The outcome

Operate a generative AI flow that has evidence-based quality thresholds and documented responses to unsafe or unsupported content.

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 narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

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.

Step by step

A workflow you can repeat.

  1. 01

    Create a versioned dataset covering normal tasks, prompt injection, sensitive data, harmful content, protected material, and unsupported-answer cases.

  2. 02

    Define task, groundedness, safety, latency, and cost metrics with pass thresholds and a human review rubric for ambiguous results.

  3. 03

    Configure system rules, content filters or Content Safety checks, Prompt Shields, network boundaries, and output validation for the use case.

  4. 04

    Run evaluations on the complete flow, inspect false positives and false negatives, and test tool calls and retrieved content as untrusted inputs.

  5. 05

    Version prompts, filters, models, and datasets together; monitor production signals, audit changes, and block promotion when regression thresholds fail.

Working standard

What good use looks like.

  • Evaluate the complete application flow.
  • Measure false positives and false negatives.
  • Version guardrails with prompts and models.

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.

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 collection.