foundry-agent/deploy/deploy.md
Deploy a Foundry Agent
Provision Azure resources when needed, deploy the agent, and smoke-test it.
For hosted agents (custom container or code), use azd deploy.
For Voice Agents, use azd deploy and smoke-test over the voice WebSocket endpoint.
For Managed Harness Agents (kind: prompt plus the Copilot harness), use azd deploy.
For ordinary prompt agents, use the Foundry MCP agent_update tool.
Quick Reference
| Property | Value |
|----------|-------|
| Hosted (recommended) | azd provision when needed, code deploy via azd deploy (codeConfiguration present), then verify and invoke |
| Hosted (container) | azd provision when needed, container deploy via azd deploy (remote builds require a Dockerfile and ACR; local builds also require Docker; no codeConfiguration: in the azure.yaml service block) |
| Voice (Prompt Voice) | azd provision when needed, declarative azd deploy, then verify over the voice WebSocket endpoint (azd ai agent invoke is not supported) |
| Voice (Hosted Voice) | azd provision when needed, azd deploy for both the kind: hosted target and kind: voice wrapper, report both versions separately, and smoke-test the wrapper over the voice WebSocket endpoint |
| Managed Harness Agent | azd provision when needed, then declarative azd deploy; no code/container packaging |
| Prompt MCP | agent_definition_schema_get, agent_update, agent_get, agent_delete |
| Versioning | Each successful azd deploy creates an immutable agent version |
| Endpoint-only patch | azd ai agent endpoint update (no new version) |
| Local dev | create-hosted, create-voice, local-run |
Route by Agent Type
- Voice Agent (single-agent Prompt Voice or two-agent Hosted Voice wrapper +
kind: hostedtarget) -> Voice (azd Voice workflow below). - Shipping Python / .NET code (
kind: hosted) -> Hosted (azd workflow below). - Explicit
kind: promptplusharness.type: microsoft_copilot_previewor legacygithub_copilot_preview-> Managed Harness Agent (azd workflow below). - Ordinary Prompt Agent model / instructions / tools -> Prompt (MCP workflow below).
Deploy Mode Selection -- Hosted agents
Follow the user's explicit deploy mode preference or the existing project configuration. Otherwise, use code deploy through azd by default (no Docker/ACR required): the agent's azure.yaml service block must contain codeConfiguration:, so azd deploy will zip the source and let Foundry build it. If azd deploy prints Packaging container for an agent that does not need container-specific behavior, add or fix codeConfiguration and retry.
When the agent depends on Dockerfile behavior, system packages, or a pre-built image, or when the user explicitly asks to build or deploy a container image, mentions Container/Docker Image/Azure Container Registry (ACR), or supplies a pre-built image, use container deploy.
Before running azd deploy, inspect the agent's service block in azure.yaml.
| Service block state | Deployment path |
|------------------|-----------------|
| codeConfiguration: present | Code deploy through azd deploy; no Docker/ACR build. |
| No codeConfiguration: with language: docker | Container deploy through azd deploy. |
codeConfiguration: example in the azure.yaml service block:
services:
<agent-name>:
host: azure.ai.agent
codeConfiguration:
runtime: python_3_13
entryPoint: main.py
dependencyResolution: remote_build
Remote ACR build example in the azure.yaml service block:
services:
<agent-name>:
host: azure.ai.agent
language: docker
docker:
remoteBuild: true
Workflow -- Hosted agent (azd)
Prerequisite: project scaffolded with
azd ai agent init. If not, start at create-hosted.
Step 1 -- Resolve azd environment
If the user provided an existing project endpoint, project ARM ID, or model deployment, set those values before deploy:
azd env set AZURE_AI_PROJECT_ENDPOINT "<project-endpoint>"
azd env set AZURE_AI_PROJECT_ID "<project-arm-id>"
azd env set AZURE_AI_MODEL_DEPLOYMENT_NAME "<model-deployment-name>"
If using container deploy and the user provided an existing ACR, set:
azd env set AZURE_CONTAINER_REGISTRY_NAME "<acr-name>"
azd env set AZURE_CONTAINER_REGISTRY_ENDPOINT "<acr-login-server>"
azd env set AZURE_CONTAINER_REGISTRY_RESOURCE_ID "<acr-resource-id>"
Verify the azd environment with azd env get-values.
