Ingredient-panel photo extraction
2025–2026
A shopping aid that reads the ingredients panel from a phone photo and returns a structured ingredient list.
AI
OCR
I built mobile systems that captured photos of product packaging and converted text.
See its threads in the worldUsed on
DocInsight extraction API
2024
An API that takes several PDF documents in a single request and returns a spreadsheet of the facts extracted from them.
Regulatory medical-writing platform
2023–2026
A platform that drafts regulatory documents for clinical trials from source evidence, built for a pharmaceutical documentation firm and its sponsors.
Assistant for tax professionals
2023–2024
Chat assistant for US tax professionals that answers from a curated knowledge base and reads uploaded individual tax returns to suggest strategies.
Supplement ingredient dataset
2021–2022
A knowledge base of supplement ingredients and synonyms plus a recogniser that finds them in free-text product listings, for an outside client.
Company-location extraction at web scale
2021–2023
A web-scale crawler that finds a company's office address from its hostname, built for an external client.
Banking document chatbot
2026
A chatbot that answers banking customers' questions from the bank's own FAQ documents using retrieval-augmented generation.
AI Course Writer
2024–2026
Generates long structured documents by filling a template's placeholders from source documents, built for an external training-material business.
DocCraft generation engine
2024–2025
A document generation engine that fills Word templates from structured data, used mainly for estate-planning paperwork.
Stories where it mattered
2026 · Regulatory medical-writing platform
A cache that remembered the failures
- Situation
- On a regulatory document platform, generated documents came out wrong in ways that did not reproduce, and retries repeated the bad output.
- Task
- Find the true cause in a pipeline whose output reaches a client in a regulated industry.
- Action
- I traced it to a global result cache that also stored partial failed runs, then re-architected generation around per-step isolation with failure-aware cleanup.
- Result
- Failed runs stopped affecting later ones, a retry became a real retry, and the written root cause let the team review it.
2026 · Regulatory medical-writing platform
Tables that arrived in the client's document as raw markup
- Situation
- Medical writing deliverables showed misplaced tables, detached titles, and sometimes raw markup visible as text in the client's document.
- Task
- Produce one root cause analysis for three separately reported bugs before anyone wrote a fix.
- Action
- I found three causes: raw XML mutation, incomplete model-emitted HTML, and context-blind placeholders. I moved tables to a structured contract with neighbour context.
- Result
- The whole class of defect went away, not just the three reported instances.
2024 · Regulatory medical-writing platform
Asking what onboarding was supposed to produce
- Situation
- Two engineers were joining a document platform module covering audit logs, automatic mapping and server management.
- Task
- Give onboarding an intended outcome rather than just an activity.
- Action
- I asked the lead for the target outcome, how we would judge pace, and when production value was expected, and offered a reference checklist.
- Result
- Onboarding ran against a stated target and a first-value date, and the checklist was reused.
Goes with
PDF Processing
Document Intelligence
Python
NLP / NERThrow me a paper plane
Write a line; I’ll find it in my inbox.