Microsoft brings its Copilot agent harness to Foundry Agent Service in public preview; billing starts Dec 1
Microsoft introduces the Microsoft Copilot harness in Foundry Agent Service in public preview, a fully managed execution system for agents that reason, use tools, and complete long-running tasks. Microsoft runs the agent loop and sandbox while developers supply skills, procedures, and tools. Agents can be defined declaratively, created in Foundry, or managed as source-controlled code via azd. The announcement also includes general availability of long-running resilience for hosted agents, which restarts interrupted work with its original input so application code must save progress. Billing begins December 1, 2026.
Open original source devblogs.microsoft.com⚑ Review needed · why this is flagged
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourcePrimary source discovery · source check open
- Linked in sourceMicrosoft’s unified harness strategy
- Linked in sourceMicrosoft Foundry
- Linked in sourceFoundry Toolkit for Visual Studio Code
- Linked in sourceMicrosoft Foundry Skill
- Linked in sourcehosted agents
- Linked in sourceLong-running resilience for hosted agents
- Linked in sourceMicrosoft Foundry portal
- Linked in sourceRead Tina Schuchman’s and Vladimir Federov’s broader announcement
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Review needed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Microsoft introduces the Microsoft Copilot harness in Foundry Agent Service in public preview, a fully managed execution system for agents that reason, use tools, and complete long-running tasks. Microsoft runs the agent loop and sandbox while developers supply skills, procedures, and tools. Agents can be defined declaratively, created in Foundry, or managed as source-controlled code via azd. The announcement also includes general availability of long-running resilience for hosted agents, which restarts interrupted work with its original input so application code must save progress. Billing begins December 1, 2026.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: devblogs.microsoft.com. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- The Copilot harness manages the agent loop, context, and sandbox, while developers provide skills, tools, and instructions.
- Reusable skills package instructions and scripts; tools can include Foundry and MCP tools with configured authentication and approvals.
- Long-running resilience for hosted agents is generally available; Foundry restarts interrupted work, but applications must checkpoint progress and avoid duplicate actions.
- Billing for the harness begins December 1, 2026 on consumption-based pricing, with harness runtime usage free before that date.
Source claims not independently checked; the harness is in public preview, and switching harness after creation is not yet supported.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Microsoft opened the Copilot harness, the managed agent loop behind its Copilot experiences, to developers in Foundry Agent Service as a public preview, so teams can pick a supported model and get tool calls, context and long-running task handling without building the loop. Long-running resilience for hosted agents is now generally available. Billing starts Dec 1, 2026.
Source claims not independently checked; the harness is in public preview, and switching harness after creation is not yet supported.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Managed harnesses reduce the infrastructure teams must build for multi-step agents, letting them focus on agent expertise and evaluation. The announcement also clarifies that recovery after interruptions depends on application-level checkpointing.
Limits and open questions
Source claims not independently checked; the harness is in public preview, and switching harness after creation is not yet supported.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.