Document Intelligence

I extracted structured information from documents using document intelligence techniques.

Used on

2024

An API that takes several PDF documents in a single request and returns a spreadsheet of the facts extracted from them.

2023–2026

A platform that drafts regulatory documents for clinical trials from source evidence, built for a pharmaceutical documentation firm and its sponsors.

2023–2024

Chat assistant for US tax professionals that answers from a curated knowledge base and reads uploaded individual tax returns to suggest strategies.

2024–2026

A document-authoring product that fills medical writers' templates from a sponsor's own source documents, with redaction of confidential detail.

2024–2026

Generates long structured documents by filling a template's placeholders from source documents, built for an external training-material business.

2025–2026

A shopping aid that reads the ingredients panel from a phone photo and returns a structured ingredient list.

2026 · Regulatory medical-writing platform

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

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

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.