Filed under

AI

Writing 9 posts

The guardrail is the feature

An agent that finds every reference to a feature flag and plans its removal is the easy half. The rule about which flags it is never allowed to propose removing is what makes it safe to leave running, and what let the job move to the person who actually wants it done.

Engineering · 4 min read

Bad acceptance criteria ship as bugs

Ambiguity in acceptance criteria doesn't disappear when implementation starts. It becomes a decision made without full context. The lineage problem, staleness semantics, product positioning: caught before a sprint begins, they're conversations. Caught after, they're migrations.

Engineering · 6 min read

The demo is the test

A feature that passes every test can still be broken in ways the test suite is structurally unable to see. Four kinds of blindness that only surfaced once real stakeholders started using an AI booking assistant in a room.

Engineering · 15 min read

Designing a logging system for an AI service

Building a standardised logging system for an AI assistant service: making consistent structured logging the path of least resistance, and thinking carefully about what an AI service should and shouldn't persist.

Engineering · 2 min read

From merged pull requests to a performance review

Merged pull requests already record what you did. Turning them into a work log with an LLM is easy; the hard part is the defensive rules that stop it corrupting the vault.

Engineering · 13 min read

Three quiet bugs hiding in a cross-service feature

Shipping a feature across four services meant coordinating an AI backend, a fare search service, and two frontend components. Along the way: a silent configuration bug, a duplicate event contract, and an HTML injection path.

Engineering · 3 min read