Every ditched personal agents for a shared Claude Managed Agents coworker in one week
every · x · 2026-10-23
Media company every explains why it moved from per-teammate personal AI agents to one shared "Every Agent," built on Anthropic's Claude Managed Agents infrastructure and shipped within a week.
Key points:
- With infra handled by Anthropic, the team focused on making the agent feel like a coworker: behavior norms, when to stay quiet, and per-teammate tool permissions.
- Security: credentials are hidden from the agent, and changes to shared skills require human approval.
- Trade-offs: lock-in to Claude, and persistent conversation history means no zero-data retention support.
More from coding & agent
- Indie dev's agent tracks 519 directories, 311 submitted for SEO backlinks — fekdaoui · 2026-10-23
- ScienceClaw Hackathon at MIT Media Lab to build decentralized AI agent collectives for science — ProfBuehlerMIT · 2026-10-23
- What should a native agent harness handle beyond tool calling? — Glittering812 · 2026-10-23
- Running ~100 DeepSeek v4.1 flash agents in parallel for under $20/month — zack_overflow · 2026-10-23
- MCP's stateless 2026-07-28 spec drops session-id — how are stateful tools adapting? — Stock-Pumpkin-8859 · 2026-10-23
- Dev adds local MCP server to Mac screenshot app so Claude designs from your references — Embarrassed-Ebb-740 · 2026-10-23