Workspace Agents in ChatGPT: Admin and Builder Controls

Why It Matters

The controls balance automation speed with security and compliance, enabling organizations to scale autonomous workflows without ceding governance; this reduces manual work and risk for product and IT teams.

Summary

OpenAI demonstrated Workspace agents for ChatGPT Enterprise that automate team workflows—like a product feedback agent that extracts CRM contacts, generates PRDs and slides, files tickets, and posts weekly updates to Slack. Agent builders control what apps and actions an agent can access, using toggles and natural-language constraints (for example, limiting outbound emails to specific domains). Enterprise admins add a governance layer with role-based access controls, app-level restrictions, parameter constraints, and optional human-in-the-loop confirmations for consequential actions. Together these features let teams delegate routine tasks while preserving IT oversight and data protection.

Original Description

Workspace agents in ChatGPT help teams turn repeatable workflows into shared agents that can pull in context, use tools, and move work forward on their own.

In this demo, you’ll see how admins and builders can set safeguards for workspace agents. Enterprise admins can centrally manage who can use, build, and publish agents, and define what agents are allowed to do. Builders can also configure when agents should ask for approval before taking specific actions, so agents work the way teams need them to across users and workflows.

Workspace agents are generally available to ChatGPT Business, Enterprise, and Edu.