Run a brutal functional audit

Get the honest map: what works, what is fake, what is broken.

First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.

Prompt Capsule

Audit this app feature by feature with zero optimism. For every feature/screen: perform its primary action for real, then refresh and check persistence. Classify each as WORKS (action real + persists), FAKE (UI responds but nothing real happens), or BROKEN (errors/dead). Produce the table: feature -> action tested -> observed result -> classification. Do not skip auth, forms, filters, or buttons in modals.

Paste into EmergentFull Build: complete implementation prompt with explicit requirements

Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.

Actual change check

Expected after this step

A complete truthful WORKS/FAKE/BROKEN feature table.

Should NOT happen

An existing feature broke
A button only logs to console
Data disappears after refresh
Errors fail silently with no visible state

This is what should exist before you continue. If reality does not match, do not move on.

Your notes for this step

Track what changed, failed, or needs follow-up. Notes export with the flow.

Pass the Verify Gate to complete this step

Verify before continuing

Do not move on until every check is true. The complete button stays locked until then.

Every feature was action-tested, not eyeballedPersistence checked with refreshesThe table covers all screens and modals

Do not continue if…

! Assuming a feature works because its UI renders
! Fixing cosmetics while core actions stay dead
! Claiming success without refresh/persistence tests
! Half-wired forms that validate but never submit

If the AI messes this up

Use this when:

- it only made visual forms or placeholder UI
- buttons do nothing or only log to console
- data is not persisted - state disappears on refresh
- something that worked before is now broken

Use this when the AI fakes progress or breaks the feature. It forces a real fix.

The audit trusted appearances. Redo it by executing each feature's primary action and refreshing; reclassify anything that does not persist or errors.