Which Works Best in a Copilot Agent — ChatGPT, Claude or Grok?

About this episode

Shervin Shaffie compares the latest AI models from OpenAI, Anthropic, and xAI in Microsoft Copilot Studio.

In this video, Shervin Shaffie, Copilot Principal Engineer at Microsoft, compares the latest models from OpenAI, Anthropic, and xAI by running the same AI agent in Microsoft Copilot Studio three times, each time powered by a different LLM. ⏩ You can watch this Podcast as a video here: https://youtu.be/imhVISEduTo This Podcast represents the opinions of Shervin Shaffie and his guests to the video and does not reflect the opinions of Microsoft, affiliates, or the companies with which this video's participants are affiliated with.

People in this episode

Host: Shervin Shaffie

Topics covered

• AI comparison
• Copilot agents
• LLM evaluation
• technology
• education

Keywords

• Copilot
• AI models
• ChatGPT
• Claude
• Grok
• Microsoft
• LLM

Mentioned in this episode

Organizations: Microsoft, OpenAI, Anthropic, xAI

Products: ChatGPT, Claude, Grok

More episodes of All About AI with Shervin

• Why AI Might Actually Make Human Skills More Valuable, Not Less — with Georgia Barnasa, Cognitive AI Architect at Microsoft · May 30, 2026 · 46 min
• I Built an AI Command Center for My Entire Workday · May 24, 2026 · 5 min
• 500 Million Have Copilot Chat — Most Only Use 10% | Learn How To Use The Other 90% · May 10, 2026 · 8 min
• Go Beyond Copilot Agents with Copilot Cowork (Custom Skills Tutorial) · May 3, 2026 · 18 min
• Copilot Now Lets You Choose Between Claude, ChatGPT, Or Both! (Full Tutorial) · April 26, 2026 · 8 min
• Build NEXT-LEVEL Copilot Agents with VS Code & GitHub Copilot · April 19, 2026 · 28 min