Agent Journey Lab

Start a $199 pilot

Research

Our research boundary

We study whether AI agents can finish public customer journeys. This page states where a public run stops, how an authorized test is different, and how a site owner can stop us.

For public research, we stop before we enter data in a form. Authorized tests use the written scope that you approve.

Read the pilot scope

Our test sessions declare AgentJourneyLab/0.1. Site owners can stop a public test: read the research boundary or write to research@agentjourneylab.com.

Commitments

Our commitments

  • Identity

    Identity

    Our public sessions declare AgentJourneyLab/0.1 in the user agent string.

  • Scope

    Scope

    Public research reads public pages only. We take no consequential action.

  • Form boundary

    Form boundary

    The run stops before form entry, account use, submission, payment, booking, or a claim.

  • Robots and rate

    Robots and rate

    We use a low request rate. We respect robots.txt.

  • Challenges

    Challenges

    We stop at a challenge or a bot block. A block is an observed policy state. We do not try to pass it.

  • Results

    Results

    We keep results private. We do not publish a result about a named site without written permission.

  • Opt-out

    Opt-out

    To exclude your domain from public research, email the domain to us. We confirm in writing.

Public and authorized

Public research and an authorized test

Public research

  • Public pages only.
  • Stops before the first form field.
  • Low request rate.
  • No account and no payment.

Authorized test

  • A written scope that you approve.
  • Limits that you state.
  • Synthetic data only.
  • Results private to you.

Contact

Contact

Write to research@agentjourneylab.com. Site owners can ask us to stop a public test at the same address.