Claude Managed Agents Workshop Q&A: Evals, CI/CD, Tenant Isolation and Long-Running Agents
AI Engineer · youtube · 2026-10-12
The closing Q&A of Anthropic's 4-part Claude Managed Agents workshop with Priyanka Phatak and Gabe Cemaj.
- Agent definitions live in YAML and sync via CI/CD with the ant CLI.
- Tenant isolation by workspace, org, or session metadata.
- Self-hosted sandboxes unlock GPUs and extra memory.
- Anthropic shares how it runs agent evals and reviews agent-written code.
- Also covered: messaging agents waiting on custom tools, sharing resources across an org, modeling a multiplayer Slack agent, keeping very long sessions responsive, and a coordinator pattern where a subagent handles custom tools so the main agent stays free.
More from coding & agent
- Screego: open-source self-hosted screen sharing for devs with 10.5k GitHub stars — thisguyknowsai · 2026-10-12
- Grok app adds Bots: users can now build custom bots like Trader inside Grok — nima_owji · 2026-10-12
- Moli: open-source headless browser for AI agents renders pixels only on demand — abhishek__AI · 2026-10-12
- Open-source real-time object detection with YOLOv8, OpenCV, and threaded frame buffering — mariamamhan · 2026-10-12
- Claude Opus 5.5 makes a Blender short film about the last black hole — 3,000 lines of Python, no gen models — toni_btrain · 2026-10-12
- HF Engineer Runs pi-web on DGX Spark to Steer Local AI Agents From His Phone — lhoestq · 2026-10-12