microsoft/Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale

microsoft/Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale

Description: Engineering patterns for taking AI agents to production — deployment, tools, memory, long-running work, human oversight, and observability at scale. From Microsoft Build 2026.

Language: Python

License: MIT

Stars: 10

Forks: 10

Open issues: 1

Created: 2026-04-10T22:44:09Z

Pushed: 2026-08-19T20:50:08Z

Default branch: main

Fork: no

Archived: yes

README:

Microsoft Build 2026

🚀 BRK241: From Prototype to Production — Build and Run Agents at Scale

Session Description

Taking an AI agent from a working prototype to a reliable, scalable production service involves real engineering: deployment, tools, memory, long-running work, human oversight, and observability. This breakout walks that journey using two sample agents you can run yourself on Microsoft Foundry:

• `field-ops-agent` — a voice-enabled field technician assistant built on the

Microsoft Agent Framework, showing tools, an MCP Toolbox connection, an optional Microsoft Fabric data agent, and procedural memory.

• `fibey-coordinator` — a long-running network operations coordinator that

monitors telemetry, persists context across sessions, scales to zero while waiting, gates actions behind human-in-the-loop approvals, and can work in Microsoft Teams.

Together they form a multi-agent system: the coordinator delegates technician questions to — and hands work orders off to — the field-ops agent over its Responses endpoint (the *agent-as-tool* pattern, opt-in via FIELD_OPS_AGENT_ENDPOINT).

Both agents deploy with a single azd command, emit traces to Application Insights, and ship with sample tool data so they run end-to-end out of the box.

🚀 Getting started

You can deploy both agents to your own Microsoft Foundry project with the Azure Developer CLI.

Prerequisites

• An Azure subscription with access to Microsoft Foundry
• Azure Developer CLI (`azd`) v1.24+
• The Foundry agents extension: azd extension install azure.ai.agents
• Python 3.12+

Required permissions

azd provision creates the Foundry project, model deployment, ACR, storage, and App Insights — and assigns Azure RBAC role assignments to the agent and project identities. To run the full deploy you need:

| Role | Scope | Why | |:-----|:------|:----| | Contributor | Subscription (or target resource group) | Provision and manage the Azure resources. | | User Access Administrator *(or Owner instead of both)* | Subscription (or resource group) | The Bicep templates create Microsoft.Authorization/roleAssignments; Contributor alone cannot write role assignments and azd provision will fail with AuthorizationFailed. | | Foundry Owner | Subscription / Foundry account | Required because azd provision creates a new Foundry project. | | Foundry Project Manager | Foundry project | Create and deploy the hosted agents, and assign Foundry User to the platform-created agent identity at deploy time. |

> The azd tooling assigns the remaining runtime roles automatically — > Container Registry Repository Reader for the project managed identity and > Foundry User for each agent's Entra identity. Optional integrations > (Search, Storage, Teams) need extra role grants on the agent's identity; those > are documented in > [src/field-ops-agent/SETUP-INTEGRATIONS.md](src/field-ops-agent/SETUP-INTEGRATIONS.md) > and [src/fibey-coordinator/TEAMS-SETUP.md](src/fibey-coordinator/TEAMS-SETUP.md). > The Foundry roles above were previously named Azure AI Owner / Azure AI > Project Manager / Azure AI User — you may still see the old names during > the rename rollout. See > Hosted agent permissions reference.

Clone and deploy

git clone https://github.com/microsoft/Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale.git
cd Build26-BRK241-from-prototype-to-production-build-and-run-agents-at-scale

# Install the Foundry agents azd extension (first time only)
azd extension install azure.ai.agents

# Log in and select the subscription that will host the project
azd auth login
az login

# Provision the Foundry project, model deployment, ACR, and App Insights
azd provision

After provisioning, set your tenant ID so azd deploy can complete the agent's RBAC setup:

# Bash / macOS / Linux
export AZURE_TENANT_ID=$(az account show --query tenantId -o tsv)
azd deploy

# PowerShell (Windows)
$env:AZURE_TENANT_ID = (az account show --query tenantId -o tsv)
azd deploy

Deploy a single agent with azd deploy field-ops-agent or azd deploy fibey-coordinator. Tear everything down with azd down.

See [src/field-ops-agent/](src/field-ops-agent/README.md) and [src/fibey-coordinator/](src/fibey-coordinator/README.md) for per-agent details, example prompts, and the optional integrations (Toolbox, Fabric, Teams, Durable Task Scheduler).

Connect the two agents (multi-agent)

By default each agent runs standalone. To turn on the coordinator → field-ops handoff (so fibey-coordinator delegates technician questions to — and hands work orders off to — the field-ops-agent), point the coordinator at the deployed field-ops agent and redeploy it:

# 1. Both agents must be deployed first (azd deploy above does both)
azd deploy field-ops-agent
azd show # copy the field-ops-agent endpoint / playground URL

# 2. Point the coordinator at the field-ops agent's Responses endpoint
azd env set FIELD_OPS_AGENT_ENDPOINT ""

# 3. Grant the coordinator's managed identity permission to invoke the
# field-ops hosted agent (Foundry User on the project / agent), then redeploy
azd deploy fibey-coordinator

When FIELD_OPS_AGENT_ENDPOINT is unset, the coordinator still runs — its ask_field_ops / dispatch_work_order tools just return a graceful "not configured" note. Details: [src/fibey-coordinator/README.md](src/fibey-coordinator/README.md#connecting-to-the-field-ops-agent-multi-agent).

> Wiring the `supplier_docs` knowledge tool (Foundry IQ): azd provision / > azd deploy create the agents, but the supplier-docs knowledge tool needs a few > extra steps (embedding model,...