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.
Domains
Healthcare AI
I built AI systems for healthcare and medical documentation.
See its threads in the worldUsed on
Medical-writing platform archive
2024–2026
A document-authoring product that fills medical writers' templates from a sponsor's own source documents, with redaction of confidential detail.
Medical-device monitoring for hospitals
2019–2021
Monitoring and remote-access system for hospital medical devices: live dashboards and alerts for staff, browser-based remote access for service engineers.
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.
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.
TalkingDB document question-answering
2021–2026
A question-answering engine that rebuilds each customer document as its section tree and fetches only the sections a question needs.
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.
2026 · TalkingDB document question-answering
Credentials in git history, and rotating keys was not enough
- Situation
- Reviewing repositories before a host move, I found OAuth client secrets in git history, which ships to anyone who clones.
- Task
- Make the secrets unreachable, not merely invalid, before the repositories were pushed to their new home.
- Action
- I cloned bare mirrors, mapped each leaked value to a placeholder, rewrote history with filter-repo, pushed to the new remotes, and documented the exact procedure.
- Result
- The repositories moved with secrets removed from every commit, and another file with hardcoded credentials was flagged for cleanup.
2026 · TalkingDB document question-answering
Holding back an accuracy number that would have looked great
- Situation
- A large reported jump in search accuracy was circulating and was about to become a go-to-market claim.
- Task
- Check whether the gain was real, since repeated passing results seemed to be counted again across runs.
- Action
- I raised it plainly, then set a general standard: proposed improvements need a frequency table of failing cases and expected fix share.
- Result
- The inflated figure never reached a customer-facing claim, and benchmark results are now reviewed against a sheet before approval.
2026 · TalkingDB document question-answering
Being asked to pull a date forward, and naming the real constraint
- Situation
- Leadership wanted a cross-product integration delivered sooner because it strengthened the story with channel partners, which I agreed with.
- Task
- Show that the date was set by available engineering time, not technical complexity.
- Action
- I agreed with the goal, offered to make time visible through tracked tasks, and named three ways to buy time: delegation, clear ownership, hiring.
- Result
- The conversation moved from when it can be done to which trade-offs we accept, with the task breakdown as shared evidence.
2026 · TalkingDB document question-answering
A port that turned out not to be a port
- Situation
- Search training was to be ported from an older e-commerce AI codebase, and the files looked like a simple lift and shift.
- Task
- Scope the port properly before committing a sequence of stories others would plan around.
- Action
- I read the code itself: the crawler was tied to one storefront, so I called for a fresh generic crawl-and-chunk pipeline and resequenced.
- Result
- The order of work changed without changing the plan, and client-specific code stayed out of the generic package.
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
Legal AI
Regulated Medical Writing
Document Intelligence
RAG
LLMs
PDF ProcessingThrow me a paper plane
Write a line; I’ll find it in my inbox.