Security and data

Security and data handling.

AutoStack environments run on synthetic data. We never need your production data, we only test an agent when its owner has asked us to in writing, and your agent's traces are deleted when the engagement ends.

Data

No real data inside the environments

No. Every policy, claim and person in our environments is synthetic. There is no personal information inside them.

Inputs

What do you need from us?

Your agent's tool interface (schemas and descriptions) and your workflow rules. Never production data.

Permission

Do you test agents without asking?

No. We test an agent only after its owner has asked us to, in writing, with the scope agreed.

Traces

What happens to your agent's traces

They're used only for your evaluation and deleted when the engagement ends.

Ownership

Who owns the results?

You own the deliverables you pay for; we keep our underlying tooling.

Processing

Where is data processed?

We use service providers for scheduling, email, our CRM and analytics. Some of them store data in the United States. See the privacy policy.

Questions from your security team.

Email us

Request an evaluation

Tell us about the agent you want evaluated.

What do you need?
How does it take actions?