BASc in Applied Artificial Intelligence Coursework across machine learning, deep learning, data science, algorithms, and the mathematics behind them. Dean’s Honours List, Student Peer Advisor, and Staff–Student Consultative Committee representative.
## Experience
CV
Section cv
Source ID cv:experience
Original https://www.henryw.me/#/cv#experience
Read https://ask-henry.whenry6688.workers.dev/agent/sources/cv%3Aexperience?format=text
Cloud, Data & AI Consulting Intern Jul 2026 – Dec 2026 PwC, Hong Kong Designed an AI-assisted knowledge management architecture that identifies gaps, acquires missing material and keeps technical guidance up to date.
## Publications & Preprints
CV
Section cv
Source ID cv:publications-preprints
Original https://www.henryw.me/#/cv#publications-preprints
Read https://ask-henry.whenry6688.workers.dev/agent/sources/cv%3Apublications-preprints?format=text
Early Epistemic Settlement in AI-Assisted Writing H. Wang Under review · arXiv:2609.09332 BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval H. Su*, H. Yen*, M. Xia*, W. Shi, N. Muennighoff, H. Wang , H. Liu, Q. Shi, Z. S. Siegel, M. Tang, R. Sun, J. Yoon, S. O. Arik, D. Chen, T. Yu ICLR 2025 Spotlight; arXiv:2407.12883
## Projects
CV
Section cv
Source ID cv:projects
Original https://www.henryw.me/#/cv#projects
Read https://ask-henry.whenry6688.workers.dev/agent/sources/cv%3Aprojects?format=text
AI × Self Jun 2026 – Present An AI-driven personal archive Built a personal archive combining hybrid search, retrieval-augmented answers and AI-composed Views. Each View connects my work, ideas and experiences around a visitor’s question and becomes an illustrated article and an interactive 3D exhibition.
## About Me
About
Section about
Source ID about:root:about-me
Original https://www.henryw.me/#/about
Read https://ask-henry.whenry6688.workers.dev/agent/sources/about%3Aroot%3Aabout-me?format=text
I was born in Taiwan , grew up in Shanghai , and now study Applied AI at the University of Hong Kong . Alongside my studies, I work in AI consulting at PwC. I explore ideas and develop models to understand how things work. When I see a way to put that understanding to use, I design and build something around it. My research explores how people and AI systems learn from experience and use their knowledge.
## I study how people and machines learn
About
Section about
Source ID about:section:how-i-research-and-build
Original https://www.henryw.me/#/about#how-i-research-and-build
Read https://ask-henry.whenry6688.workers.dev/agent/sources/about%3Asection%3Ahow-i-research-and-build?format=text
My research explores how people and AI systems learn from experience and use their knowledge. I also examine how interacting with AI shapes the way we think and learn.
## I want to remember what life felt like
About
Section about
Source ID about:section:outside-work
Original https://www.henryw.me/#/about#outside-work
Read https://ask-henry.whenry6688.workers.dev/agent/sources/about%3Asection%3Aoutside-work?format=text
My mother used to drive me to the coast near Napier , where we would sit and watch the sea for hours. In Hong Kong , I spent evenings on the waterfront at Kennedy Town. As AI becomes part of everyday life, I value having a record of my own thoughts and feelings. I write them down in Fragments before they fade.
## Say Hello
About
Section about
Source ID about:contact
Original https://www.henryw.me/#/about#say-hello
Read https://ask-henry.whenry6688.workers.dev/agent/sources/about%3Acontact?format=text
I'd love to hear from you. Personal messages to whenry6688@gmail.com Academic matters to henry.why@connect.hku.hk
## Why SlidePoise
SlidePoise
Section slidepoise
Source ID slidepoise:purpose
Original https://www.henryw.me/slidepoise/#why-slidepoise
Read https://ask-henry.whenry6688.workers.dev/agent/sources/slidepoise%3Apurpose?format=text
Each slide needs a layout that serves its message and objects you can edit. Template-based workflows can limit how freely a slide’s layout responds to its content. Image generation makes it possible to explore layouts around the content of a slide. Turning a chosen design into a useful deck also requires accurate text, editable charts and a consistent visual style.
## How SlidePoise works
SlidePoise
Section slidepoise
Source ID slidepoise:philosophy
Original https://www.henryw.me/slidepoise/#philosophy
Read https://ask-henry.whenry6688.workers.dev/agent/sources/slidepoise%3Aphilosophy?format=text
Explore the four stages through the consulting presentation. The brief guides reference selection and image generation. The selected design guides reconstruction, and the rendered PowerPoint is checked against both the brief and the design. The Agent reviews your brief and source material, researching useful facts, examples and context where needed.
