Bind extraction runs to immutable document digests
A corrected document is uploaded under the same filename and the old result appears current.
- Focused work estimate
- 2h + prerequisites
- Priority in the scenario
- High
- Engineering practice
- Provenance · Idempotency
Estimated field mix
- Applied AI50%
- Data engineering30%
- Storage systems20%
Field percentages are editorial estimates of the ticket's engineering focus. They total 100%; they are not measured time, proficiency scores, or ownership evidence.
Review it, then add it to your workspace.
The board opens an editable draft; nothing is saved until you confirm it. Sign-in and workspace permissions apply, and Demo boards remain ephemeral.
Project context
A fictional procurement team receives inconsistent supplier documents. It wants draft records that staff can review without treating model output as authoritative accounting data.
Setup prerequisites
- Author synthetic text invoices with ambiguous dates, currencies, and line items; use a deterministic provider double.
Preceding work
Complete these dependencies, or supply their agreed outputs before taking this ticket.
Acceptance criteria
- Identify runs by document digest and extractor version.
- Preserve earlier runs when content changes.
- Reject a result bound to another document digest.
Implementation constraints
- Filenames are display labels, not identity.
Verification to include
- Replay an unchanged document deterministically.
- Change one byte and prevent reuse of the old result.
Deliverables
- Run identity contract.
Rollout and recovery
Append new runs on document changes; never rewrite accepted extraction history.
Value of the work
For the engineer: Practice schema constraints, numerical checks, review workflows, and safe model boundaries.
For the team: Produce an inspectable extraction prototype that can reduce manual transcription while preserving review control.
Evidence boundaries
Outcome Evidence: Tests, patches, and runbooks are requested deliverables. They become Outcome Evidence only through a qualified Mission and immutable Evidence IDs.
Ownership Evidence: Independent adaptation must be observed under a declared verification policy and cite immutable Evidence IDs. Completing a planning ticket establishes no Ownership Evidence.