Build, Deploy & Monitor AI Agents with Astropods

AI agents are moving beyond experiments. They answer questions, run workflows, call tools, and collaborate across real teams. Building agent logic is only the beginning. You also need a repeatable way to configure, test, deploy, and observe agents in production.

Astropods in the Postman AI stack

Astropods is a product in the Postman AI stack. Postman is building the infrastructure for agents and APIs, with each product covering a specific layer that helps customers achieve AI sovereignty. Astropods is the agent operating system layer: it runs and controls AI agents in production with runtime, observability, and guardrails at scale.

Astropods gives you that lifecycle in one platform. This guide takes you from a local project to a deployed, monitored agent.

What you will do: create an agent, run it locally, publish a blueprint, deploy it, connect Slack, and inspect production behavior.

Understand the Astropods lifecycle

Astropods organizes an agent into four stages:

Stage	What it represents
Project	Your local codebase and astropods.yml specification.
Blueprint	A versioned, deployable snapshot in the registry.
Agent	A running instance of a blueprint.
Observability	Usage, cost, network, runtime, and trace data from the deployed agent.

The declarative astropods.yml file describes the agent’s models, interfaces, integrations, knowledge stores, and runtime requirements.

Start with the Astropods documentation or review the complete agent lifecycle.

1. Build and run an agent locally

Install the ast CLI, start Docker, and create a project.

ast project create <name> --model gateway --template mastra
cd <name>
ast login

The --model gateway option connects the project to the AI Gateway, so the agent can use managed models without a separate provider API key.

The generated project includes:

• astropods.yml, the agent specification.
• AGENT.md, project guidance for coding agents such as Codex, Claude Code, Copilot, or Cursor.
• CLAUDE.md, additional instructions for Claude Code.

Implement the agent manually or ask a coding agent to build the required logic. If the agent needs external credentials, configure them locally.

ast project configure
ast project start

Astropods starts the agent and its sidecars in containers. Messaging agents can use the local chat interface at http://localhost:3100.

Follow Your first project for the current quickstart.

2. Publish and deploy a blueprint

A blueprint packages the agent’s container image and registered specification into a versioned artifact.

Validate the specification, then publish a private or a public blueprint.

ast spec validate
ast blueprint push <name> 

Blueprints are private by default. Use  — visibility public only when you intend to publish to the public catalog.

Keep AGENT.md current. It becomes the Agent Card shown on the blueprint page and should explain what the agent does, which integrations it needs, and how to use it.

Deploy the blueprint with an authenticated web interface:

ast blueprint deploy <name>

Verify the result with ast agent list then open the launch URL and run a representative request.

See Your first blueprint and Deploy your first agent for the full workflow.

3. Connect the agent to Slack

Slack puts the agent where your team already works. In the Slack API dashboard:

1. Create an app for the target workspace.
2. Generate an app-level token with connections:write.
3. Enable Socket Mode and Event Subscriptions.
4. Add the required bot scopes. A common starting point is chat:write and app_mentions:read.
5. Install the app and copy the bot token.

Select the Slack adapter in the deployment form and provide the app and bot tokens. You can also deploy through the CLI.

ast blueprint deploy <name> --adapter slack

Your organization may require administrator approval before you can install the Slack app. Configure access separately for the web and Slack interfaces.

4.  Operate and monitor and improve the agent

Deployment starts the operational lifecycle. Astropods gives your team one place to govern agents, run them across environments, and measure how well they perform your team’s work. Once your agent is running, use traces, evals, and monitoring to understand its behavior and guide improvements:

• Traces: understand what happened. Review an interaction’s input, output, model calls, tool calls, timing, and cost. Follow each step to pinpoint failed tool calls, unexpected responses, or slow operations.
• Evals: identify what needs improvement. Run automated checks against production traces to flag unnecessary tool calls, exposed personal data, or negative user sentiment. Use default evaluators or define custom checks to identify problems and regressions as you iterate. Learn more about evals.
• Monitor: track performance and adoption. Inspect token usage, spend, active users, request volume, latency, and network activity to see how usage and performance change over time.

Learn more in Managing your agents and Monitor your agents.

Bring an existing agent to Astropods

Already have an agent? Use the Astropods Claude Code plugin to help migrate it to run on Astropods. The plugin also includes skills for creating a new project from scratch.

Run these commands in Claude Code:

/plugin marketplace add astropods/agents
/plugin install astropods@astroai

Then ask Claude Code to migrate your agent to Astropods. See the plugin README for the included skills.

Production readiness checklist

1. ast spec validate succeeds.
2. The main workflow works locally and after deployment.
3. Required variables are documented and no credentials are committed.
4. The Agent Card explains the blueprint and its integrations.
5. Web and Slack access policies match the intended audience.
6. A production request produces a complete trace.
7. Token usage, latency, network activity, and logs look healthy.

Start building

Astropods gives you one workflow to define an agent, test it locally, publish a versioned blueprint, deploy it securely, and understand its behavior in production.

Ready to deploy your first agent? Follow the hands-on Postman Learning Path:

Building with Agents learning path

You can also start with Your first project or explore the Astropods documentation.

Resources

• Postman AI stack
• Astropods documentation
• Complete agent lifecycle
• Deploy your first agent
• Monitor your agents
• Building with Agents learning path