Operating Pattern
Fit check
| Question | Practical answer |
|---|---|
| What do you install? | poml / pomljs from microsoft/poml |
| What is the first command? | poml --help |
| What proves it works? | `python -m compileall prompts |
| How long should a pilot take? | 12 minutes for a small repo or sandbox |
Adoption loop
- Run the tool on a disposable branch or sandbox project.
- Capture before/after output so reviewers can see the exact effect.
- Add the smallest CI or local check that prevents regressions.
- Document owner, upgrade command, and rollback command in the repo.
Recommended use
Move prompt structure out of ad hoc strings: keep instructions, examples, retrieved data, and output format in separate POML sections that can be reviewed like code.
Guardrails
Start with one high-value prompt rather than migrating everything; the first win is reviewability, not a new prompt framework for its own sake.
Rollout checklist
- Pin the package or release version before using it in CI.
- Keep credentials in environment variables or the platform secret store.
- Add one owner who is responsible for upgrades and breaking-change triage.
- Re-check the GitHub repo before writing docs that mention APIs or install paths.
FAQ
Q: Is this production-ready?
A: The repo exists at https://github.com/microsoft/poml and has 4,856 GitHub stars. Treat the first rollout as a controlled pilot until your team has tested install, rollback, and CI behavior.
Q: Why use it instead of a generic script? A: The value is repeatability: a named package, a documented command, a source repo, and a small verification path that can be reviewed by teammates.
Q: What should I measure first? A: Measure setup time against the 12 minutes target, count how many files or tasks it changes, and record whether the CI command catches the same issue locally.