Investigate a conversion drop with a warehouse agent that exposes its SQL
At a glance
OpenAI's data-analyst example combines schema discovery, metric context, read-only SQL, and explicitly saved corrections in one persistent investigation; database execution stays in the application. This workflow is listed under builder, openai-agents-api, data-analysis, read-only-sql, agent-memory.
OpenAI's SRE example ties an alert webhook to a persistent agent session and Slack thread, investigates bundled telemetry and code-change fixtures, and records rollback decisions without performing deployments.
Official Agents API cookbook: connect Slack threads to persistent agent sessions, workplace tools, and isolated sandboxes so workplace chat becomes a durable agent runtime.
Make's memory guide provides a concrete read-normalize-reason-route-write pattern keyed to a customer or case, with module-level inspection and recovery paths for missing or malformed state.
A Technically writer documents a month-long Claude Code experiment managing a Meta Ads account: fresh sessions read prior logs, pull performance data, decide, act or abstain, and commit the updated history.
