Aspire
microsoft/aspire.dev
Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps.
Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry.
Install Deploying Scalable Agents
$ npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/ai-agents-for-beginners deploying-scalable-agents --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deploying-scalable-agents .claude/skills/deploying-scalable-agents && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "deploying-scalable-agents" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agents into .claude/skills/deploying-scalable-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploying-scalable-agents", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agentsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/ai-agents-for-beginners deploying-scalable-agents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/deploying-scalable-agents .agents/skills/deploying-scalable-agents && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deploying-scalable-agents" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agents into .agents/skills/deploying-scalable-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploying-scalable-agents", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/ai-agents-for-beginners deploying-scalable-agents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/deploying-scalable-agents .cursor/skills/deploying-scalable-agents && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "deploying-scalable-agents" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agents into .cursor/skills/deploying-scalable-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploying-scalable-agents", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/microsoft/ai-agents-for-beginners.git --path .agents/skills/deploying-scalable-agents--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/ai-agents-for-beginners deploying-scalable-agents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/deploying-scalable-agents .gemini/skills/deploying-scalable-agents && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "deploying-scalable-agents" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agents into .gemini/skills/deploying-scalable-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploying-scalable-agents", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install microsoft/ai-agents-for-beginners deploying-scalable-agentsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/deploying-scalable-agents .github/skills/deploying-scalable-agents && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "deploying-scalable-agents" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agents into .github/skills/deploying-scalable-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploying-scalable-agents", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/ai-agents-for-beginners deploying-scalable-agents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/deploying-scalable-agents .opencode/skills/deploying-scalable-agents && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "deploying-scalable-agents" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/.agents/skills/deploying-scalable-agents into .opencode/skills/deploying-scalable-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploying-scalable-agents", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
deploying-scalable-agents- GitHub stars
- 77k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 600 words
- Files
- 1
- Skills in repo
- 123
- Repo updated
- First seen
- Licence
- MIT
At a glance
Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry.
- Works in 3 steps: Client-hosted — the reasoning loop runs… → Hosted agent (Foundry Agent Service) —… → Agent workflow — multiple agents/tools…
- : deploy an agent to production
- SKILL.md covers Triggers, Core mental model, Deployment patterns (pick one,… and Lifecycle (the loop that ships…, plus 5 more sections
- Calls az; reaches ai.azure.com
What it does
Deploying Scalable Agents is an agent skill from microsoft/ai-agents-for-beginners, published by the product's own GitHub organization. Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry. Covers deployment patterns (client-hosted, hosted agents, agent workflows), the agent lifecycle, model routing, response caching, evaluation gates, human-in-the-loop approval, observability with OpenTelemetry, cost optimisation, and smoke-testing deployed agents with the AI Smoke Test action. Based on Lesson 16 of AI Agents for Beginners. USE FOR: deploy an agent to production, scale an agent, Microsoft Foundry…
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Observability, Caching and QA and bug reports. It works with Microsoft Azure and OpenTelemetry. The repository describes itself as: 18 Lessons to Get Started Building AI Agents. The licence is MIT.
When your agent uses it
- : deploy an agent to production
- Microsoft Foundry hosted agent
- Foundry Agent Service
- Response caching
Example prompts
- “/deploying-scalable-agents”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Client-hosted — the reasoning loop runs in your process. Max control; you own scaling/state.
- Hosted agent (Foundry Agent Service) — Foundry hosts the loop, stores threads, enforces RBAC/content safety, shows the agent in the…
- Agent workflow — multiple agents/tools composed into a graph with branching, approval nodes, and durable checkpoints.
What it can do on your machine
Read from SKILL.md and the folder at commit 25b7985. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
az
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
ai.azure.com
Also links to:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Deploying Scalable Agents loads about 1.5k tokens when it runs. Until then it costs about 253 tokens; SKILL.md has 600 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from microsoft/ai-agents-for-beginners at commit 25b7985, republished under its MIT licence (© microsoft). 600 words, ~1,508 tokens.
Download SKILL.mdSave it as
.claude/skills/deploying-scalable-agents/SKILL.md (or your agent's skills folder).- name
- deploying-scalable-agents
- description
- Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry. Covers deployment patterns (client-hosted, hosted agents, agent workflows), the agent lifecycle, model routing, response caching, evaluation gates, human-in-the-loop approval, observability with OpenTelemetry, cost optimisation, and smoke-testing deployed agents with the AI Smoke Test action. Based on Lesson 16 of AI Agents for Beginners. USE FOR: deploy an agent to production, scale an agent, Microsoft Foundry hosted agent, Foundry Agent Service, model routing, response caching, evaluation gate, release gate, human approval workflow, agent observability, agent tracing, agent cost optimisation, smoke test a hosted agent, production customer support agent. DO NOT USE FOR: building your first agent (start with Lesson 01), running agents locally on-device (use local-ai-agents / Lesson 17), Azure infrastructure provisioning unrelated to agents, non-Foundry deployment targets.
