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

LLMOps Basic — 160: iterate incident comms on `Benchmark scepticism rituals` — memo `607460 [160]`

Lesson 160: Benchmark scepticism rituals

Focus

Document interfaces between retrieval, prompts, and policy engines. Token Benchmark scepticism rituals:160 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Agent choreography

1. Observe bucket `TENANT-5`
2. Max steps `9`
3. Tools: `retrieve, escalate_human, log_decision`
4. Stop: spend cap | keyword `STOP-15`

Practice

Practice Simulate degraded retrieval once; capture user-facing fallback copy. — 160 Bump 23.