Skip to main content
An agent is the stable identity your application calls. An agent version is the immutable configuration AIR executes: prompt, model, tools, fallbacks, output contract, and limits.

​
Build the first version

1

Create or choose a prompt version

Save reusable instructions under Prompts, or write new instructions directly in the agent composer.
2

Choose model access

Use a Papermap-managed model when available, connect an OpenAI or Anthropic provider key, or use Testing → fake-echo for a zero-credential staging smoke test.
3

Allow only required tools

Open Advanced — fallback models, tools, output, and limits and add only tools this version should call. Project-level enablement does not grant an agent access automatically.
4

Choose the output contract

Leave Output schema blank for free-form text, or provide an object-rooted JSON Schema when your application needs predictable fields.
5

Activate deliberately

Select Activate immediately for a new agent, or create an inactive version when you want to test before moving serving traffic.
AIR agent composer showing the selected prompt and testing model

The composer makes the prompt, model, and tool boundary visible before activation.

​
Return structured output

Add a JSON Schema under Advanced → Output schema when downstream code needs a stable response contract. The schema must declare an object at the root.
AIR sends the schema to supported model providers and validates the final model response again before completing the run. A successful run stores the parsed object directly:
If the final response is not valid JSON or does not match the schema, AIR marks the run as failed and does not publish a successful final output. The raw model response remains available in the run trace for debugging.
Without an output schema, AIR preserves the existing free-form response shape with the model response under the text field.

​
Test before integrating

The Try it panel creates a real run using the selected agent version. Open the resulting trace to verify the exact configuration and model behavior.
AIR agent page showing an active version and successful test transcript

An active version and its successful test transcript.

​
Change an agent safely

Create a new version whenever you change instructions, model, allowed tools, output schema, or limits. Test it, then activate it. Existing runs remain tied to the version with which they started; new runs use the active version.
Do not edit production behavior in place. Version first, test the version, and then move serving traffic.