Skip to content

Research from the Etheon Lab

Research is how we get better at building AI software. Our Lab publishes it so you can check it: publications, milestones, conclusions and releases.

Research is how we get better at building AI software. Our Lab publishes it so you can check it: publications, milestones, conclusions and releases.

Publication ·

How we build an AI agent, in five steps

An agent is software that takes actions in your systems. We build it in five steps, inside limits held outside the model, with a person where it matters.

By kind. Everything our Lab publishes, grouped by what it is.

  • How we build an AI agent, in five steps

    An agent is software that takes actions in your systems. We build it in five steps, inside limits held outside the model, with a person where it matters.

  • Which AI model should we use?

    The one that does your task best at a cost you can carry. We score candidate models on your evaluation set and choose by quality, cost and response time.

  • What the Etheon Lab works on

    The Etheon Lab studies what makes AI software safe to ship: evaluation, guardrails, observability, safe releases and governance.

The Lab's product and open source. What our Lab ships, and the code we publish.

Product

  • Etheon Delta A product of the Etheon Lab.

Get started with Etheon

Tell us your use case and timeline. We reply within one business day.

Careers

Open roles and how we hire

View open roles

Open source

The code we publish.

GitHub (opens in a new tab)