> For the complete documentation index, see [llms.txt](https://docs.algenta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.algenta.ai/microsoft-and-azure/overview.md).

# Algenta for Microsoft Cloud

Turn enterprise data and operating models into governed decisions across Microsoft 365, powered by a decision runtime in your own Azure subscription

Algenta turns your enterprise data and operating models into **governed decisions** that employees can frame and act on directly inside Microsoft 365 — in Copilot, Teams, and Excel — while the decisions themselves are computed by a decision runtime deployed in your organization's own Azure subscription.

The split is deliberate. Microsoft 365 is where people already work, so that is where a decision is framed, explained, and acted upon. But the logic that turns assumptions into a recommendation, the evidence behind it, and the data it reads should sit under your control. Algenta gives you **one stable Decision API** deployed to your Azure, and then many Microsoft experiences on top of it — with no duplicated decision logic to keep in sync.

{% hint style="info" %}
**Where each part runs.** Microsoft 365 (Copilot, Teams, Office/Excel), Microsoft Graph, and Microsoft Entra are Microsoft-hosted services. The Algenta data plane — the gateway, the Algenta runtime, and the artifact store — runs in **your** Azure subscription. Running in your subscription puts these components under your control; it does not by itself make them network-private. Employees sign in with their existing Microsoft Entra identity, and the gateway derives their organization, workspace, and role from identity mappings you provision, not from values the client application supplies.
{% endhint %}

## How it fits together

The customer-controlled Azure gateway is the trust foundation. Every Microsoft experience is a thin adapter that calls the same governed decision lifecycle running behind that gateway:

* **Copilot & Teams** connect to the engine over the **Model Context Protocol (MCP)**: frame a request in conversation — or drop in a spreadsheet — run the real simulation, optimization, or forecast, and cite the computed numbers. Recommendations only; approving or executing a plan is always a separate, credentialed human action, never something the agent does on its own.
* **Excel** lets a user select ranges as a decision's assumptions, preview exactly what will be sent, run the analysis in your Azure, and write results to **new** sheets without overwriting the source.
* **Entra SSO** means there are no separate Algenta credentials — employees authenticate with the Microsoft identity they already have, and admin consent is granted once at the tenant level.

Figures returned to any of these surfaces are **model-estimated under the stated assumptions**, with the supporting evidence available for inspection.

## Explore this section

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><a href="/microsoft-and-azure/copilot-teams.md"><strong>Decision Agent in Copilot &#x26; Teams</strong></a></td><td>A declarative agent that frames, runs, and explains governed decisions in the tools employees already use.</td><td></td></tr><tr><td><a href="/microsoft-and-azure/excel.md"><strong>Excel Decision Add-in</strong></a></td><td>Turn selected ranges into a decision's assumptions and write results back into new sheets — with a preview before anything is sent.</td><td></td></tr><tr><td><a href="/microsoft-and-azure/entra-sso.md"><strong>Sign in with Microsoft Entra</strong></a></td><td>Employees use their existing Microsoft identity; you grant admin consent once and manage access centrally.</td><td></td></tr><tr><td><a href="/microsoft-and-azure/gateway.md"><strong>Deploy the decision gateway to your Azure</strong></a></td><td>The customer-controlled foundation every Microsoft experience calls — deployed into your own subscription.</td><td></td></tr><tr><td><a href="/concepts/decision-service.md"><strong>The governed decision lifecycle</strong></a></td><td>Understand how a decision is framed, run, recommended, and approved before you wire up a surface.</td><td></td></tr></tbody></table>

## Next steps

Start with the foundation, then add the experiences your employees will use:

1. [Deploy the decision gateway to your Azure](/microsoft-and-azure/gateway.md) — stand up the decision plane in your own subscription.
2. [Sign in with Microsoft Entra](/microsoft-and-azure/entra-sso.md) — register the app and grant admin consent so employees authenticate with their existing identity.
3. Add the surfaces: the [Decision Agent in Copilot & Teams](/microsoft-and-azure/copilot-teams.md) and the [Excel Decision Add-in](/microsoft-and-azure/excel.md).
4. If you are new to the model, read [the governed decision lifecycle](/concepts/decision-service.md) first.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.algenta.ai/microsoft-and-azure/overview.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.