Basic Usage

Agents

Agents allow you to build the backend of your generative AI application. You can import an agent template or create your own with your own models and data sets. The Playground allows you to test the output of your agent against different prompts.

Before creating an agent, make sure your project has at least one model available, either added to the project or shared with every project. A data source is optional; add one when you want the agent to answer from your own content. For more information, visit Model Lifecycle Management.

Creating a New Agent

To create a new Agent:

1. Select the Project you want to create your Agent in.
2. Select the Agents tab.
3. Check the Models tab to confirm the project has at least one model.
4. Click Add a New Agent. The agent opens in the builder with Input, a model step, and Output already connected.
5. Click the agent name in the top left to rename it.
6. Select the model step to choose the model and prompt you would like to use.
7. Drag any other steps you need onto the canvas: data sources, Memory, Python Code, or other agents.
8. Use the line drawer to connect the steps together.
9. Your changes save automatically to your draft (the top bar shows Saving... and then Saved). When you are ready for users to run this version, click Publish.

Test an Agent

To test your agent:

1. Open an Agent.
2. Select “Playground”.
3. Insert the prompt in the text box at the bottom.
4. Attach any files or images if needed.
5. Submit the prompt.
6. View the output in the output box.

The Playground runs your current draft, so every change is testable immediately.

Compare Agents

To compare responses side by side:

1. Open an Agent.
2. Click the Open Compare Playground icon, just below the Open Playground icon on the canvas. The Test page opens with two panes: your current draft and the agent's published version.
3. Use + and - next to Agents at the bottom to add or remove panes (up to five). You can change the agent and version in each pane.
4. Type one prompt in the text box at the bottom and submit it. Every pane runs the same input.
5. Click Exit to return to the builder.

Editing an Agent

To edit an Agent:

1. Open the agent.
2. Make changes on the canvas. They save automatically to your draft.
3. Click Publish when you want the changes to go live for every interface. Until then, users keep running the published version.

For drafts, published versions, and restoring an earlier version, see Manage Agent Versions.

Debugging an Agent

To debug an Agent:

1. Test the Agent in the Playground.
2. In the left menu, go to Audit → Activity → Agent Executions and select the execution you are debugging.
3. Review the logs for errors.

Using Your Agent

Published agents are used through interfaces. Open the ⋯ menu next to the agent in the Agents list and select Interfaces to add one:

• Airia Catalog lets people in your organization chat with the agent after they sign in to Airia. Under Permissions, choose Public or Private with selected users and groups. See Airia Catalog Interface.
• API is available for every agent, for calling the agent from your own application. See API Interface.

For every interface type, see Managing Agent Interfaces.

To Generate Your API Key

API keys are created under Settings → Developer → API Keys. Name the key, set its scope, and copy the value before you leave the page (the full key is only shown once). See API Keys for the full flow.