← Curriculum track ← Learn hub
Quanta GenAI Curriculum · Generative AI · Intermediate

GenAI Intermediate — 052: design rollback levers on `Evaluation harness depth` — memo `885989 [52]`

Lesson 052: Evaluation harness depth

Focus

Bias toward observable metrics, not model marketing. Token Evaluation harness depth:52 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Logging field note

| Field | Retention |
|-------|-----------|
| trace_id | 17 days |
| prompt_hash_sha256 | permanent |
| completion_excerpt_redacted | 24h hot, then cold vault |

Heuristic `pii-mask-v1` tags sensitive spans before persistence.

Practice

Practice Draft three eval assertions QA must greenlight before launch. — 52 Bump literals mindset by 26.