Skip to content

use PRD as a richer verification contract #3

Closed

Description

@dominicnunez

Problem

PRDs are currently treated as a task checklist — the agent marks items [x] when it thinks they're done, and the loop checks if all items are checked. There's no verification that the completed work actually satisfies the intent behind each task.

Idea

The PRD could become a structured contract that the verification step checks against:

  • Acceptance criteria: each task specifies observable outcomes ("endpoint returns 200 with valid auth", "form shows error on empty submit")
  • Edge cases: explicitly listed scenarios the implementation must handle
  • Architecture constraints: "use the existing UserRepo pattern", "no new dependencies"
  • Integration points: which existing tests must still pass, which APIs are affected

The verification step could then:

  1. Parse acceptance criteria from the PRD
  2. Check that test cases exist covering each criterion
  3. Verify architecture constraints weren't violated (no new deps in package.json, imports follow patterns)
  4. Run the full test suite to catch regressions

Context

This shifts the PRD from "list of things to do" to "list of things to prove were done." It makes the autonomous loop more trustworthy for complex tasks where "tests pass" isn't enough signal.

Activity

  1. dominicnunez commented on Feb 21, 2026

    @dominicnunez
    OwnerAuthor

    Closed as duplicate of #24 - PRD format (Phase 1) addresses this with BDD-style acceptance criteria, task verification steps, and done criteria per task.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions