See everything AI does in your apps

Every tool call is logged with who made it, which AI client and app were involved, and what your policies decided. See it in the dashboard, or ask about it in plain English.

Free Trial

What you can see in Dtwo

Dtwo Hub dashboard: allow, deny and redact totals, top users, AI clients, MCP servers and tools, recent events with the policy reason

What was allowed, blocked and redacted

See this month's totals at a glance. A jump in blocked calls can mean a policy is too strict, or that someone is trying something they shouldn't.

Allowed 49,090
Blocked 1,290
Redacted 1,980

Who's using AI, and with what

See which people, MCP servers and tools are behind the activity. Find out which apps your team actually relies on, and who's getting the most out of AI.

Users

  1. j.chen
  2. a.patel
  3. m.ortiz

MCP servers

  1. Salesforce
  2. Microsoft 365
  3. GitHub

Tools

  1. soql_query
  2. send_mail
  3. create_pr

Every event, with the reason

Each call shows who made it, which AI client and app were involved, and the policy that decided the outcome. No guessing why something was blocked.

  • a.patel Claude m365.send_mail Blocked No email outside acme.com
  • m.ortiz Cursor zendesk.get_ticket Redacted Mask payment data
  • j.chen Codex github.create_pr Allowed

Investigate in plain English

With the Dtwo plugin in your AI client, you can ask questions about your logs instead of digging through them. Find out who did what, spot patterns, and get a summary ready for your next audit.

Dtwo plugin

43 attempts were blocked by "No email outside acme.com":

  • a.patel Claude 18 attempts Tuesday
  • m.ortiz Cursor 12 attempts Wednesday
  • r.kim Cursor 9 attempts Thursday
  • j.chen Codex 4 attempts Friday

Dtwo plugin

4 policies blocked the most calls:

  • No email outside acme.com Microsoft 365 412 calls
  • No deleting CRM records Salesforce 287 calls
  • No pushing to main GitHub 164 calls
  • No posting to #general Slack 96 calls

FAQs

What gets logged?

For every tool call: who made it, which AI client, app and tool were involved, when it happened, and what your policies decided. The data sent to the tool is never stored.

Do we need to install anything on laptops?

No. Every connection between your AI clients and your apps goes through Dtwo, so that's where activity is logged.

How is each call tied to a person?

People sign in to Dtwo with your identity provider, like Microsoft Entra or Okta. Every call they make is recorded under their name.

How do I ask questions about my logs with AI?

Install the Dtwo plugin in your AI client. Then ask things like "who was blocked from sending email this week?" and get an answer from your logs.

Does Dtwo only watch, or can it stop things too?

Both. The same policies that show up in your logs block risky actions, narrow requests and redact sensitive data before AI sees it.

The threat isn't AI. It's AI you can't see.

See every action, every decision and every policy that made it.

Free Trial
Get in touch

Tell us what you need to govern.

A few lines is plenty — what you're deploying, and what you need control over. We read every one.