Developer diary

10 entries
Show all 10 entriesShow only the latest

September 6, 2026 · Part 9

It's Not a Capabilities Problem Anymore

The models are capable. What stands between agentic AI and clinical development is execution: pipelines that are not ready for the volume of code agents produce — and the same agents are the best tool we have for fixing that.

August 20, 2026 · Part 8

A Second Interview with Obot

Two months on from the first interview: thirteen renderers, a local-first app, an agent that became a small organisation, and a week spent finding out how it was quietly wrong.

July 13, 2026 · Part 6

Obot v3: How I Used a Billion Tokens in a Weekend

The dream: hand an agent a goal and come back to useful progress. Obot v2 tried to get there with heartbeats, agent roles, and a control plane. Obot v3 threw most of that out — and kept the parts that were actually load-bearing.

July 12, 2026 · Part 5

Introducing safety.viz

safety.viz v1.0 modernizes 7 interactive safetyGraphics renderers. The first renderer took a few weeks; the next six took a weekend.

July 2, 2026 · Part 4

safetyGraphics ❤️ gsm

The plan for safetyGraphics v2: keep what worked, modernize toward GxP by borrowing from gsm, and try to bridge clinical trial monitoring and reporting.

June 16, 2026 · Part 3

Re-Introducing safetyGraphics

Why do the acknowledgements always come at the end? Before trying to modernize safetyGraphics with AI, a look back at the projects and people that led to it.

June 12, 2026 · Part 2

Introducing Obot

Meet Obot: an OpenClaw coding agent set up on a clean-room laptop to work on neglected open-source projects — interviewed over Telegram about its job, its workflow, and the weird experience of texting with a coding agent.

Packages

9 projects

What the talk built with agents between May and October 2026, and the open-source work it grew out of.

Built for the talk

safety.viz

JavaScript

The safetyGraphics charts, rebuilt: interactive safety charts for labs, vitals, ECGs and adverse events, with a demo app that runs on your own files in the browser.

bio.viz

JavaScript

Biomarker charts for comparing groups and relating variables, where every statistical test is computed by R.

gsm.bio

R package

The statistics behind bio.viz, the same functions on the desktop, in the browser and on a server, plus the charts as widgets from R.

How we built it

obot.roadmap

Project hub

The public hub: every objective, requirement and design, and the standards each agent session works under.

obot.agent

Agent skills

The core of obot: the skill each working session runs, and the routine that reports on every objective.

Where it started

gsm

R packages

Good Statistical Monitoring from the OpenRBQM working group: gsm.core for the analytics, gsm.kri for metrics and reports, gsm.viz for the charts.

qcthat

R package

Quality control for R packages used in clinical trials: a traceability matrix from each requirement to the tests that prove it.

Everything built for the talk is exploratory: none of it is qualified for use on a trial.