- license
- MIT
Deploying Scalable Agents with Microsoft Foundry
Companion skill for Lesson 16 – Deploying Scalable Agents. Use it to help a learner move an agent from prototype to a scalable, observable production deployment. Ground every recommendation in the lesson content and the runnable notebook; do not invent Foundry APIs.
Triggers
Activate this skill when a learner wants to:
- Deploy an agent to Microsoft Foundry as a hosted agent and make it versioned/observable.
- Choose between client-hosted, hosted-agent, and agent-workflow deployment patterns.
- Add model routing, response caching, or bounded concurrency to control latency and cost.
- Add an evaluation gate so a bad agent version cannot ship.
- Add a human-in-the-loop approval step for high-risk actions.
- Instrument an agent with OpenTelemetry tracing for production observability.
- Smoke-test a deployed agent as a fast post-deploy gate.
Core mental model
A production agent is mostly the operational skeleton around the model (~80%), not the model itself. Map every recommendation to one of these concerns:
| Concern | Prototype → Production |
|---|---|
| Hosting | notebook → versioned hosted service |
| Identity | your az login → managed identity + scoped RBAC |
| State | in-memory → externalised thread/memory store |
| Failure | traceback → retries, fallbacks, alerts |
| Cost | "a few cents" → tracked, routed, cached, budgeted |
| Quality | eyeballing → automated evaluation gate |
| Trust | you approve → policy + human-in-the-loop |
Deployment patterns (pick one, or combine)
- Client-hosted — the reasoning loop runs in your process. Max control; you own scaling/state.
- Hosted agent (Foundry Agent Service) — Foundry hosts the loop, stores threads, enforces RBAC/content safety, shows the agent in the portal. Less control, far less operational surface.
- Agent workflow — multiple agents/tools composed into a graph with branching, approval nodes, and durable checkpoints.
Lifecycle (the loop that ships an agent)
create → version → evaluate (gate) → deploy hosted → observe online → collect failures → repeat.
Offline evaluation is a gate, not an afterthought — a version does not ship
unless it clears the threshold. Online observability feeds real failures back
into the offline test set.
Scaling and cost levers (in priority order)
- Right-size the model — use the smallest model that passes the evaluation gate.
- Route by complexity — small/fast model for simple requests, large model for real reasoning (DIY classifier or Foundry Model Router).
- Cache — serve near-duplicate requests without a model call.
- Stateless design + bounded concurrency — externalise state; retry with backoff.
Show full SKILL.md (232 more words)Show less
Key patterns to reproduce
Point the learner at these from the notebook
16-python-agent-framework.ipynb:
- Request handler: cache → route by complexity → trace span → run → cache.
- Evaluation gate: score an offline test set; return
pass_rate >= thresholdand only deploy if true. - Human approval:
@tool(approval_mode="always_require")for actions like large refunds. - Tracing: wrap each request in
tracer.start_as_current_span(...)and set attributes likerouted.model,customer.id.
Smoke-testing a deployed agent
After deploy, verify the endpoint actually answers (a green deploy can still be
silent). Use the AI Smoke Test
action via .github/workflows/smoke-test.yml
with the catalog in tests/. The runner POSTs each
prompt to POST {project_endpoint}/agents/{agent_name}/endpoint/protocols/openai/responses
and asserts on the reply text. The identity needs the Azure AI User role at
Foundry project scope; the token audience must be https://ai.azure.com/.
Layer the gates: smoke test (reachable/responding, every deploy) → offline evaluation (good enough to ship, before promotion) → online evaluation (how is it doing in the wild, continuous).
Enterprise controls
- RBAC: give each hosted agent a managed identity with least privilege.
- MCP in production: treat every MCP server as an untrusted boundary — pin the version, scope its identity, validate outputs, rate-limit, never expose secrets.
Guardrails for the assistant
- Prefer the canonical
FoundryChatClient(...)+provider.as_agent(...)pattern used across the course. - Do not promise live-Azure results you have not verified; recommend the smoke-test workflow to confirm a deployment.
- Keep evaluation and cost advice tied together: evaluation sets the quality floor, routing/caching keep cost near that floor.
© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/deploying-scalable-agents of microsoft/ai-agents-for-beginners.
