Henry's public source catalogue
# Henry's public source catalogue
Content revision 4e771eaf0390cc87b6c7c6fd8469f3508f6ceeec7119472e6c1ccf17e2e1e5d2
138 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
These places have shaped a lot of who I am today.
## 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 , followed by 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 gave me a direct experience of everyday school life in New Zealand. 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 work on AI and data systems for financial-services and public-sector clients, combining solution architecture with hands-on development. I translate business needs into technical requirements and evaluate how existing tools can work together within the client’s constraints.
## 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
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 on how insurance products are configured in a banking app across markets. I connected each product’s business requirements to the screens and fields it needed, then automated the configuration process. Shared mapping rules gave the team a way to carry changes in requirements through to the app.
## 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 digital content, bringing its study-tour and travel programmes into a coherent online presence. 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.
## 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.
## 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.
## 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.
## Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override
Research
Section research
Source ID research:priorsPersist
Original https://www.henryw.me/#/research#priorsPersist
Read https://ask-henry.whenry6688.workers.dev/agent/sources/research%3ApriorsPersist?format=text
I investigated how language models follow a new instruction while established knowledge continues to influence their responses. I designed a Stroop-style task that puts a familiar association in conflict with a temporary definition. A prompt might define doctor as forest , while the usual association with hospital competes with that instruction.
## 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
AI × Self lets visitors bring their own questions to my work, ideas and experiences. Each question can become a View, a narrative that connects original material into a particular perspective. The Gallery gathers these perspectives into exhibitions people can explore and share. As the archive grows, it records both what I have made and the ways others come to understand it.
## 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. AI helps develop the content and explore compositions using your references and assets. The Agent interprets the chosen design, OpenCV measures its geometry, and local tools reconstruct the slides as editable objects.
## 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.
## Lexaday
Builds
Section projects
Source ID projects:lexaday
Original https://www.henryw.me/#/projects?to=lexaday
Read https://ask-henry.whenry6688.workers.dev/agent/sources/projects%3Alexaday?format=text
Lexaday began with an interest in images as memory cues for vocabulary. Giving every word its own image would create a large collection of separate associations. I built the lessons around shared roots, pairing each root with an AI-generated image and related words so the same visual association could support later learning. Personalised spaced repetition brings earlier roots back alongside new material.
## 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.
## Where I've Wandered
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
Some of the places I've been, with a photo from each. 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.
## 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, with rules specifying the components it needed. 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
Try changing the trip type, destination or length below and follow the effect through the highlighted rules to the packing list. Notice how a choice can reveal a follow-up question, and how separate decision tables each contribute to the final output.
## 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 product specifications through a dynamic form, and the engine automatically applied the decision tables to generate the required UI-component configuration. Follow-up fields appeared according to conditions expressed in a small notation. The roughly 32 KB VBA engine evaluated these definitions alongside the mapping rules.
## 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 Lexaday explores whether an image attached to a word root can help learners develop a feel for its meaning across a family of words. Each lesson combines a generated image with a family of related words, and a personalised review schedule brings those connections back over time.
## 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. The intervals increase through one, two, four, eight, and progressively more 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.
## 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.
## 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.
## 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.
## 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 an answer that connects the policy to their purchase and helps them take the next step. For this course project, we built an assistant that retrieves relevant information, works with order records and carries out support actions through conversation.
## 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
” 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.
## 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. 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.
## 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 The work, ideas and experiences collected here reflect different parts of my life. AI × Self lets visitors connect them through their own questions. A question about the places that shaped me, for example, brings travel records and personal writing into a View, a composed reading with its original sources.
## 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 curiosity can cross all of those boundaries. Questions about how I think, what I build or where I have lived can bring together material I published years apart and for different reasons.
## 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
Opening a long project page still leaves a visitor looking for the passage that answers their question. I made each Search result show the matching text and open its precise location. A visitor may remember a project’s name, or only the idea that made it interesting. Search accommodates both.
## 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
Once the passages had embeddings, numerical representations of their meaning, I could compare them with one another as well as with a query. That suggested another way to explore the collection. Material filed under research, work, or personal writing could sit together because of what it discussed.
## 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
Each answer includes citations that lead into the relevant projects and writing. Suggested follow-up questions help a visitor develop an overview into a closer look at a decision, experience or connection. Visitors can also listen to the answer in an AI voice trained on recordings of my own voice.
## 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
Trying a project’s demo reveals how it behaves. Photographs bring places and experiences into view, while a piece of writing preserves how I understood an idea at the time. In a View, these original pieces become part of the explanation, appearing where they help develop its meaning. Each response becomes a composed reading.
## 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
The question behind a View sets the exhibition’s theme. Its sections form a sequence of rooms, and the original material becomes the work on display. The Gallery opens in a shared entrance hall where visitors can browse exhibitions created by other people or compose a View around their own question. I gave these activities a place in the room.
## Inside an exhibition
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:article-and-exhibition-keep-the-same-place
Original https://www.henryw.me/#/aipersonalarchive#article-and-exhibition-keep-the-same-place
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Aarticle-and-exhibition-keep-the-same-place?format=text
An exhibition lets visitors encounter the material as they follow a View. A photograph can fill a wall, a piece of writing can occupy a reading stand, and a record of places can become a globe. The narrative stays beside the work, explaining what connects it to the question. Visitors can also read the View as an article.
