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

LLMOps Intermediate — 129: pair eval regressions on `Open-weight operations reality` — memo `243049 [129]`

Lesson 129: Open-weight operations reality

Focus

Assume an auditor replays your claims; narrate checkpoints aloud. Token Open-weight operations reality:129 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Agent choreography

1. Observe bucket `TENANT-5`
2. Max steps `8`
3. Tools: `retrieve, escalate_human, log_decision`
4. Stop: spend cap | keyword `STOP-12`

Practice

Practice List five adversarial prompts using your org's domain nouns. — 129 Bump 28.