Skip to main content

Connect Drata to ChatGPT

Give ChatGPT governed access to Drata’s 38 tools through Runlayer, with identity, policy, scanning, and audit on every call.

Set up

Add Drata to ChatGPT in four steps

Admins approve the server once. Everyone in ChatGPT then gets it through the same governed connection.

  1. 1

    Approve Drata in Runlayer

    Add Drata from the catalog and choose who can use it and which of its tools are allowed.

  2. 2

    Connect ChatGPT to Runlayer

    Admins publish the Runlayer Plugin and its skill to the whole ChatGPT organization. With direct tool listing turned on for your deployment, Drata’s 38 tools show up in ChatGPT’s own tool list.

    ChatGPT setup guide
  3. 3

    Sign in to Drata

    Sign in the way Drata requires. Runlayer holds the credentials so they stay out of the client’s configuration.

  4. 4

    Use Drata from ChatGPT

    Drata’s approved tools appear in ChatGPT. Every call is checked against policy and recorded.

Tools

38 Drata tools in ChatGPT

Runlayer policy decides which of these ChatGPT users can call.

  • Create background check

    File a Background Check for a personnel record, evidenced by a URL.

  • Create control

    Create a new compliance control in a workspace.

  • Create evidence

    Register a new evidence bucket in Drata's reusable Evidence Library.

  • Create risk

    Create a new custom risk in a risk register.

  • Create vendor

    Create a new third-party vendor for the account (TPRM).

  • Delete evidence

    Permanently delete an ENTIRE evidence bucket -- the folder AND every file in it, plus all version history and control linkages.

  • Delete evidence artifact

    Permanently delete ONE file from an evidence bucket, including that file's entire version history.

  • Delete risk

    Permanently delete a single risk from a risk register.

See all 38 Drata tools

Control

What Runlayer can see and stop in ChatGPT

Some controls apply to every client at the gateway. Others depend on what ChatGPT exposes to Runlayer.

  • Gateway policy (available)

    Every Drata call from ChatGPT passes through Runlayer, where your policies can allow, alert, mask, or block it.

  • Audit trail (available)

    Each call is recorded with the user, ChatGPT as the client, the tool, and the policy and scanner decisions.

  • Compliance API import (available)

    OpenAI Compliance Logs Platform imports ChatGPT web chats for review.

  • Managed browser extension (available)

    Managed Chrome, Edge, and Firefox deployments can monitor supported web-chat activity and apply prompt-time controls where the surface permits it.

  • Native enforcement adapter (not available)

    Runlayer has no device-side adapter for ChatGPT yet, so control happens at the gateway.

Frequently asked questions

Connect more

Find another combination