Run:
azd ai project show --output json
azd ai agent show --output json
Branch on output: not_deployed -> Step 2. active / deployed -> redeploy (skip Step 2, go to Step 3). If azd ai project show fails with missing_project_endpoint, do Step 2 first -- azd provision will create the project.
Important: Before deploy, also make sure the agent's
azure.yamlservice block and the azd environment are aligned with the user's provided configuration values.
Step 2 -- Provision Azure resources (one-time per env)
🚦 Project-selection gate. If no foundry project endpoint is configured (not in the message,
azd env, or.env) and the user hasn't asked to create one, stop and ask them to pick an existing foundry project or confirm creating a new one — don't silently select.
Skip azd provision when the user gave you an existing AZURE_AI_PROJECT_ENDPOINT or FOUNDRY_PROJECT_ENDPOINT and no infrastructure changes are needed. If container deploy needs a new ACR, run azd provision even when using an existing Foundry project.
Run provision only for new projects or real infrastructure changes:
azd provision --no-prompt
Optional: run
azd provision --preview --no-promptfirst to preview the resource changes (a what-if) before applying them.Optional: add
--no-stateon a fresh azd environment to skip the existing-deployment check and provision faster; omit it when re-provisioning an existing one.
What this does:
- Creates the Foundry project (if not present) and supporting resources under
infra/. - Creates connections declared as top-level
azure.ai.connectionservices.${PARAM_*}placeholders resolve from the active azd env. - Wires model deployments, AI Search, ACR, etc.
infra/layers/provision in parallel when present.
After provision completes for a new project, run azd env get-values and set missing required azd env values, especially AZURE_AI_PROJECT_ID and AZURE_TENANT_ID, before local run or the first azd deploy.
Step 3 -- Pre-deployment check
Branch by deploy mode.
Code deploy
Run azd env get-values and verify that these values are set for the intended
environment:
AZURE_AI_PROJECT_ENDPOINTAZURE_AI_PROJECT_IDAZURE_AI_MODEL_DEPLOYMENT_NAMEAZURE_TENANT_ID
For Python, verify that <service-dir>/.agentignore excludes .venv/, adding the rule if missing.
Container deploy
Complete the Container Deploy Precheck before continuing.
Step 4 -- Deploy the agent
Private package index: If
azd deployfails and the user'suv.lockpoints to a private Python package index, the Foundry service might be unable to access the index when installing dependencies. Guide the user to regenerateuv.lockusing the public PyPI index, or export the locked dependencies to arequirements.txtfile with pinned versions, and then retry the deployment.
azd deploy --no-prompt
# Multi-service:
azd deploy <service-name> --no-prompt
What deploy does:
- Reads the agent's
azure.yamlservice block, packages the agent, uploads it, and registers a new immutable version. - Code deploy (
codeConfigurationpresent): zips source, excludes.agentignore, and lets Foundry build the runtime image. - Container deploy (no code configuration): builds the
Dockerfile, pushes to the project's ACR, registers the version. When the service block hasimage:set,azdreuses the pre-built image.
After deploy, azd writes AGENT_<SVC>_NAME, AGENT_<SVC>_VERSION, and AGENT_<SVC>_<PROTO>_ENDPOINT (one per protocol) into the active env.
For agents with Activity protocol, azd deploy also generates <service-dir>/TEAMS_APP_SETUP.md; read it and explain the remaining post-deployment steps to the user.
Re-deploying an identical build still creates a new version; azd prints Agent version <n> is already active. and skips the poll.
If deploy reports Done for the service and then fails only in postdeploy with Agent <service-name> with version <n> not found, the azure.yaml service key and the service's name: were mismatched. Rename the azure.yaml services key to the deployed agent name and rerun azd deploy --no-prompt; do not switch deploy mode.
Step 5 -- Verify and invoke
azd ai agent show --output json
Expect "status": "active" (or "deployed") and an agent_endpoints map. Inspect the selected service protocols in azure.yaml, then smoke-test:
For the Responses or Invocations protocol, smoke-test with azd:
azd ai agent invoke "hello, are you up?"
For a multi-protocol service, pass --protocol explicitly.
Remote invocation can incur model usage charges. Run it only as part of the requested deployment or test.
