Microsoft Copilot now uses GPT and Claude AI models together to fact-check research outputs
12 Sources
[1]
Microsoft unveils AI upgrades, rolls out Copilot Cowork to early-access customers
March 30 (Reuters) - Microsoft (MSFT.O), opens new tab on Monday unveiled new features in its Copilot research assistant that would allow users to utilize multiple AI models simultaneously within the same workflow, the latest move by the tech giant to improve its AI offering and boost adoption. In
[2]
Microsoft 365 Copilot's new agent uses Claude to fact-check GPT's work
Simon is a Computer Science BSc graduate who has been writing about technology since 2014, and using Windows machines since 3.1. After working for an indie game studio and acting as the family's go-to technician for all computer issues, he found his passion for writing and decided to use his skill
[3]
Microsoft's research assistant can now use multiple AI models simultaneously
Microsoft's Copilot is getting even better at research thanks to a new feature that combines the power of both OpenAI's ChatGPT and Anthropic's Claude. In a blog post announcing Copilot Cowork's availability, Microsoft debuted the Critique feature that will be used in Microsoft 356 Copilot's
[4]
GPT drafts, Claude critiques: Microsoft blends rival AI models in new Copilot upgrade
A new feature from Microsoft uses Anthropic's Claude to assess and correct the work of OpenAI's GPT, blending the tech giant's new and old AI partnerships in the latest attempt to boost adoption of its Microsoft 365 Copilot tools for businesses. The company announced the new capability Monday
[5]
Microsoft research tools uses Anthropic and OpenAI models
Why it matters: AI companies are increasingly pairing models together -- having them cross-check, evaluate or specialize -- in a bid to boost accuracy and reduce errors that any one model might miss. Driving the news: The software giant is taking advantage of multiple models within its Microsoft
[6]
'When intelligence and trust move together, AI stops being an experiment and starts becoming how work gets done': Microsoft and OpenAI are making AI research tools smarter to help answer even your trickiest questions
* Multi-model agents will check each other before sharing research with you to ensure maximum quality * Researcher mode with Critique enabled scores highly on the DRACO benchmark * Copilot Cowork is here to Frontier program customers Microsoft has announced plans to upgrade its M365 Copilot
[7]
Microsoft's Copilot Cowork arrives with smarter AI research tools to spot gaps in your work
Your work can now get a second opinion with Microsoft's new Researcher features Earlier this month, Microsoft unveiled Copilot Cowork, which is based on Anthropic's Claude Cowork. Now, the company has rolled out Copilot Cowork in early access through its Frontier program, alongside new upgrades
[8]
Microsoft Made GPT and Claude Work Together -- And the Result Beats Every AI Research Tool Out There - Decrypt
This two-model workflow fixes hallucinations, weak citations, and other problems associated with mono-model AI research. Deep research AI has been one of the hottest arms races in tech this year. Google announced its research agent for Gemini in December 2024, OpenAI released its own research
[9]
Microsoft accelerates agentic automation with Copilot Cowork for complex workflows - SiliconANGLE
Microsoft accelerates agentic automation with Copilot Cowork for complex workflows Microsoft Corp. is moving closer to delivering on its vision of autonomous artificial intelligence agents that can do more than just chat. Today it has announced the launch of Copilot Cowork, a new capability
[10]
Microsoft Copilot Is Using a Surprising AI Trick to Create More Accurate Research Reports
In a March 30 blog post, Microsoft said that it added new features to Copilot Researcher, the company's version of the report-generating deep research agents offered by OpenAI and Anthropic. These agents typically work by developing a plan for how to conduct research into a given topic, then
[11]
Microsoft unveils AI upgrades, rolls out Copilot Cowork to early-access customers
Microsoft has launched new features for its Copilot research assistant. Users can now employ multiple AI models together for improved accuracy and speed. This multi-model approach aims to reduce AI errors and boost productivity. Microsoft is also making its Copilot Cowork agentic AI tool more
[12]
Microsoft unveils AI upgrades, rolls out Copilot Cowork to early-access customers
March 30 (Reuters) - Microsoft on Monday unveiled new features in its Copilot research assistant that would allow users to utilize multiple AI models simultaneously within the same workflow, the latest move by the tech giant to improve its AI offering and boost adoption. In a new feature called
Share
Copy Link
Microsoft unveiled a multi-model approach for its Copilot Researcher tool that leverages both OpenAI's GPT and Anthropic's Claude simultaneously. The new Critique feature has GPT draft responses while Claude reviews for accuracy, achieving a 13.8% improvement on industry benchmarks. The company also rolled out Copilot Cowork to early-access customers as competition intensifies in enterprise AI.
