First page of Microsoft's 100,000-partner directory, sorted by responsiveness Microsoft Solutions Partner — Security, Modern Work, Infrastructure, App Innovation Microsoft partner since 2006 1,100+ organizations under management
Home/Services/AI Agent Development with Microsoft Foundry
Development

AI Agent Development with Microsoft Foundry

AI Agent Development with Microsoft Foundry designs, builds, evaluates, and deploys production pro-code AI agents on Microsoft Foundry — the platform Microsoft renamed from Azure AI Foundry. Scope covers retrieval-augmented generation (RAG) over your company data, function and tool calling into Microsoft Graph and line-of-business systems, multi-agent orchestration where the workflow justifies it, automated evaluations, content-safety guardrails, and telemetry — with the finished agent deployed to Microsoft Teams, a web experience, or Microsoft 365 Copilot. Work is time and materials at $175 per hour, typically from $12,500, and a typical build runs about six weeks; final scope depends on data readiness, integrations, security requirements, and the number of environments and channels.

Timeline 6 weeksService owner Nick SavenMicrosoft FoundryMicrosoft AzureMicrosoft Teams

What this engagement is

Microsoft renamed Azure AI Foundry to Microsoft Foundry at Ignite in November 2025, and the new name became official in Microsoft's Product Terms in January 2026. The platform, SDKs, and your existing Azure resources are the same — this page uses the current name throughout. This service is for organizations whose agent use case has outgrown low-code tooling: you need control over model selection, the retrieval pipeline, orchestration logic, source control, CI/CD, and measurable answer quality. We build on Foundry Agent Service and the Foundry SDKs — grounding the agent in your data through a retrieval index, wiring tool calls into Microsoft Graph and your business systems, adding evaluation runs and content-safety filters before launch, and instrumenting telemetry so you can see what the agent actually does in production. The engagement is engineering-led: everything lives in a repository you own, and the agent ships only after it passes the evaluation set you approved. If your scenario fits a low-code build, our Custom Agent Development with Microsoft Copilot Studio service is the right starting point instead — we will tell you which one applies during scoping.

Success criteria

01The approved use case, target users, data sources, tools, risk boundaries, and human-oversight rules are documented before build work starts.
02The agent answers from your approved data sources with citations, and tool calls execute only against the systems and permissions you signed off.
03An evaluation set covering functional, grounding, safety, and failure-path cases runs green before the agent reaches real users, and the results are shared with you.
04Content-safety filters, authentication, least-privilege access, and telemetry are configured and demonstrated, not just described.
05The agent is deployed to the agreed channel (Teams, web, or Microsoft 365 Copilot) and validated by a limited pilot group before wider release.
06You receive the source repository, infrastructure definitions, evaluation assets, operating documentation, and a prioritized improvement backlog.

What you receive

Use-case definition, feasibility, and solution-architecture record, including the build-vs-Copilot-Studio decision and its rationale.
A working agent on Foundry Agent Service: model deployment, instructions, retrieval-augmented grounding over your approved data, and function/tool calling into Microsoft Graph or line-of-business systems within scope.
Retrieval pipeline configuration — indexing, chunking, and permission handling for the grounding sources agreed at scoping.
Automated evaluation set with baseline results, plus content-safety and guardrail configuration with documented settings.
Deployment to the agreed channel (Microsoft Teams, web front end, or Microsoft 365 Copilot) with authentication and telemetry wired in.
Source code repository, infrastructure-as-code where used, operating runbook, and handoff session with your team.
Prioritized improvement backlog and a written recommendation on ongoing operations.

How the work unfolds

Milestone 1

Discovery and use-case framing — confirm the business goal, target users, success measures, risk profile, and the level of autonomy the agent is allowed; validate that pro-code Foundry work is warranted over a low-code build.

Milestone 2

Architecture and data review — assess grounding sources, permission models, model availability in your Azure region, integration targets, compliance constraints, and environment strategy; produce the solution design.

Milestone 3

Environment setup — provision or validate the Foundry project, model deployments, retrieval index, source repository, and CI/CD path in your Azure subscription.

Milestone 4

Grounding build — index the approved data sources, implement the retrieval pipeline, and verify that answers respect existing permissions.

Milestone 5

Tools and orchestration — implement function/tool calling into Microsoft Graph and scoped business systems; add multi-agent orchestration only where the design calls for it.

Milestone 6

Evaluation and safety — build the evaluation set with your subject-matter experts, run it against the agent, configure content-safety filters and guardrails, and iterate until agreed thresholds pass.

