Asking in natural language a question finances an agent integrated in Teams

What was done

In Microsoft France's AI Tour 2026 page, FDJ UNITED is presented as a major player in gambling in Europe, which generalizes the use of agentic AI to reduce repetitive tasks. After spreading Microsoft Copilot to all its employees, the group deployed Microsoft Azure AI Foundry and designed "a first expert agent of the Finance function directly integrated with Microsoft Teams". According to Microsoft, "all employees have near immediate access to finance expertise by asking their questions in natural language." For its part, "the financial management frees up time and focuses on the most complex issues that account for 10-15% of the 1,500 solicitations, which it received every year, until this agent was put in place".

Before you start

Tool cited by the source: Agent Finance (FDJ UNITED, Azure AI Foundry); other tools cited: Agent Finance (FDJ UNITED), Azure AI Foundry and Microsoft Copilot. 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.

1. 01

   Gather the context

   Spot the bracketed items in the prompt ([coller]) and prepare what they ask for.

2. 02

   Adapt the prompt

   Copy the prompt below, replace the bracketed items, then paste it into Microsoft Copilot.

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.

Question by a staff member in the Financial Directorate: [coller]. Extracts from internal procedures, reports and notes: [coller].

1. Answer only with these excerpts, citing the document.
2. If the question is simple (where to find a condition, how to charge a fee note according to the procedure), give the procedure to follow.
3. If it is complex or non-procedural, prepares the file to be transmitted to a controller, with the parts already assembled and the points opened.
No amount, no rate and no accounting rules.

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.
• Obtain instructions to remedy a recommendation AdvisorMicrosoft · This skill helps to obtain rectification instructions for an already selected Azure Advisor recommendation, so that the client can execute them himself.
• Recommend an Azure skill adapted to the taskMicrosoft · This skill is used for searching the Azure skills catalogue, to recommend an installable agent skill that corresponds to an Azure task: list plugins and skills from the API GitHub repository `microsoft/azure-skills`, read descriptions, find the plugin name in `plugin.json` (which may differ from the folder name), and then propose installation instructions depending on the client (Copilot CLI, Claude Code, or other).
• Check and manage quotas and Azure capacityMicrosoft · This skill is used for consultation and demand for Azure quotas, as well as for routine use, to plan a deployment or choose a region: check service limits, use, and request an increase — this demand is free: only the resources actually used are paid, not the quota allocation.
• Forecast and estimate planned Azure resource costMicrosoft · Prepares an expenditure forecast Azure and estimates the price of resources or anticipated workloads: projection the following month, comparison to a target, estimation of a virtual machine, comparison of storage levels or regions, retail price, EA rate or negotiated grid.