## Designing an immersive visit
AI × Self
Section aipersonalarchive
Source ID aipersonalarchive:the-exhibition-is-designed-as-one-experience
Original https://www.henryw.me/#/aipersonalarchive#the-exhibition-is-designed-as-one-experience
Read https://ask-henry.whenry6688.workers.dev/agent/sources/aipersonalarchive%3Athe-exhibition-is-designed-as-one-experience?format=text
I designed the building, displays and guidance together. The open layout helps people find their way, display forms suit the original material, and light and sound shape how they attend to the works.
## 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
Search, Ask, View and Gallery share the site’s published material. Each site build prepares passages with links to their original locations, embeddings that represent their meaning, and a catalogue of the material available for composition. The catalogue includes descriptions of interactive components, so the system can select a working example alongside a written passage.
## Returning to my own archive
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
Keeping this site gives me a record of what I could articulate at different moments. Reading across it raises other questions. A fragment can take on a different meaning beside a project I made later. An experience can help me understand why an earlier idea mattered. A View gives one of these readings a form I can revisit.
## 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.
## 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 carries out tasks in the applications the team already uses.
## 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 platform includes an assistant that answers questions about using and maintaining IT systems. It searches a collection of technical documents and uses relevant passages to help compose each answer, an approach 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
Before collecting more documents, I needed to identify what information was missing. Having material on a topic does not tell us which questions it can answer. Documentation on certificates might explain how to renew one while leaving out how to get an application to use its replacement.
## 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, with extra installation and maintenance. I compared those options with an extension that could combine control and interaction inside Chrome or Edge.
## 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. The meal stayed with me partly because the food was good and partly because it became one of the moments attached to that trip with him. I especially liked the beef balls and diaolong, a tender sliced cut commonly served in Chaoshan hot pot.
## 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. What interests me is not just that they are cute, but that they show generative content triggering 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. What I took from the conversation was not a dramatic conclusion but a quieter one.
## 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 genuinely 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.
## 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. 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
One time the PI of our SLR Lab took me and another RA out to play badminton and table tennis. It was not a serious sports day. We played, missed shots, picked up balls, laughed a bit, and drifted between the two games in the slightly messy way small group outings usually go. I liked it because it made the lab feel like more than papers, meetings, and tasks.
## 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. Much of the routine has 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 not standing at a landmark but moving 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.
## 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. The day did not have much of a plot, but it stayed with me more clearly than many carefully planned sights. Before that trip, the Mediterranean had mostly been a name from maps, history, and photographs of Greece.
## 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. 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. Built a structure-preserving RAG ingestion pipeline for complex documents and an LLM-assisted pipeline that recovers legacy ETL logic for data migration.
## 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
Human-AI interaction and collaboration Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation H. Wang Under review; arXiv:2606. 26502 Language models, behavior, and interpretability BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval H. Yu ICLR 2025 Spotlight; arXiv:2407. 12883 Han-yu Wang (Henry) Last updated September 2026
## 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'm Han-yu Wang, and you can call me Henry. I was born in Taiwan , grew up in Shanghai , and now study in Hong Kong . I'm a fourth-year student majoring in Applied Artificial Intelligence at the University of Hong Kong. Alongside my studies, I'm currently working in AI consulting at PwC. Across my studies and work, I'm drawn to things that are still taking shape.
## How I Research and Build
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
How we learn and think In my Research , I work across human learning, AI models, and human-AI interaction. I study how people and machines learn from experience, how what they learn is represented and used, and how it shapes what they can do later.
## Outside work
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
I like the open space by the sea. In Hawke's Bay , my mother would drive me to the coast near Napier . In Hong Kong , I spent time at Kennedy Town Praya during my early university years. When I travel, I also like taking ferries and walking along the waterfront. I like travelling, and I often keep a photograph or a few notes from a trip.
## 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
If you want to get in touch, I'd be glad to hear from you. For personal messages, write to me at whenry6688@gmail.com . For academic matters, reach me at 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
Agentic slide generation needs both freedom of layout and control over the final deck. Fixed templates keep layouts consistent, but restrict how content can be presented. Image generation allows freer design, yet leaves the work of maintaining consistency and turning those designs into accurate, editable slides.
## 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
The Agent plans what the presentation should communicate and how the slides fit together. An image model explores layouts using that content, your style references and selected assets. To turn a chosen design into PowerPoint, the Agent identifies its objects and their relationships while local tools measure their geometry.
## Places and moments
About
Section about
Source ID about:gallery
Original https://www.henryw.me/#/about#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.
## What Henry is currently doing
Home
Section home
Source ID home:currently
Original https://www.henryw.me/#/home#story-now
Read https://ask-henry.whenry6688.workers.dev/agent/sources/home%3Acurrently?format=text
Henry is developing SlidePoise, an open-source agentic slide generation framework for planning presentations, exploring slide designs and reconstructing them as editable PowerPoint. Henry is developing AI × Self, a personal archive that lets visitors connect his work, ideas and experiences through their own questions. Each View composes a perspective with original sources.