Open the folder on GitHubat commit 25b7985
Compare with similar skills
Deploying Scalable Agents next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Deploying Scalable Agents this skillmicrosoft/ai-agents-for-beginners | 77k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Aspiremicrosoft/aspire.dev | 196 | 4 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Aspire MonitoringCommunityToolkit/Aspire | 629 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Temps Best Practicesgotempsh/temps | 822 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Backdoor Deploymentmicrosoft/Docker-Provider | 173 | — | ~7k | Automated safety check: Pass | Custom licence | |
| Observability Architecturemajiayu000/litellm-rs | 116 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Aspire Monitoring
CommunityToolkit/Aspire
ANALYSIS SKILL - Observe Aspire apps: logs, traces, metrics, resource state, telemetry export, browser telemetry, and the standalone dashboard.
Temps Best Practices
gotempsh/temps
Best-practices reference for preparing and instrumenting applications on Temps.
- Official
Backdoor Deployment
microsoft/Docker-Provider
Validate a container image change via backdoor deployment. An agent skill from microsoft/Docker-Provider.
Observability Architecture
majiayu000/litellm-rs
LiteLLM-RS Observability Architecture. An agent skill from majiayu000/litellm-rs.
- Official
Azure Monitor Opentelemetry Exporter Java
microsoft/skills
Azure Monitor OpenTelemetry Exporter for Java. An agent skill from microsoft/skills.
More from microsoft/ai-agents-for-beginners
All 123 skills in this repo- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
A skill your agent uses when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script…
- Official
Azure Openai To Responses
microsoft/ai-agents-for-beginners
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API.
- Official
Azure Openai To Responses
microsoft/ai-agents-for-beginners
Shift Python apps dem from Azure OpenAI Chat Completions go Responses API.
- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
Kasuta, kui kasutaja palub luua, üles ehitada või redigeerida Jupyteri märkmikke (.ipynb) katsetuste, uurimiste või juhendite jaoks; eelista kaasasolevaid malle ja käivita abiskript newnotebook.py…
- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
Käytetään, kun käyttäjä pyytää luomaan, alustamaan tai muokkaamaan Jupyter-muistikirjoja (.ipynb) kokeita, tutkimuksia tai opetusohjelmia varten; käytä mieluummin mukana olevia mallipohjia ja…
- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
À utiliser lorsque l'utilisateur demande de créer, structurer ou modifier des notebooks Jupyter (.ipynb) pour des expériences, explorations ou tutoriels ; privilégiez les modèles fournis et exécutez…
Related
Works with
Categories
Questions about Deploying Scalable Agents
What does Deploying Scalable Agents do?
Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry. Deploying Scalable Agents is an agent skill from microsoft/ai-agents-for-beginners, published by the product's own GitHub organization. Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry.
When should I use Deploying Scalable Agents?
Deploying Scalable Agents fits situations like: : deploy an agent to production; microsoft Foundry hosted agent; foundry Agent Service; response caching.
How do I install Deploying Scalable Agents in Claude Code?
Run `npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a claude-code`. Or copy the skill folder (.agents/skills/deploying-scalable-agents in microsoft/ai-agents-for-beginners) into .claude/skills/deploying-scalable-agents in your project. Claude Code loads it when a task matches its description.
How do I install Deploying Scalable Agents in Codex?
Run `npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a codex`. Or copy the skill folder (.agents/skills/deploying-scalable-agents in microsoft/ai-agents-for-beginners) into .agents/skills/deploying-scalable-agents in your project. Codex loads it when a task matches its description.
Can I use Deploying Scalable Agents in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/ai-agents-for-beginners --skill deploying-scalable-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deploying-scalable-agents, .gemini/skills/deploying-scalable-agents, .github/skills/deploying-scalable-agents and .opencode/skills/deploying-scalable-agents in your project.
What does Deploying Scalable Agents need to run?
Going by SKILL.md and its folder, Deploying Scalable Agents needs the command-line tools its instructions call (az).
Does Deploying Scalable Agents access the network?
SKILL.md names 2 domains. In commands or code: ai.azure.com; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. This is read from the text; nothing was executed.
Is Deploying Scalable Agents safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Deploying Scalable Agents use?
Deploying Scalable Agents is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Deploying Scalable Agents use?
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Deploying Scalable Agents?
Skills that share tags, products or a category with Deploying Scalable Agents: Aspire (microsoft/aspire.dev, 196 stars), Aspire Monitoring (CommunityToolkit/Aspire, 629 stars), Temps Best Practices (gotempsh/temps, 822 stars) and Backdoor Deployment (microsoft/Docker-Provider, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Deploying Scalable Agents?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/ai-agents-for-beginners, which has 76,567 GitHub stars. The repository holds 123 skills in this directory. The repository was last updated on September 19, 2026.
Source: microsoft/ai-agents-for-beginners on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.