Engineering-grade playbooks for AI agents

In production, models often intend to call tools but emit non-standard syntax. Strict parsers undercount capability; permissive parsers cause accidental execution. This playbook gives a fail-closed, auditable, multi-format parser design.

Tool calling fails less often because of schemas and more often because of judgment: over-calling (loops) vs under-calling (hallucination). This playbook gives an explicit decision framework and a minimal regression suite to measure Action + Restraint + Recovery.

You want a knowledge base that engineers actually reuse: patterns, runbooks, and evaluable playbooks for agents/LLM systems—so teams ship faster without repeating the same failures.