Official Agents API cookbook: connect Slack threads to persistent agent sessions, workplace tools, and isolated sandboxes so workplace chat becomes a durable agent runtime.
Learnable test: keep deterministic paths in code; put the agent loop only on the flowchart box whose next step depends on discoveries (multi-source state, content-driven checks, unencoded domain knowledge)—else it’s an API call in a badge.
OpenAI's Cookbook provides a synthetic support-agent optimization sprint comparing prompts, tool controls, model routing, caching, and offline follow-up; its default simulation is not a production performance benchmark.
The workflow scores incoming mail for prompt-injection patterns, routes high-risk messages to review, and uses Gemini for structured triage of the remaining messages.