Using findIQ in Microsoft Copilot and other AI systems
The two routes to AI in findIQ: Quinn, or your own system — Microsoft Copilot, Claude, or another MCP-capable one — via the MCP server.
Written By Tommy Giesbrecht
Last updated About 1 month ago
Article goal: After reading this article, you will know the two ways to use AI with findIQ — Quinn, or your own AI system via the MCP server — where the guides are, and what such a system is allowed to do.
Relevant for the Editor and Administrator roles. Quinn is currently in beta.
Two ways to use AI with findIQ
Quinn is the built-in route: the assistant is part of findIQ and ready to use, and findIQ selects provider and model. If you would rather use an AI system of your own — Microsoft Copilot, Claude, or another one — it reaches findIQ through the MCP server.
Both routes work on the same data. The difference is who chooses the model and who pays for it.
Connecting your own AI system
findIQ can be used from AI systems that support MCP, an open standard for giving AI systems access to external software. The system is connected once to the findIQ MCP server; from then on it works on the same data as the findIQ app — machines, templates, routines, heatmaps. Signing in happens with each person’s own findIQ credentials.
With Microsoft Copilot the connection is tested and documented, and so is Claude. ChatGPT and other MCP-capable systems follow the same principle; only the interface differs.
📘 Guides
Setup in Microsoft Copilot Studio · Setup for Claude · Background: What Is an MCP Server?
What the AI system is allowed to do
Never more than the person. The user signs in with their usual findIQ credentials. From then on the AI system can never do more than that person — and for safety it can do less in some places.
Reading and writing. Anything the API can do, the MCP server can do too: reading data ("Which machines does customer X have?") as well as creating and changing it.
Safety limits. An AI system cannot delete templates or machines — not even when the person signed in would be allowed to.
Read next
Working with Quinn — Use cases and prompt best practices.
Quinn FAQ — Short answers on access, model, data processing, and costs.
What is Quinn? — What Quinn is and how it relates to working in the interface.
Quinn beta and what’s next — Schedule, known limitations, examples of what may come next, and feedback.