Quickstart
Build, deploy, and run your first AI agent in about ten minutes.
This walkthrough takes you end to end: connect a model, build an agent, test it, deploy it, run it, and review the run. We build an agent here because it's the quickest path to a working result — but workflows are an equal way to build and share the exact same test, deploy, and run steps.
Before you start
You'll need to be signed in to Compass with access to an organization and a project. If this is your first time, see the interface tour to get oriented, then come back.
1. Pick your workspace
At the top of the app, use the workspace switcher to choose the organization and project you want to work in. Everything you create in this quickstart will live in that project. If you're not sure, the Default project is a fine place to start.
2. Connect a model provider
An agent needs a model to think with, so first add a provider connection.
Open Connections
In the left navigation, under Forge, click Connections.
Add a provider
Choose a provider — for example Anthropic — and click New connection.
Enter your credentials
Give the connection a name (e.g. "Anthropic — Quickstart"), paste your API key, and select a default model. Save the connection.
The connection shows a status indicator once Compass confirms the credentials work. See Providers for the full list and options.
3. Build the agent
Create a new agent
Under Forge, click Agents, then New Agent. This opens the agent builder. Your work auto-saves as a draft as you go.
Name and describe it
Give it a clear name, like "Release Notes Writer", and a short description.
Write its instructions
In Instructions, tell the agent what it does and how to behave — this is its system prompt. For example:
You are a concise technical writer. Given a list of merged changes, write friendly release notes grouped into Features, Fixes, and Improvements.
Choose its model
Under Model, select the provider connection you created in step 2.
That's a complete agent. (Optionally, open the Tools panel to let it call an integration, a workflow, or another agent — see Giving agents tools.)
4. Test it
Click Test to open the test panel. Type a message — for example, paste a few bullet points of changes — and send it. The response streams back live, and a collapsible trace shows any tool calls and the token count.
Test conversations are throwaway, so experiment freely. Tweak the instructions and test again until you're happy.
5. Deploy it
When it's ready, click Deploy. A dialog confirms the details and runs a quick validation:
- Fix any errors it flags (for example, a missing model). Warnings won't block you.
- The dialog shows the version you're about to publish (your first deploy is v1).
Confirm to freeze this draft into version v1 and publish it as live. Your agent can now be run by your team and other agents.
6. Run it
The quickest way to run a deployed agent is Compass Chat:
Open Compass Chat
Open the chat panel and start a new chat.
Enable your agent
Open the tools picker and turn on the agent you just deployed.
Ask it to work
Send a message asking it to do its job. It runs and streams the result back, just like in testing — but this is your live, deployed version.
Other ways to run
You can also run on a schedule (see Triggers & schedules) or from your own code through the API (see Running via API). A one-off "Run now" button in the UI is on the way.
7. See what happened
Under Console, open Observability. You'll find your run in the list, with its status, duration, and token usage. Click it to open the trace — the step-by-step record of everything the agent did, including each tool call with its inputs and outputs.