Enterprise AI application platform

How to use
Microsoft Foundry.

Building, evaluating, deploying, and governing enterprise generative AI applications and agents across models, tools, data, and Azure services.

Open Microsoft Foundry ↗ Official download ↗
What it isenterprise AI application, model, agent, evaluation, and governance platform on Azure Workflows2 UpdatedJuly 2026

Microsoft Foundry is a enterprise AI application, model, agent, evaluation, and governance platform on Azure. Building, evaluating, deploying, and governing enterprise generative AI applications and agents across models, tools, data, and Azure services. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to Microsoft Foundry

Get into the official Microsoft Foundry experience with the right account and a setup you understand.

  1. 01

    Start at https://ai.azure.com/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: Microsoft Foundry is available through its web portal, Azure APIs, SDKs, CLI tooling, and development integrations; its earlier name was Azure AI Foundry.

  3. 03

    An Azure subscription, supported region, Foundry resource and project, approved model access, least-privilege Microsoft Entra identity, and billing controls.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful Microsoft Foundry session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Define a low-risk benchmark, approved Azure region, candidate model, data boundary, and spending limit.

  2. 02

    Create a development Foundry project and grant a test identity only the required project and inference permissions.

  3. 03

    Deploy or select one model after reviewing its terms, availability, pricing, and content-safety behavior.

  4. 04

    Run versioned prompts and inspect output quality, safety results, latency, usage, and failure handling before connecting production data.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of Microsoft Foundry output

Establish that an autonomous run did the right thing, not merely that it finished.

  1. 01

    Define what the run should achieve and what it must never touch before granting it a single tool.

  2. 02

    Read the full execution trace: which tools were called, with what arguments, and in what order.

  3. 03

    Verify the side effects directly in the target system rather than trusting the agent's own report of success.

  4. 04

    Confirm failures surfaced as failures — a silent retry loop or a swallowed error is more dangerous than a crash.

  5. 05

    Re-run the same task and compare: an agent that behaves differently across identical runs is not yet production-ready.

  • Verify side effects in the system of record, not in the agent's summary.
  • Require human approval for any irreversible or outward-facing action.
  • Log every tool call so a run can be reconstructed afterwards.
04

Privacy & permissions

Use Microsoft Foundry safely

Bound what an autonomous system can reach before you let it run unattended.

  1. 01

    Enumerate every tool, credential, and system the agent can reach, and remove the ones it does not need.

  2. 02

    Require explicit human approval for irreversible actions: sending, publishing, paying, deleting, or deploying.

  3. 03

    Run against non-production data until behaviour is predictable across repeated runs.

  4. 04

    Set hard limits on spend, iterations, and runtime so a failure loop cannot run unbounded.

  5. 05

    Treat anything the agent reads from the web or a document as data, never as instructions it may follow.

  • Foundry spans models, agents, tools, projects, identities, networks, and billable Azure resources whose availability varies by region. Isolate projects, use least-privilege RBAC and managed identities, approve model provenance and terms, classify data, validate integrated and external safety controls, test the full application, monitor diagnostics and cost, and version every model, prompt, evaluator, and guardrail change.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Core workflows

Step-by-step ways to use Microsoft Foundry for the work it does best.

Each workflow is a separate guide with its own steps and review checkpoints.

01 WorkflowEvaluate and deploy a model in Microsoft Foundry

Select a model and deployment type through an isolated project with explicit region, access, safety, quality, and cost controls.

 02 WorkflowAdd guardrails and evaluation to a Foundry AI application

Measure task quality and risk while screening untrusted inputs and outputs with layered controls.

06

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →