---
type: "post"
id: "building-effective-agent-automations-claude-dev-blog-55ed08"
slug: "building-effective-agent-automations-claude-dev-blog-55ed08"
title: "Building effective agent automations / claude.dev Blog"
description: "Anthropic published a reference implementation for a scheduled Claude Managed Agents automation on October 8, 2026."
retrieval_nugget: "Anthropic published a reference implementation for a scheduled Claude Managed Agents automation on October 8, 2026."
published_at: "2026-10-21"
updated_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "published_at"
topics: ["claude","anthropic"]
entities: ["Anthropic","Claude Managed Agents","Claude API","Claude Code","Slack","GitHub"]
related_patterns: ["company-memory-needs-write-loops","agent-security-moves-to-runtime-boundaries","verification-bandwidth-is-the-scarce-resource"]
novelty_label: "new_fact"
what_changed: "Anthropic adds a separate guide and reference implementation for scheduled Claude Managed Agents that monitor Slack and GitHub, track changes, and send updates."
prior_refs: ["memory:7c816215-dca7-8ef6-af6d-e88638b23b46","memory:e3a931fa-8dad-8154-a802-701fca45a1e5"]
source_url: "https://claude.dev/blog/building-effective-agent-automations"
source_urls: ["https://claude.dev/blog/building-effective-agent-automations"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:building-effective-agent-automations-claude-dev-blog-55ed08"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/building-effective-agent-automations-claude-dev-blog-55ed08/","markdown":"https://newruntime.com/posts/building-effective-agent-automations-claude-dev-blog-55ed08.md","json":"https://newruntime.com/posts/building-effective-agent-automations-claude-dev-blog-55ed08.json"}
---

# Building effective agent automations / claude.dev Blog

## Retrieval answer

Anthropic published a reference implementation for a scheduled Claude Managed Agents automation on October 8, 2026.

Anthropic published a reference implementation for a scheduled Claude Managed Agents automation on October 8, 2026. The example reads selected Slack channels and GitHub pull requests, tracks changes between runs, and posts a brief to Slack. Claude Managed Agents is described as beta.

The configuration includes an agent, deployment schedule and time zone, memory stores, a vault, an environment allowlist, and a Slack app manifest. Setup requires a Slack app and a GitHub token. The `ant apply` command creates the configured resources in a Claude API workspace; Anthropic says the automation then runs on its infrastructure.

The guide recommends a separate bookmark for each source rather than a fixed time window, so a late or early run does not miss or repeat items. If a source fails, its bookmark remains unchanged and the brief should disclose the unavailable source. It also calls for confirmation from Slack before updating the reporting ledger and bookmarks, scoped credentials in a vault, read-only access where possible, and a per-run spending cap.

The source does not establish reliability, costs, general availability, or performance of Managed Agents in other deployments.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- topic hub: [Anthropic](https://newruntime.com/topics/anthropic.md): Explore the anthropic topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)