# Anthropic

Canonical: https://mudpie.ai/authors/anthropic/
Updated: 2026-09-20

Anthropic publishes primary engineering material on Claude, MCP, agent harnesses, long-running agents and managed agent infrastructure.

Source: https://www.anthropic.com/engineering

Organization description comes from Anthropic's public engineering and product pages; image comes from its official GitHub organization. Checked September 19, 2026.

## Referenced in 101

- [MCP joins the Agentic AI Foundation](https://blog.modelcontextprotocol.io/posts/2025-12-09-mcp-joins-agentic-ai-foundation/) — Moving stewardship into a neutral foundation makes MCP less dependent on Anthropic while creating a formal home for ecosystem governance.
- [Claude Managed Agents overview](https://platform.claude.com/docs/en/managed-agents/overview) — Claude Managed Agents supplies the harness, environments, sessions, tool execution and durable state around Claude so teams do not rebuild the control plane.
- [Claude Managed Agents: get to production faster](https://claude.com/blog/claude-managed-agents) — Anthropic positions managed agents as composable cloud infrastructure for long-running work, not another prompt template or chatbot framework.
- [Scaling Managed Agents: decoupling the brain from the hands](https://www.anthropic.com/engineering/managed-agents) — Separating model reasoning from execution workers lets the platform scale, recover and secure long-running agents without tying identity to one process.
- [Ship your first Managed Agent](https://www.youtube.com/watch?v=19HDQ9HppOA) — A working incident-investigator agent makes the managed platform concrete: define an agent, environment and session, then stream and supervise the run.
- [Memory and dreaming for self-learning agents](https://www.youtube.com/watch?v=RtywqDFBYnQ) — Agent memory needs deliberate consolidation and reflection; saving every token is not the same as learning from experience.
- [Building more effective AI agents](https://www.youtube.com/watch?v=uhJJgc-0iTQ) — Reliable agent systems start with simple workflows and add autonomy only when the task and evidence justify the extra uncertainty.

This is a Mudpie reference profile, not an account or endorsement. The profile records an authority connected to the source; it is not necessarily the article byline.