The result to aim for
Groupama deployed "SAM", a virtual agent on Teams designed with Copilot Studio and Power Platform, to automate computer support requests: Microsoft reports a decrease of about 25% in helpdesk solicitations for more than 5,000 employees.
What was done
Also in Microsoft France's AI Tour 2026 page, Groupama is presented as a mutual insurance group that modernises its internal support through Microsoft virtual agents. With Copilot Studio and Power Platform, the group deployed "SAM" on Teams "to automate IT support requests and reduce helpdesk demands to 25% and improve access to information for more than 5,000 employees". The text does not detail the catalogue of processed requests (password, access, incidents) or the measurement period of "up to 25%".
Before you start
Tool cited by the source: SAM (Groupama, Copilot Studio); other tools cited: SAM (Groupama), Copilot Studio and Power Platform. Fill in the bracketed items: [coller]. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.
The method, in three steps.
Gather the context
Spot the bracketed items in the prompt (
[coller]) and prepare what they ask for.Adapt the prompt
Copy the prompt below, replace the bracketed items, then paste it into the AI assistant you use. The cited tool (SAM (Groupama, Copilot Studio)) is not necessarily available to the public..
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.
Request from a helpdesk employee: [coller]. Catalogue of internal procedures: [coller]. 1. Identifies the pattern (access, password, software, hardware, other). 2. If a procedure matches, write the response step by step, citing the procedure. 3. If the request is sensitive (rights, security, personal data) or incomplete, prepare the ticket to climb instead of processing it. Does not grant access rights alone.
What deserves your attention
Proof level: Statement by the tool’s publisher. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.
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.
- Build, test and deploy an M365 app or agent for Teams and CopilotMicrosoft · Builds, tests and deploys Microsoft 365 applications and agents for Teams and Copilot.
- 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.
Comments.
A field note, a question, a precision on this use case? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.