Library · topic
Fundamentals
The core mental models: what an agent loop is, how to think about budgets, structured outputs, and the read → act → observe → correct cycle everything else here elaborates.
- Deep diveverified 2026-07-28
Human approval gates for high-stakes actions
Place approval gates immediately before consequential actions such as sending messages, moving money, changing production, deleting data, or releasing…
- Deep diveverified 2026-07-28
Structured outputs with JSON Schema
Use schema-constrained generation when downstream code needs machine-readable output: define required fields, closed enums, bounds, and disallow unexp…
- Field noteverified 2026-07-14
Production customer support agents
A support agent can deflect repetitive requests by answering from versioned help-center content and resolving low-risk tasks such as checking delivery…
- Field noteverified 2026-07-14
Production agents in finance
Finance agents need data minimization, field-level protection for PII, least-privilege access, immutable audit trails, retention controls, and jurisdi…
- Field noteverified 2026-07-14
Production agents in healthcare
Healthcare agents handling protected health information require HIPAA-aligned administrative, physical, and technical safeguards, minimum-necessary da…
- Field noteverified 2026-07-14
Planning and task decomposition
ReAct interleaves reasoning, actions, and observations so the agent can revise its approach from environmental feedback; plan-then-execute first creat…