For the Activity protocol, azd ai agent invoke won't work; follow invoke to invoke the agent.
Run one remote invocation only unless the user explicitly asked to test multi-turn/session behavior. A single successful response is enough for the deployment smoke test. Anything other than a completed/successful response -> run azd ai agent doctor --output json, then follow troubleshoot.
Step 6: Auto-Generate Evaluation Suite (MANDATORY — RUNS AUTOMATICALLY)
⚠️ Pre-summary gate. If you are about to write a deployment summary or Playground link and Step 6 has not run, you are violating this skill. Run Step 6 first.
This step runs automatically after deploy. Ask the user which source to use and start it right after deploy succeeds — with --no-wait, generate returns in seconds and generation runs server-side, so it overlaps with invoke/test steps and finishes faster overall.
"Your agent is deployed. Want me to set up an evaluation suite now? (a) Yes — current agent instructions (synthetic Q&A), (b) Yes — historical traces (last 3 days), (c) Yes — use existing
eval.yaml, (d) No / later."
| Choice | Command | What's next |
|---|---|---|
| (a) Agent instructions | azd ai agent eval generate --gen-instruction "<agent purpose>" --no-wait --no-prompt — --gen-instruction is required (hosted agents don't auto-derive it); use the service's description: in azure.yaml. | Generation runs server-side. Tell the user: "Suite submitted. Run azd ai agent eval run whenever you're ready — it'll finalize eval.yaml and execute the eval in one step." |
| (b) Historical traces | azd ai agent eval generate --trace-days 3 --max-samples 50 --no-wait --no-prompt | Same as (a). |
| (c) Existing eval.yaml | Skip generate. | Tell the user: "Using existing eval.yaml. Run azd ai agent eval run when ready." |
| (d) No / later | Skip. | Tell the user: "You can run azd ai agent eval generate (and then eval run) anytime." |
Other useful flags on generate: --dataset <path-or-name> to reuse an existing dataset instead of generating one, --evaluator <name> (repeatable) to pin built-in or custom evaluators, --eval-model <name> to choose the model used for generation and evaluation, --reset-defaults to overwrite an existing eval config, --name <suite-name> and --out-file <path> (default eval.yaml).
Then proceed to Step 7. See After Deployment — Auto-Generate Evaluation Suite for run/refresh details. Run azd ai agent eval run only after the user explicitly agrees.
Step 7 -- Hand off
- Send more messages -> invoke
- Evaluate / optimize -> observe
- Diagnose failures -> troubleshoot
- Search traces / latency -> trace
.agentignore
azd ai agent init writes a default <service-dir>/.agentignore for code deploy projects (gitignore syntax) that excludes tooling files, secrets, language artifacts, and Docker files from the deploy ZIP. Only the root file is read; use !path to force-include.
Endpoint or card edits -- no new version
When only agentEndpoint: or agentCard: changed in the azure.yaml service block:
azd ai agent endpoint update # patch in place
azd ai agent endpoint update --force # skip confirmation for breaking changes
Idempotent.
Multi-environment deploys
azd env list
azd env select prod
azd deploy --no-prompt
Each env has its own AGENT_<SVC>_* vars.
