Skip to main content
Platform covers the work you do with Agent Registry itself, in the order teams usually do it: build an agent and the context it uses, share the skills it relies on, track what it does, and measure how well it does it.

Build context

Register agents, equip them with governed skills and tools, and connect the clients and frameworks they run in.

Find & share

Find, assess, publish, release, and improve reusable skills.

Track usage

Send traces from your agents and coding sessions, attribute them to the right agent, and compare usage, cost, and errors.

Measure quality

Test an agent against fixed cases before release, gate pull requests on the scores, and judge the sessions it produces in use.

​
Common first tasks

Bring agent into Atlan

Register an agent from its repository with Atlan Desktop, add its skills and context, and send its first trace.

Choose skill publishing method

Compare the ways to publish skills to a workspace, prepare the package, and verify the version in Atlan.

Send and verify traces

Choose how to send traces, send them as the right identity, and confirm they reached the intended workspace and agent.

Run your first eval

Run a two-case eval from Python or TypeScript and confirm the experiment and its traces are stored in your workspace.
To find a specific page, use Search the docs at the top of any page.