{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiayveydf5lvq322lfdbt3k4vvpbpyfaasswmm3pdn5ckst7cctd3y",
    "uri": "at://did:plc:xxrzfynfiasdpbxteqxi4jgq/app.bsky.feed.post/3mmfmw2sbstq2"
  },
  "description": "We are announcing the ability to use code interpreters on SharePoint sources in agent conversations in Microsoft Copilot Studio. This feature will be available in general availability on May 31, 2026.\n\nHow does this affect me?\nThis feature enables Copilot Studio agents to generate and execute Python code to respond to user prompts. Code interpreter supports tasks such as data preparation, statistical analysis, table joins, forecasting, and chart generation. These tasks work with structured files",
  "path": "/m365-message-center/message/mc1318109/",
  "publishedAt": "2026-05-22T00:00:06.000Z",
  "site": "https://blog.tophhie.cloud",
  "tags": [
    "As an uploaded file in an agent chat",
    "As a referenced knowledge source in a SharePoint documents library",
    "Use code interpreter on SharePoint sources in agent conversations"
  ],
  "textContent": "We are announcing the ability to use code interpreters on SharePoint sources in agent conversations in Microsoft Copilot Studio. This feature will be available in general availability on May 31, 2026.\n\n**How does this affect me?**\nThis feature enables Copilot Studio agents to generate and execute Python code to respond to user prompts. Code interpreter supports tasks such as data preparation, statistical analysis, table joins, forecasting, and chart generation. These tasks work with structured files like CSV and Excel. Code interpreter supports the GPT-4.1 model.\n\nUsing code interpreter for agents:\n\n  * Unlocks trustworthy analysis inside agents and prompts by employing deterministic, reproducible computation instead of best-effort large language model (LLM) reasoning for data questions.\n  * Lowers the skill barrier for advanced analytics by letting users ask analytical questions in natural language.\n  * Generates tables and visualizations of results programmatically that users can see, download, and reuse.\n\n\n\nAn agent in Copilot Studio can ingest a structured data file in two ways:\n\n  * As an uploaded file in an agent chat.\n  * As a referenced knowledge source in a SharePoint documents library.\n\n\n\nThis feature is tailored for developers, business analysts, and low-code makers. Code generation and execution integrate seamlessly with the Copilot Studio ecosystem to create powerful, AI-driven solutions.\n\n**What action do I need to take?**\nThis message is for awareness, and no action is required.\n\nIf you would like more information on this feature, please visit Use code interpreter on SharePoint sources in agent conversations.",
  "title": "MC1318109: Microsoft Copilot Studio - Use code interpreter on SharePoint sources in agent conversations",
  "updatedAt": "2026-05-22T00:00:06.558Z"
}