Microsoft brings the Copilot harness to Foundry Agent Service in public preview: Microsoft runs the agent loop and sandbox, you bring skills and tools
Another managed agent execution layer arrives, and long-running resilience for hosted agents is now generally available.
// Key points
- Agents are defined declaratively; reusable skills package instructions, scripts and resources; Foundry and MCP tools connect with explicitly configured authentication and approvals; agents work with files and code and delegate bounded tasks to built-in subagents.
- Agent definitions can live in source control, and you can choose a supported Foundry model without rewriting the orchestration.
- Long-running resilience for hosted agents (bring your own framework and loop) is generally available: Foundry detects interruptions and restarts the work with its original input, while your code is responsible for saving progress and preventing duplicate actions.
Builder's takeSkills plus MCP plus subagents is now the common shape across Anthropic, GitHub and Microsoft: write agent capabilities as skills and MCP tools rather than tying them to one platform. The part to remember is resilience: a restart replays the original input, so any write action such as sending email or creating a report must check whether it already happened. PandaClaws' publish step needs that idempotency check whatever platform it runs on.
// Background · from #AI agents
Full timeline →- Oct 29 GitHub Agentic Workflows is generally available: write automation in Markdown, compile it to Actions YAML, and run it with Copilot or your own coding agent
- Oct 29 Copilot Memory is generally available on paid plans, and "dreaming" enters public preview: it curates memories and proposes instruction changes through pull requests
- Oct 29 Amazon Quick adds smart approvals: a separate classifier model auto-approves routine agent actions and sends consequential ones to the user