{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifk2eospzyupoa7guzdgkqrpywa56gb52ovfrp3tzlxneuhszgzjq",
    "uri": "at://did:plc:dz7fbvkxedbwlm4sroohfpee/app.bsky.feed.post/3mickxki75s22"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihcl43zdtnnlcah7ekdkng4pwqypcm6hdca5fp2vgehs3tobj7tqq"
    },
    "mimeType": "image/png",
    "size": 297175
  },
  "description": "What's new? Microsoft added Critique and Council in Microsoft 365 Copilot Researcher; Critique uses two models to draft and vet content, Council compares Anthropic and OpenAI data;",
  "path": "/microsoft-365-copilot-gets-critique-and-council-modes/",
  "publishedAt": "2026-03-30T21:06:49.000Z",
  "site": "https://www.testingcatalog.com",
  "tags": [
    "pic.twitter.com/m4RlQmCKzs",
    "March 30, 2026",
    "pic.twitter.com/2p7O14OLFp",
    "Source",
    "@satyanadella"
  ],
  "textContent": "Microsoft has introduced Critique and Council, two advanced multi-model capabilities within the Microsoft 365 Copilot Researcher tool. Critique is constructed as a dual-model system: one model generates the research draft, planning, sourcing, and synthesizing information, while a second model reviews and refines the output, emphasizing source reliability, completeness, and strict evidence grounding. This architecture, based on evaluations across the DRACO benchmark, delivers measurable gains over traditional single-model solutions, surpassing Perplexity's Claude Opus 4.6 by 13.88% in overall research quality.\n\n> Introducing Critique, a new multi-model deep research system in M365 Copilot.\n>\n> You can use multiple models together to generate optimal responses and reports. pic.twitter.com/m4RlQmCKzs\n>\n> — Satya Nadella (@satyanadella) March 30, 2026\n\nCouncil enables simultaneous report generation from both Anthropic and OpenAI models, followed by a side-by-side comparison and a summary from a judge model that highlights consensus, divergence, and unique insights.\n\nThese features are currently available to users through the Microsoft 365 Copilot Frontier program, targeting professionals and enterprises who require robust, in-depth research capabilities. The system is accessible to organizations enrolled in the program, focusing initially on users in regions where Microsoft 365 Copilot is supported.\n\n> New in M365 Copilot: Council.\n>\n> You can run multiple models on the same prompt at the same time, so you can see where they align and diverge, and understand what each adds. pic.twitter.com/2p7O14OLFp\n>\n> — Satya Nadella (@satyanadella) March 30, 2026\n\nMicrosoft, the company behind these updates, has positioned Copilot as a central element of its productivity suite, integrating leading AI models from multiple vendors. By leveraging both in-house and third-party AI expertise, Microsoft continues to pursue improvements in workplace automation and research reliability, aiming to set a new standard for enterprise-grade research assistants.\n\nSource",
  "title": "Microsoft 365 Copilot gets Critique and Council modes",
  "updatedAt": "2026-03-30T21:06:49.584Z"
}