Common failure modes -- Hosted
| Error | Fix |
|-------|-----|
| missing_project_endpoint | Run azd env set AZURE_AI_PROJECT_ENDPOINT <url>, or run azd provision for a new project. |
| invalid_agent_manifest | azd ai agent doctor; fix the named field. |
| invalid_connection | Inspect with azd ai connection show <name>. |
| Docker daemon not running | You are on the container path. Add/fix codeConfiguration and retry code deploy. Only install Docker or try remote image build if you specifically need container deploy. |
| ACR push 403 | Foundry project RBAC is missing AcrPush for your identity. Consider switching to code deploy to avoid ACR entirely. |
| [ImageError] Container registry authentication failed | The Foundry project managed identity lacks AcrPull, or Container Registry Repository Reader on an ABAC registry. Grant it before retrying. |
| container registry endpoint not found | ACR is not configured. Use azd env set AZURE_CONTAINER_REGISTRY_ENDPOINT <url>, or switch to code deploy. |
| Agent version poll times out | Build still running; retry azd ai agent show after a minute. |
| session_not_ready (424) | Cold start or readiness delay. Wait 15-30 seconds and retry. If persistent, use 1 CPU / 2Gi memory minimum, verify the model deployment name, capability host, and agent identity role. |
| invalid value "json" for --output from azd ai agent invoke | Invoke supports only default and raw currently. Retry without --output json. |
| could not resolve agent service in azd project: no azure.ai.agent service named '<agentName>' found in azure.yaml from azd ai agent invoke | Name mismatch. Use the service name, update the azure.yaml service block, or use --agent-endpoint when invoking outside the project. |
| subscription quota exceeded | Ask user to request quota; do not auto-retry. |
| Bicep deploy errors | Forward error.details[] verbatim to the user. |
| RoleAssignmentUpdateNotPermitted during provision | A role assignment already exists but conflicts. Check for existing role assignments with az role assignment list --scope <resource-scope>. The provision may have succeeded for all resources except RBAC — verify with azd ai project show and manually assign the Cognitive Services User role to the agent identity if needed. |
| eval generate: one of --gen-instruction ... is required | Retry with --gen-instruction "<agent purpose>" (Step 6 option (a)). |
| unknown command "init" for "azd ai agent eval" | Command was renamed: use azd ai agent eval generate (requires azd CLI with azure.ai.agents extension up to date). |
For deeper logs, see troubleshoot.
Workflow -- Managed Harness Agent (azd)
A Microsoft Foundry Managed Harness Agent is a declarative Prompt Agent configuration that this workflow deploys with azd. Read create-managed-harness before creating or editing it.
Step 1: Resolve and validate
Inside the azd project, select the service and verify that it is a Prompt Agent using either recognized Copilot harness discriminator. New authoring uses:
host: azure.ai.agent
kind: prompt
harness:
type: microsoft_copilot_preview
Existing services may use legacy github_copilot_preview; preserve the
authored harness and toolset discriminator family. Reject Hosted-only
code/container fields. Do not convert an ordinary Prompt or Hosted Agent in
place.
Resolve the active environment:
azd env get-values
azd ai project show --output json
azd ai agent show --output json
If the Agent is not deployed, continue to provisioning. If active/deployed, skip provisioning unless infrastructure changed.
Step 2: Provision when required
Run azd provision --no-prompt only for a new Foundry project, a new model deployment, or another real infrastructure change. If no project is configured and the user did not select a new or existing project, stop and ask.
A Managed Harness Agent does not require Hosted Agent source packaging, Docker, ACR, runtime, protocol, or container configuration.
Step 3: Deploy
azd deploy <service-name> --no-prompt
Deployment reads the Prompt Agent definition from azure.yaml and creates a new immutable version. It must not package source or build a container.
Step 4: Verify and invoke
azd ai agent show --output json
Verify the version is active/deployed and the published definition retains:
kind: prompt- New definitions use
harness.type: microsoft_copilot_preview. - Existing definitions retain their authored Microsoft or legacy GitHub harness/toolset discriminator family.
- Requested direct tools
- Exact versioned Toolbox MCP endpoint and matching short
project_connection_id, when explicitly configured - Versioned Skill references, when explicitly configured
A successful deploy that drops the harness is a failure. A redeploy that silently changes an existing Copilot harness or toolset discriminator family is also a failure.
Run one remote smoke invocation:
azd ai agent invoke <service-name> "hello, are you up?"
Follow the Managed Harness Agent branch in invoke. Do not use Hosted sessions/files/monitor and do not start evaluation generation in Phase 1.
Step 5: Hand off
Show Agent name, version, project, model, harness, tools, optional Toolbox, deployment status, and smoke-test status.
Common failure modes -- Managed Harness Agent
| Error | Fix |
|---|---|
| Deploy packages code/container | Remove Hosted-only fields and verify kind: prompt |
| Published definition lacks harness | Fix harness.type, verify the extension version, and redeploy |
| Tool shape rejected | Read the matching Managed Harness Agent tool reference and preserve REST field names |
| Connection missing | Use a user-supplied/existing configured connection, or create it only on explicit request |
| Toolbox MCP returns 401 | Verify the MCP tool has a matching UserEntraToken project connection with audience https://ai.azure.com and target equal to the exact versioned Toolbox endpoint |
Workflow -- Voice Agent (azd)
Follow Voice Agent deployment for Prompt Voice and Hosted Voice provisioning, deployment order, and two-stage verification.
