Automatically analyze and classify industrial maintenance response reports

What was done

According to the testimony published by Microsoft on October 24, 2025, after deploying 30,000 Microsoft 365 Copilot licenses (70% of employees recommended it to their colleagues a year later), TotalEnergys develops agents for specific activities. MARGE (Machine Assisted Reliability and Graving Engine), built with Copilot Studio and support from Microsoft's Industry Solutions teams, automatically analyzes and ranks industrial maintenance intervention reports. According to the source, fault analysis is more reliable, with an improvement of 25-45% in the identification of their causes. Some 30 such applications are deployed or under development, based on business value, frequency of use and potential impact.

Before you start

Tool cited by the source: Copilot Studio (Microsoft). Gather the information the prompt asks for. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.

The method, in three steps.

1. 01

   Gather the context

   Gather the information described in the prompt.

2. 02

   Adapt the prompt

   Copy the prompt below, replace the bracketed items, then paste it into the AI assistant you use. The cited tool (Copilot Studio (Microsoft)) is not necessarily available to the public..

3. 03

   Reread before using

   Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.

Your starting point.

Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.

Here are maintenance responses reports: Here is our breakdown classification:

For each report:
- equipment concernedd
- symptom found
- probable cause granting to nomenclature, with the sentence of the report justifying it
- confidence level (high/medium/low)
There groups recurrent causes by equipment. Classify "to be reviewed by an engineer" any incomplete or ambiguous report.

What deserves your attention

Useful skills

Official skills on the same task, paired by the desk: they are not part of the described case.

• Build, deploy and operate Microsoft Foundry agents and modelsMicrosoft · Covers the full life cycle of Microsoft Foundry agents, models and resources: construction, deployment, evaluation, optimization, refining and operation, including azd, hosted agents, tools, batch or continuous evaluations, IC/CD, agent optimizer, model deployment and refining (SFT, DPO, RFT), RBAC, quotas, regions and knowledge indexes.
• Create and launch reporting agent evaluations M365 CopilotMicrosoft · This skill covers the evaluation of Microsoft 365 Copilot reporting agents, with the `@microsoft/m365-copilot-eval` public LTC.
• Build a multichannel agent M365, Teams or Copilot Studio in .NETMicrosoft · The SDK Microsoft 365 Agents for .NET builds corporate agents for Teams, Microsoft 365 and Copilot Studio, typically hosted on ASP.NET Core, with AgentApplication routing and MSAL-based authentication.
• Build a multichannel agent M365, Teams or Copilot Studio in PythonMicrosoft · This skill relates to the SDK Python Microsoft 365 Agents.
• Build a multichannel agent M365, Teams or Copilot Studio in TypeScriptMicrosoft · This skill documents the SDK TypeScript Microsoft 365 Agents (`@microsoft/agents-hosting` depending on the source text).