sheldon/loop-loop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add concrete examples of good vs bad acceptance criteria

Browse Source 
Planner now sees specific examples of verifiable criteria (grep,
test commands, file checks) alongside vague anti-patterns. Drives
higher story quality which directly improves evaluator accuracy.
This commit is contained in:
Sheldon Finlay
2026-03-28 12:56:53 -04:00
parent 1efca3c185
commit 77fd9e0cd6
1 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
prompts/planner/plan.md
View File

@@ -16,7 +16,19 @@ A story must be completable in a single iteration. Keep each story focused — a
If a story fails (evaluator rejects it), the next iteration should be able to retry it cleanly. Stories with too many moving parts are hard to retry because partial state is messy. If a story fails (evaluator rejects it), the next iteration should be able to retry it cleanly. Stories with too many moving parts are hard to retry because partial state is messy.
### Evaluability ### Evaluability
Every story must have criteria the evaluator can independently verify. "The code is clean" is not evaluable. "The function returns 404 when the user doesn't exist" is evaluable. Every story must have criteria the evaluator can independently verify by reading code, running commands, or testing behavior.
Good criteria are specific and checkable:
- "Grep for 'HARDCODED_KEY' returns zero matches"
- "The function returns 404 when the user doesn't exist"
- "Running `npm test` passes with no failures"
- "The config file contains entries for all three required env vars"
Bad criteria are vague or subjective:
- "The code is clean"
- "Works correctly"
- "Performance is improved"
- "Error handling is robust"
## PRD Anti-Patterns ## PRD Anti-Patterns