Operating manual
Tag: llm-operations
A focused reading path for llm-operations: related field notes, evidence trails, and operating questions from the archive.
- the-model-answer-is-not-accepted-knowledge.md
The Model Answer Is Not Accepted Knowledge
Valid JSON proves shape, not truth. Reliable AI extraction needs evidence, provenance, policy controls, and reversible claim acceptance.
open artifact → - model-availability-needs-a-risk-contract.md
Model Availability Needs a Risk Contract
A backup model is not a continuity plan. Define the substitute, thresholds, evidence, authority, and drill before production access changes.
open artifact →