LLMs

I integrated large language models into customer-facing and internal products.

Used on

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.

2023

A chatbot for a financial advisory web app that answers visitors, serves members from their profile and collects planner data.

2024–2026

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

2023

Web tool that turns a founder's answers about their idea into a written business report for the founder and advisers.

2021–2023

A sales-enablement product that sits beside a live video meeting and shows reps cue cards, persona and sales stage.

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.