Workflow -- Prompt agent (MCP)
Ordinary Prompt Agents are not containerized -- they are a model + instructions + optional tools, created through the Foundry MCP server. Do not use this branch for a Managed Harness Agent.
MCP tools
| Tool | Purpose |
|------|---------|
| agent_definition_schema_get | Get the schema (schemaType: "prompt"). |
| agent_update | Create or update; supports isCloneRequest + cloneTargetAgentName. |
| agent_get | List or fetch one. |
| agent_delete | Delete an agent. |
Steps
- Collect config -- resolve endpoint from
azd env get-valuesor ask. Then ask for agent name, model deployment (e.g.gpt-4o), and optional instructions, temperature, tools. - Get schema --
agent_definition_schema_getwithschemaType: "prompt". - Create --
agent_updatewith{"kind": "prompt", "model": "<deployment>", "instructions": "...", "temperature": 0.7}. - Smoke test -- follow invoke.
- Auto-generate evaluation suite -- see Step 5: Auto-Generate Evaluation Suite (Prompt) below.
- Hand off -- evaluate via observe; clone via
agent_update+isCloneRequest; delete viaagent_delete.
Step 5: Auto-Generate Evaluation Suite (Prompt) (MANDATORY — RUNS AUTOMATICALLY)
⚠️ Pre-summary gate. If you are about to write a deployment summary or Playground link and Step 5 has not run, you are violating this skill. Run Step 5 first.
This step runs automatically after deploy. Ask the user which source to use and start it right after deploy succeeds — with --no-wait, generate returns in seconds and generation runs server-side, so it overlaps with invoke/test steps and finishes faster overall.
"Your agent is deployed. Want me to set up an evaluation suite now? (a) Yes — current agent instructions (synthetic Q&A), (b) Yes — historical traces (last 3 days), (c) Yes — use existing
eval.yaml, (d) No / later."
| Choice | Command | What's next |
|---|---|---|
| (a) Agent instructions | azd ai agent eval generate --gen-instruction "<agent purpose>" --no-wait --no-prompt | Generation runs server-side. Tell the user: "Suite submitted. Run azd ai agent eval run whenever you're ready — it'll finalize eval.yaml and execute the eval in one step." |
| (b) Historical traces | azd ai agent eval generate --trace-days 3 --max-samples 50 --no-wait --no-prompt | Same as (a). |
| (c) Existing eval.yaml | Skip generate. | Tell the user: "Using existing eval.yaml. Run azd ai agent eval run when ready." |
| (d) No / later | Skip. | Tell the user: "You can run azd ai agent eval generate (and then eval run) anytime." |
Common failure modes -- Prompt
| Error | Fix |
|-------|-----|
| Schema fetch failed | Verify endpoint format: https://<resource>.services.ai.azure.com/api/projects/<project>. |
| Agent creation failed | Use agent_definition_schema_get to verify the definition. |
| Permission denied | User needs Foundry User role on the project. |
| Model not found | Deploy the model first via models/deploy-model. |
Display agent details
After a successful deploy, show the agent's name, version, status, and endpoints in a table. Include a Playground link:
https://ai.azure.com/nextgen/r/{encodedSubId},{resourceGroup},,{accountName},{projectName}/build/agents/{agentName}/build?version={agentVersion}
encodedSubId is the subscription GUID as URL-safe base64 (no =):
python -c "import base64,uuid;print(base64.urlsafe_b64encode(uuid.UUID('<SUBSCRIPTION_ID>').bytes).rstrip(b'=').decode())"
For hosted agents, playground_url is in azd ai agent show --output json.
After Deployment — Auto-Generate Evaluation Suite
Reference for Step 6 options (a) and (b) — start
generateright after deploy so its server-side generation overlaps with invoke/test steps and finishes faster. Options (c) and (d) skipgenerateand go straight to section 3 (run) or stop.
1. Inspect existing eval.yaml
Check the selected agent root for eval.yaml:
- Exists and matches the selected agent → skip
generate; go to step 3 (run). - Missing or stale → continue to step 2.
2. Submit generation (asynchronous, server-side)
Run azd ai agent eval generate --no-wait with the user's chosen flags (see the Step 6 table). The command:
- Submits dataset + evaluato