← Curriculum track ← Learn hub
Quanta GenAI Curriculum · LLMOps · Basic

LLMOps Basic — 152: compress prompt surface on `Benchmark scepticism rituals` — memo `532073 [152]`

Lesson 152: Benchmark scepticism rituals

Focus

Bias toward observable metrics: latency, cost, escalation rate. Token Benchmark scepticism rituals:152 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Logging contract

| Field | Retention |
|-------|-----------|
| trace_id | 12d |
| prompt_hash | policy-defined |
| completion_excerpt | 24h hot |

Mask tier `pii-v1` before persistence.

Practice

Practice Draft three eval assertions QA must pass before prompt promotion. — 152 Bump 23.