Skip to content

#180 · AI Pentest Reasoning Logs: See Every Step Your AI Pentest Takes

Availability: General Availability

Reasoning Logs give you a live, navigable view of your AI pentest while it runs. You open the agent tree, pick any agent, and read its reasoning, the tools it called, the findings it raised, and how long each step took. Security teams told us they want a full audit trail of what the agent tried, what it skipped, and what it proved. That's what you get now.

image.png

What's new:

  • Live agent tree: the orchestrator and every sub-agent (BOLA, business logic, XSS, SQL injection, and more) appear as a tree you expand and navigate.
  • Full step detail: each agent exposes its reasoning, tool calls, findings count, and run duration, so you follow how one signal escalates into an attack chain.
  • Live during the scan: activity streams in as the pentest runs. You don't wait for the final report to see what's happening.
  • Cleaner and more readable: jump straight to the latest activity, with the noise stripped out so the trace stays easy to follow.

Questions?

Have a question? Reach out on your dedicated support channel, or email us at support@escape.tech.