Anthropic publishes reference guide for building scheduled automations with Claude Managed Agents
ClaudeDevs · x · 2026-10-09
Anthropic shipped a reference implementation and walkthrough for Claude Managed Agents (beta): a scheduled agent that reads Slack and GitHub, tracks changes since the last run via memory stores, and posts updates back to Slack.
- Full daily-brief config included: agent instructions, deployment schedule, network allowlist, preference/state memory stores, and vault credential management
- A Claude Code command (/claude-api managed-agents-onboard) sets the agent up interactively
- Common failure modes covered, like silently losing source access or ignoring user preferences
- Requires a Slack app and GitHub token; new API credits bundled with Max and Team plans cover usage
Related event: Anthropic Shares Tutorial on Scheduled Agents with Claude Managed Agents(2 posts)→
More from coding & agent
- OpenAI-Affiliated Account Teases Major Agent Progress: "A Helluva 3 Months" Ahead — iruletheworldmo · 2026-10-09
- Agent Plasticity paper: frontier models differ wildly in how efficiently they self-improve from experience — _akhaliq · 2026-10-09
- Rebuild any e-commerce cart with Claude + Aftersell's copy-prompt workflow — EXM7777 · 2026-10-09
- Hone Raises $60M Seed From Benchmark and Index to Launch AI Engines That Own Business Outcomes — varunshenoy_ · 2026-10-09
- Attach an external Mac so your agents can drive the iOS simulator — lucasmeijer · 2026-10-09
- Running agents across machines: give the agent SSH keys to other machines it can use at will — lucasmeijer · 2026-10-09