1.9 KiB
1.9 KiB
Task Reliability Ledger
Purpose: Make the ≥100 error-free executions rule and Leonard scoring measurable.
Until a task type has documented runs, human approval remains required before any client-facing publish for that task type.
Error definition (default): Output that invents facts/numbers, mis-assigns Evidence Tier, includes solution language in Layer 1/2, omits required Snapshot Date / recency, violates template structure, or would be unsafe to show a client without correction.
Publish-gate counters (automation eligibility)
| task_type | runs | errors | last_error_date | notes |
|---|---|---|---|---|
| gbp_snapshot_ingest_r1_r3 | 0 | 0 | — | Leonard execution card only |
| data_inventory_draft_l1a | 0 | 0 | — | Public baseline |
| threat_register_draft_l2 | 0 | 0 | — | Diagnosis only |
| review_reply_draft | 0 | 0 | — | Not auto-publish |
| gbp_field_edit_draft | 0 | 0 | — | Not auto-publish |
| qa_answer_draft | 0 | 0 | — | Not auto-publish |
Rule: A task_type may bypass human approval only after ≥100 completed runs with zero errors for that exact task_type, documented here. Reliability does not transfer across task types.
Leonard / agent scored runs (rubric 0–2 × 5 criteria)
| date | agent | client | task_type | score_total | zeros? | pass? | reviewer | notes |
|---|---|---|---|---|---|---|---|---|
| — | — | — | — | — | — | — | — | No scored runs yet |
Pass: no zeros and total ≥ 7/10.
How to log a run
- After human review of an agent draft, add one row to the appropriate table.
- If the draft required material correction for an error (see definition), increment
errorsand setlast_error_date. - Do not count unscored exploratory chat as a run.
Last updated: 2026-08-02