Skip to content
Aandeg

AI agent research lab

How AI agents behave on the systems they touch

Aandeg studies what happens when AI agents meet real websites, APIs, and tools, and publishes what we find.

Get notifiedRead the research

Agents are becoming a new kind of user

AI agents now browse websites, call APIs, and operate tools on people's behalf. The systems they use were built for human visitors or for predictable, hand-written clients. None of them were designed around a model deciding what to do next.

How agents behave in those systems, where they succeed, where they fail, and what they change, is not yet well understood. Aandeg exists to study it carefully and in the open.

Coming soon

Agent Assay

Agent Assay is Aandeg's first product, growing out of our research. We'll share what it does, and open the waitlist, closer to launch.

Get notified

How we work

  1. Observe

    We watch what agents do when they meet real websites, APIs, and tools, including where they get stuck or behave in ways nobody expected.

  2. Measure

    We turn those observations into repeatable measurements, so results can be compared across agents and over time.

  3. Share

    We write up what we find with enough detail for others to check our work.

From the research

The first posts are on the way.

Get notified when Agent Assay opens

Leave your email and we'll let you know when it's ready.

The waitlist isn't open yet, and we aren't collecting email addresses.