Attach provenance and confidence

A memory without provenance is a rumor.

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

Prompt Capsule

Extend the memory entry schema with metadata: {content, type, provenance: {session_id, date, evidence: 'user-stated' | 'observed-success' | 'observed-failure' | 'inferred'}, confidence: high | medium | low, last_confirmed}. Rules: user-stated preferences and observed successes/failures start high; inferences start low; confidence rises when a later session re-confirms (update last_confirmed) and falls when related actions fail. Update the write tool to require metadata and the read path to render it compactly (e.g. a [high, user-stated, 2026-07] suffix). Backfill existing entries with best-effort metadata, marking unknowns explicitly.

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

All memory entries carrying provenance and confidence, backfill included.

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.

Schema enforced on new writesEvidence types drive initial confidenceExisting entries backfilled honestly

Do not continue if…

! Remembering everything, so recall drowns in noise
! No provenance, so bad memories cannot be traced or trusted
! Contradictory facts accumulating until the agent's worldview is incoherent
! Single-observation 'facts' treated with the same trust as confirmed ones

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.

Everything is marked high confidence. Audit the evidence field: 'inferred' can never start high - if the model cannot cite where a fact came from, it is an inference.