Build in Public · 10 Parts

Home HD

I have a chronic illness, so I built a system to run my life around it. This series walks through the whole thing — the daily tracker, the data, the AI assistant, the £0 cloud architecture, and the readiness score I'm building next. Real system, in daily use, screenshots with synthetic data.

  1. Part 1

    I built a system to run my life around a chronic illness

    A working app I built for myself — it logs my treatments, reads my own blood-test trends, and answers questions with an AI assistant. The start of a build-in-public series.

  2. Part 2

    Treating at home saves the NHS thousands a year

    The cost case for treating a chronic illness at home: ~£9–12k saved per patient per year, an NHS target the country is missing, and why better software closes the gap.

  3. Part 3

    Logging a live session: before, during, and after

    The core daily loop of the app — a pre-treatment form, a live session with timed readings, and an auto-filled summary that always yields to a manual edit.

  4. Part 4

    Turning two years of blood tests into trends

    A small data-engineering story: a long-format schema, phase tagging so one bad month doesn't flatten the trend, and a regex parser instead of an LLM.

  5. Part 5

    An AI assistant that reads my actual health data

    A function-calling assistant whose system prompt is rebuilt every turn from my live data, with symptom-driven retrieval and voice input. A reusable pattern for AI over your own data.

  6. Part 6

    Giving the assistant hands: an action layer and a data layer

    Turning a chat assistant into a safe agent: an on-device action layer behind a state machine with human confirmation, plus a read-only MCP data-context endpoint.

  7. Part 7

    Running a real health app on £0

    The all-free-tier Google Cloud architecture — and the one deliberate choice (client-side writes) that keeps it from stalling at the worst possible moment.

  8. Part 8

    One codebase, two apps: a local-first community edition

    From one Flutter codebase, a cloud edition and a fully local-first, no-account community build with on-device CSV/PDF export — switched by a build flag.

  9. Part 9

    The readiness score: what I'm building next

    The honest roadmap: a live body-data foundation, the daily readiness score I'm building on top of it, and why the pattern fits any fluctuating-capacity condition.

  10. Part 10

    What's next — and I can build this pattern for your condition

    The closing post of the series: what's still on the roadmap, and the invitation to build the readiness-engine pattern for other conditions and use cases.

← All blog posts