Give agents a conformance suite to test against

Write a suite that checks changes against the reference behavior the system must match, and have agents run it on every change.

View in Markdown

Prompt

Evaluate and apply this CI technique to my repository: Give agents a conformance suite to test against.

Write a suite that checks changes against the reference behavior the system must match, and have agents run it on every change.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/agent-conformance-suite.md

Inspect this repository’s CI workflows, build and test commands, dependencies, and recent run timings. Identify where this technique applies and explain the expected benefit using this repository’s evidence.
Measure a baseline from recent comparable runs: elapsed time, queue time, runner minutes and failures where available. If data is unavailable, say what cannot be measured.
Compare relevant company approaches, checking prerequisites, platform differences and tradeoffs. Rank applicable options by evidence, fit and measurable opportunity; do not present company results as predictions for this repo.
Recommend the smallest safe change, show what checks and fallback paths remain, and ASK ME WHICH CHANGE TO APPROVE BEFORE EDITING ANY FILES.
Only after approval, work on a new feature branch, make one reversible change, and open a reviewable pull request. Never merge or push to a default or protected branch.
Keep required checks, test coverage, deployment and release behavior intact. Validate the change and compare equivalent runs where possible; report limitations and what should be monitored after merge.

View all playbooks

How OpenAI used this technique

Read what OpenAI changed and follow the original sources.

Give agents a conformance suite to test against

Translated to GitHub Actions

What OpenAI built: OpenAI wrote a conformance test suite so the agents building Pando, its Git backend, could test their changes against standard Git behavior.
Your GitHub Actions version: A conformance suite in your repository that agents run on every change and a GitHub Actions job runs on every pull request.

OpenAI built Pando, a Git backend for its monorepo, with Codex in ten weeks: one engineer designed its core, teams of agents implemented it, and a handful of engineers deployed it. The team wrote a conformance test suite so agents could test their changes against standard Git behavior. It also built deterministic simulation testing harnesses that check the system's invariants and properties, which found subtle race conditions and regressions.

Use it when: Agents change code that has to match a reference: a protocol, a file format, a public API, or the system it reimplements.
Before applying it: Take the expected results from the reference implementation itself, and add a case each time an agent finds a new difference.
GitHub Actions adaptation: Compare the source system with your own workflow before applying this translation.

How OpenAI used this technique

Give agents a conformance suite to test against

Company Playbooks