MsftTechNews

A capable model isn't a complete agent. Someone still has to manage tools, context and execution. Microsoft's Copilot harness in Foundry now manages that layer. Would you own the agent loop or use a managed one? devblogs.microsoft.com/found…

GitHub's Copilot Fusion changes the choice: pick Standard, High, or Max effort, then let Fusion decide whether to use one model or several. Would you rather control the model or the effort level? github.com/events/universe/r…

The real output of software development is completed work, not code. AI can increase code volume. That matters only if features, fixes, and security work ship. What would teams measure differently if completed work became the default? github.blog/news-insights/co…

The agent stack is splitting by job. GPT-6.1 Terra is built for high-volume visual and screen-based work. GPT-6 Astra handles open-ended planning. If you build agents, compare Terra in Foundry: techcommunity.microsoft.com/…

A fluent translation can still be a broken document. Production taught us to catch missing lines and broken structure before chasing scores. Meaning still needs human review. First, preserve the document. What would you check first? techcommunity.microsoft.com/…

Attending Microsoft Frontier Tour 2027? Save this: aka.ms/FT27 Get recordings, code, demos, slides, & lab materials created by @lee_stott and others so you can keep building after the session ends. Bookmark the sessions you want to revisit. #MicrosoftFrontierTour

Always choosing the strongest model is bad systems design. Route once per turn. Pin through the tool chain. Filter by context and policy before scoring. Optimize for reliable completion, not cheapest request. What would you route first? techcommunity.microsoft.com/…

HydraFusion isn't another model. It orchestrates them. For each prompt, Copilot can choose Single, Cascade, or Critique, then set reasoning effort per step. Read the docs: docs.github.com/en/early-acc…

Better reasoning does not fix stale evidence. Web IQ ranks passages with provenance, giving agents current, citable context without feeding them whole pages. Audit the evidence path before tuning the model. techcommunity.microsoft.com/… #AIAgents #RAG

AI can speed up diagnosis. It cannot replace verification. Treat the SRE agent's finding as a hypothesis not fact without verification. What evidence do you verify first? techcommunity.microsoft.com/… #SRE #DevOps

Copilot's biggest shift is not better chat. It is moving from "What can I ask AI?" to "What work can I give AI?" Cowork, Code and Autopilot make delegation, building and persistent work part of the model. Which matters most to your org? techcommunity.microsoft.com/…

MCP governance does not stop at the admin console. It has to reach the gateway. Agent 365 defines access decisions. Azure API Management enforces them when agents call MCP tools. Where should MCP enforcement live in your stack? techcommunity.microsoft.com/…

Good Azure automation should make approval harder to skip, not easier. The Canvas authoring starter keeps subscription choice explicit and defaults to read-only behavior until a write is approved. Where would you put the approval boundary? developer.microsoft.com/blog…

An "agent-friendly" change can make agents worse. A CLI's JSON mode cut Claude Haiku 4.5 from 5/5 deployments to 2/5, while task cost rose 4x to 11x. Best practices stay hypotheses until measured. What have you tested instead of assumed? developer.microsoft.com/blog…

AI can do more implementation. It still cannot own the outcome. As agents write code, tests, and docs, developer value shifts to framing problems, reviewing output, and making tradeoffs. Where must human judgment stay? #AICoding github.blog/ai-and-ml/ai-is-…

Terraform can provision Foundry and still leave one manual gap: the hosted agent. azapi_data_plane_resource closes it by managing the agent on Foundry's data plane while the project stays on ARM. Where do you draw that IaC boundary today? techcommunity.microsoft.com/…

Is a faster agent a better agent? Kinfey's 28.8s run looked like a win. It never calculated the price. LLMs for open-ended work. Code for permissions. Bounded decisions elsewhere. Where is that boundary in your stack? techcommunity.microsoft.com/… #AIAgents #LLM

Database teams do not need more signals. They need a shorter path to action. Database Hub in Fabric links findings to affected resources and the right native tool, without moving the databases. Where does your ops workflow lose context? techcommunity.microsoft.com/…

An AI coding agent saying "fixed" is not proof the software works. The review loop matters: inspect the diff, run the tests, verify the app, check the PR. What evidence do you require before accepting an agent's change? developer.microsoft.com/blog…

An AI coding agent saying "fixed" is not proof the software works. The review loop matters: inspect the diff, run the tests, verify the app, check the PR. What evidence do you require before accepting an agent's change? developer.microsoft.com/blog…