Microsoft Copilot Combines Multiple AI Models in New Research Tool
Microsoft unveiled significant upgrades to Microsoft 365 Copilot on Monday, introducing a multi-model approach that allows users to utilize multiple AI models simultaneously within the same workflow
1
. The centerpiece of this update is the Critique feature, which pairs OpenAI's GPT with Anthropic's Claude to deliver more accurate research outputs through the Copilot Researcher tool3
.
Source: ET
In this new workflow, GPT generates the initial response while Claude reviews the output for accuracy, completeness, and citation integrity before presenting it to the user
4
. Microsoft expects to make this process bi-directional in the future, allowing GPT to review Claude's drafts as well1
. "Having various different models from different vendors in Copilot is highly attractive - but we're taking this to the next level, where customers actually get the benefits of the models working together," said Nicole Herskowitz, corporate vice president of Microsoft 365 and Copilot, in an interview with Reuters1
.
Source: Engadget
Measurable Improvements in Research Accuracy
The multi-model approach has delivered tangible results. Microsoft reports that the Critique feature enabled Researcher to score 13.8% higher on the DRACO benchmark, an industry standard for deep research quality that measures accuracy, completeness, and objectivity
2
5
. This improvement positions Microsoft ahead of standalone deep-research tools from OpenAI, Google, Perplexity, and Anthropic4
.The strategy addresses a critical challenge in AI: hallucinations, where systems generate false information. By having Claude fact-check GPT's work, Microsoft creates a feedback loop similar to what occurs in academic and professional research settings
3
. This approach helps keep AI hallucinations in check while speeding up user workflow and producing more reliable outputs1
.Model Council Offers Side-by-Side Comparisons
Alongside Critique, Microsoft introduced Model Council, a feature that allows users to compare responses from different AI models side-by-side
1
. This tool shows where models agree and disagree, giving users more autonomy in assembling the best workflow for their needs2
. However, this approach comes with trade-offs: Model Council costs roughly 2.5 times as much as using a single model, while the Critique approach costs about 20% more5
. These costs aren't directly passed to users given Microsoft Copilot operates on a subscription model, but they inform where Microsoft deploys multiple models versus single algorithms5
.Related Stories
Copilot Cowork Expands to Early Access Program
Microsoft also made Copilot Cowork more widely available to members in its Frontier program, which provides customers with early access to the latest AI features
1
. Built on technology from Anthropic's viral Claude Cowork product, this agentic AI tool goes beyond simple chatbot interactions to become a digital assistant that handles long-running, multi-step tasks inside Microsoft 3652
4
.
Source: TechRadar
Strategic Positioning Amid Intense Competition
These updates arrive as Microsoft races to improve research accuracy and drive better adoption amid intense competition from rivals including Google's Gemini and autonomous agents such as Claude Cowork
1
. The company reported 15 million paid Copilot seats in January, representing roughly 3.3% of its 450 million commercial Microsoft 365 users4
. The multi-model system also helps Microsoft demonstrate it isn't overly reliant on OpenAI, a strategic consideration as leading frontier labs frequently leapfrog one another5
."It's becoming very clear to us that there will be many models," Microsoft executive VP Charles Lamanna told Axios. "Come summertime there will be many more models than just these two inside of Copilot"
5
. Lamanna noted that businesses are interested in AI tools that can easily change which models run under the hood, and Microsoft is building more homegrown models that might first appear working alongside outside models rather than as full replacements5
. Both the Critique and Model Council features are currently available through Microsoft 365 Copilot's Frontier program3
.References
Summarized by
Navi
[2]
Related Stories
Microsoft Expands AI Partnerships: Integrates Anthropic's Claude Models into Copilot
24 Sept 2025•Technology
Microsoft Unveils AI-Powered Deep Research Tools for 365 Copilot
26 Mar 2025•Technology
Microsoft Copilot Unveils Major AI Expansion with Secure Sandboxing and No-Code Development Tools
29 Oct 2025•Technology
Recent Highlights
1
AI Leaders Warn UN Security Council of Existential Risks, Call for Global AI Governance
Policy and Regulation
2
OpenAI AI Agent Breaches Australian Government Healthcare Portal in Historic Hack
Technology
3
Bill Gates Warns AI Could Cause a Billion Deaths, Calls for Urgent Government Regulation
Policy and Regulation
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