## The View Gallery introduction
AI × Self
Section aipersonalarchive
Source ID interactive.archive.gallery-video
Original https://www.henryw.me/#/aipersonalarchive#gallery-video
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.archive.gallery-video?format=text
Henry’s 1 minute 42 second video introduces The View Gallery. It follows a visitor’s question as AI connects his work, ideas and experiences into a View, then shows the exhibition, original exhibits, audio guide and sharing in the Gallery. Visitors explore Henry’s work, ideas and experiences through their own questions. AI connects original material into a story shaped by the question. Henry calls that a View.
## An exhibition ticket
AI × Self
Section aipersonalarchive
Source ID interactive.archive.exhibition-ticket
Original https://www.henryw.me/#/aipersonalarchive#sample-exhibition-ticket
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.archive.exhibition-ticket?format=text
The View Gallery gives each selected exhibition a ticket with its title, illustration, creation date and number. Its reverse carries the summary. The ticket records visit progress and marks a completed visit with a dated stamp.
## The View Gallery design
AI × Self
Section aipersonalarchive
Source ID interactive.archive.gallery-design
Original https://www.henryw.me/#/aipersonalarchive#gallery-design-study
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.archive.gallery-design?format=text
The View Gallery brings shared exhibitions into one building. Four interactive studies show its interior, building form, floor plan and light and dark treatments together. The Gallery interior. I gathered the collection, the archive and the exhibition entrance around one open Hall. The building as a whole. A central Hall connects the archive court and exhibition wings. Orientation within the Gallery.
## Designing the exhibition
AI × Self
Section aipersonalarchive
Source ID interactive.archive.exhibition-design
Original https://www.henryw.me/#/aipersonalarchive#the-exhibition-is-designed-as-one-experience
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.archive.exhibition-design?format=text
Henry designed the exhibition to make reading a View feel like an immersive visit. Eight design studies explain arrival, wall writing, objects, the afterword, the visit map, lighting, audio narration and language. Entering the exhibition. The entrance gives visitors a moment to understand the exhibition before stepping inside.
## Exploring the archive
AI × Self
Section aipersonalarchive
Source ID interactive.archive.illustration.main
Original https://www.henryw.me/#/aipersonalarchive#archive-overview-illustration
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.archive.illustration.main?format=text
Questions bring original material into answers, composed readings and exhibitions. Search finds a passage, Ask gives an answer with a citation, and View composes articles and exhibitions. Three saved Views appear above The View Gallery’s architectural model and ticket.
## A composed View
AI × Self
Section aipersonalarchive
Source ID interactive.archive.illustration.view
Original https://www.henryw.me/#/aipersonalarchive#archive-view-illustration
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.archive.illustration.view?format=text
AI connects original material around a visitor’s question, composing a View to read as an article or explore as an exhibition. Visitors bring different questions about Henry’s life, research and design. A question about what Henry’s memories reveal about him brings photographs, a reflection on identity and a travel globe into a View shown as an article and exhibition.
## SlidePoise introduction
SlidePoise
Section slidepoise
Source ID interactive.slidepoise.video
Original https://www.henryw.me/slidepoise/#overview
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.slidepoise.video?format=text
Henry’s two-minute video demonstrates SlidePoise, his open-source skill for creating editable PowerPoint presentations with an AI Agent. It follows content planning, asset selection, image generation, OpenCV measurement and reconstruction, then shows editable slides and reusable visual styles. The visitor gives the Agent a brief, source material and a preferred style.
## Cathay Flex introduction
Cathay Flex
Section projects
Source ID interactive.cathayflex.video
Original https://www.henryw.me/#/projects#cathayflex
Read https://ask-henry.whenry6688.workers.dev/agent/sources/interactive.cathayflex.video?format=text
A narrated demonstration of Cathay Flex, Henry’s team project for the Cathay Pacific Hackathon. Travellers earn credits by accepting suitable travel changes and use those credits across services and future journeys. The video shows how AI, constrained optimisation and a transaction and settlement system coordinate these arrangements.
## Places and moments
Travels
Section travels
Source ID about:gallery
Original https://www.henryw.me/#/travels#showcaseimages
Read https://ask-henry.whenry6688.workers.dev/agent/sources/about%3Agallery?format=text
A gallery of places and moments from Henry's travels and everyday life.