Milestone 7

Pilot and deployment — publish to the agreed channel for a limited pilot group, review telemetry and feedback, fix what the pilot surfaces, then release to the approved audience.

Milestone 8

Handoff — walk your team through the repository, runbook, evaluation assets, and telemetry; deliver the improvement backlog and the operations recommendation.

Prerequisites

An Azure subscription where the Foundry project, model deployments, and supporting resources will run, with agreed rights for our engineers to deploy into it.
A Microsoft 365 tenant and Entra ID in place if the agent will be deployed to Teams or Microsoft 365 Copilot, with the licensing your chosen channel requires.
Grounding data sources identified, accessible, and permissioned — SharePoint sites, databases, file stores, or APIs — in good enough shape to index.
A named business owner, a technical owner, and subject-matter experts available for scoping, evaluation-case review, and pilot feedback.
Access to the line-of-business systems and APIs the agent must call, including service accounts, app registrations, or credentials where actions are in scope.
Your security, privacy, and compliance requirements stated before production deployment — including any data-residency or model-region constraints.
Awareness that model availability varies by Azure region and that Azure consumption (model tokens, retrieval index, hosting) is billed by Microsoft to your subscription, separate from our fees.

Who does what

IT Partner

  • Use-case feasibility, solution architecture, and the honest pro-code-versus-low-code recommendation.
  • Foundry project setup, model deployment, and retrieval pipeline implementation in your Azure subscription.
  • Agent build: instructions, grounding, function/tool calling, and orchestration code in a repository you own.
  • Evaluation set construction, content-safety and guardrail configuration, and pre-launch test runs.
  • Deployment to the agreed channel, telemetry wiring, pilot support, and fixes for what the pilot surfaces.
  • Documentation, runbook, handoff, and the written operations recommendation.

Your team

  • Provide the business goal, priority scenarios, acceptance criteria, and realistic test questions with expected answers.
  • Assign business, technical, and security owners with authority to make timely decisions and approvals.
  • Provide or approve Azure subscription access, tenant roles, service accounts, app registrations, and integration credentials.
  • Prepare and permission the grounding data sources; own the quality of the underlying content.
  • Purchase Microsoft licensing and carry Azure consumption costs for the agent's resources.
  • Review evaluation results, participate in the pilot, and approve production release.
  • Own internal communication, adoption, and business-process decisions after handoff unless separately contracted.

What's not included

Low-code agent builds in Microsoft Copilot Studio — that is a separate, usually less expensive service (Custom Agent Development with Microsoft Copilot Studio), and we will route you there when it fits.
Training or fine-tuning custom models. We select, configure, and ground existing models; model training is a different engagement.
Microsoft licensing and Azure consumption — model tokens, retrieval index capacity, hosting, and any Microsoft 365 Copilot or channel licensing are billed by Microsoft to you.
Broad data cleanup, permission remediation, or content restructuring beyond what the scoped grounding sources require — larger cleanup is quoted separately.
Ongoing operations after handoff — monitoring, prompt and knowledge refresh, and cost review are covered by our Managed AI Agent Operations and Optimization service, not this project.
An enterprise AI governance or security program. We configure the agent's own guardrails; tenant-wide AI security and data-governance work is covered by our AI security and Purview services.
Guaranteed model accuracy, deterministic outputs, or business outcomes — generative systems are probabilistic, and we commit to the evaluation process, not to a number invented before we see your data.

Limitations & technical notes

!Agent quality is bounded by the quality, permissions, and freshness of the grounding data; weak source content produces weak answers no matter how good the engineering is.
!Generative outputs are probabilistic. Evaluation sets, guardrails, and telemetry reduce risk; they do not eliminate it, and higher-risk scenarios should keep a human in the loop.
!Model catalog, feature names, and regional availability on Microsoft Foundry change frequently — the design is validated against what your subscription and region actually offer at project start, and the naming on this page reflects Microsoft's Product Terms as of January 2026.
!Azure consumption costs scale with usage and are difficult to predict precisely before the pilot; we instrument cost telemetry early so the pilot produces a real number rather than a guess.
!Actions against business systems depend on API availability, permissions, and service limits in those systems; some integrations surface constraints only during build.
!Timeline depends on client-side access provisioning, data readiness, and review cycles — the six-week typical duration assumes prerequisites are met at kickoff.

Frequently asked questions

Is Microsoft Foundry the same thing as Azure AI Foundry?

Yes. Microsoft renamed Azure AI Foundry to Microsoft Foundry at Ignite in November 2025, and the new name became official in Microsoft's Product Terms in January 2026. The platform, SDKs, and existing deployments are unchanged — if your team still says 'Azure AI Foundry,' you are talking about the same thing this service builds on.

When do we need Foundry instead of Copilot Studio?

Choose pro-code Foundry work when you need control that low-code tooling doesn't give you: model selection, a custom retrieval pipeline, orchestration logic in source control, CI/CD, automated evaluations, or a custom user experience. If your scenario is a governed Q&A or workflow agent over Microsoft 365 data, our Copilot Studio service is usually faster and cheaper — and we'll say so during scoping.

Can the agent answer from our company data?

Yes — grounding the agent in your data is the core of the service. We build a retrieval-augmented generation (RAG) pipeline over approved sources such as SharePoint, databases, file stores, or APIs, and verify during evaluation that answers come from those sources and respect existing permissions.

Can the agent take actions, not just answer questions?

Yes. We implement function and tool calling so the agent can call Microsoft Graph and your line-of-business systems — creating records, looking up orders, filing tickets — within the permissions you approve. Every action path is covered by the evaluation set and scoped to least-privilege access.

Do you build multi-agent solutions?

When the workflow justifies it. Foundry supports orchestrating multiple specialized agents, and we design that way when a single agent would become an unmaintainable monolith. We don't add multi-agent complexity for its own sake — it increases cost, latency, and testing surface.

Which models can we use?

Foundry exposes a large model catalog, including OpenAI models and others, with availability varying by Azure region. We recommend a model based on your quality, latency, cost, and data-residency requirements, and validate the choice against what your subscription and region actually offer at project start.

How do you make sure the agent is safe and accurate before launch?

We build an evaluation set with your subject-matter experts — real questions with expected answers, plus failure and abuse cases — and run it against the agent before any user sees it. Content-safety filters and guardrails are configured and tested, and the agent ships only after the evaluation results you approved pass.

Where can the agent be deployed?

To Microsoft Teams, a web front end, or Microsoft 365 Copilot, depending on where your users work and what your licensing supports. The channel is agreed at scoping because it affects authentication, licensing, and the user experience we build.

How much does it cost?

Work is time and materials at $175 per hour, with typical projects starting from $12,500. The estimate is put in writing before work begins. Cost drivers are the number of grounding sources, the integrations the agent must call, evaluation depth, and how many environments and channels you need. Azure consumption is separate and billed by Microsoft to your subscription.

How long does a build take?

A typical build runs about six weeks from kickoff to handoff, assuming prerequisites — Azure access, data sources, and named owners — are ready at the start. Complex integrations, multiple channels, or slow review cycles extend that.

Who owns the code and the Azure resources?

You do. Everything is built in your Azure subscription and delivered in a source repository you own, with infrastructure definitions and an operating runbook. There is no proprietary layer of ours between you and the solution.

Is our data used to train the models?

Per Microsoft's documented data-privacy commitments for its Azure-hosted AI services, your prompts, retrieval data, and outputs are not used to train Microsoft's foundation models. Your data stays in your subscription, and we configure the agent to respect your existing permissions. Your compliance team should review Microsoft's current terms for your specific requirements.

What happens after the agent goes live?

The project ends with handoff: repository, runbook, evaluation assets, telemetry, and an improvement backlog. Agents drift after launch — knowledge goes stale, costs creep, usage shifts — so we recommend our Managed AI Agent Operations and Optimization service for ongoing monthly operations, or your team can run it from the runbook.

Do you train or fine-tune custom models?

No — model training and fine-tuning are outside this service. In our experience most business agent use cases are solved better and cheaper with the right existing model plus good retrieval and evaluation. If scoping shows your case genuinely needs fine-tuning, we'll say so and scope it separately.

What do we need to have ready before starting?

An Azure subscription we can deploy into, identified and accessible grounding data sources, named business and technical owners, access to any systems the agent must call, and your security and compliance requirements stated up front. The six-week typical timeline assumes these are in place at kickoff.

What is not included?

Low-code Copilot Studio builds (separate service), model training, Microsoft licensing and Azure consumption, broad data cleanup, ongoing operations after handoff, and enterprise-wide AI governance programs. Each has a named home in our catalog, and we cross-refer rather than blur the scope.

Didn’t find your question?

Ask it here. A real engineer answers by email within one business day — and if it’s a good one, it becomes part of this page so the next person finds it.

Answered by a person, one time, to your inbox. Nothing you type here is published without a human reviewing and anonymizing it first.

Often combined with

Time & materials; typical from $12,500
6 weeks
Scope my agent build