OpenAI Launches Workspace Agents in ChatGPT: Codex-Powered Agents for Teams

OpenAI has released workspace agents in ChatGPT, allowing teams to build Codex-powered shared agents that handle complex, multi-step workflows across tools like Slack and CRMs-all within organizational permissions and controls.

openai Apr 22, 2026

OpenAI has introduced workspace agents in ChatGPT. Teams can now create shared agents capable of handling complex tasks and long-running workflows, all while operating within the permissions and controls established by their organization.

Workspace agents represent an evolution of GPTs. Powered by Codex, they can take on many of the tasks people already perform at work-from preparing reports, to writing code, to responding to messages. They run in the cloud, so they can continue working even when the user is not present. They are also designed to be shared within an organization, allowing teams to build an agent once, use it collaboratively in ChatGPT or Slack, and improve it over time.

AI has already helped individuals work faster on their own, but many of the most important workflows inside an organization depend on shared context, handoffs, and decisions across teams. Workspace agents are built for that kind of work: they can gather context from the right systems, follow team processes, ask for approval when needed, and keep work moving across tools. For example, OpenAI's sales team uses an agent to pull together details from call notes and account research, qualify new leads, and draft follow-up emails right in a rep's inbox. It helps account teams spend less time stitching together details and more time with customers.

Workspace agents are available in research preview in ChatGPT Business, Enterprise, Edu, and Teachers plans. To get started, users describe a workflow their team does often, and ChatGPT will help turn it into an agent from start to finish.

Note: GPTs will remain available while teams test workspace agents with their workflows. OpenAI plans to make it easy to convert GPTs into workspace agents soon.

Building a Powerful Workspace Agent in Minutes

Users describe the job they want done or drop in a file. ChatGPT then helps turn it into an agent: defining the steps, connecting the right tools, adding skills, and testing it until it works as expected.

Here are a few agents teams at OpenAI have built-and that other teams can build too:

  • Software Reviewer: Reviews employee software requests, checks them against approved tools and policies, recommends next steps, and files IT tickets when needed.
  • Product Feedback Router: Monitors Slack, support channels, and public forums, then turns feedback into prioritized tickets and weekly product summaries.
  • Weekly Metrics Reporter: Pulls data every Friday, creates charts, writes the summary, and shares a report with the team.
  • Lead Outreach Agent: Researches inbound leads, scores them against a qualification rubric, drafts personalized follow-up emails, and updates the CRM.
  • Third-Party Risk Manager: Researches vendors, assesses signals like sanctions exposure, financial health, and reputational risk, and produces a structured report.

Templates are also available for finance, sales, marketing, and more. Each comes with built-in skills and suggested tools, enabling quick setup and customization.

Putting Agents to Work Across Tools and Teams

Agents are powered by Codex in the cloud, giving them access to a workspace for files, code, tools, and memory. They go beyond answering a prompt: they can write or run code, use connected apps, remember what they have learned, and continue work across multiple steps.

Workspace agents can keep working even when the user is away. They can be set to run on a schedule or deployed in Slack so they pick up requests as they come in. For example, OpenAI's product team built an agent that proactively answers employee questions in Slack channels. The agent responds with a clear answer, links relevant documentation, and can file a ticket when it finds a new issue. This helps teams get unblocked faster while ensuring important follow-ups don't slip through the cracks.

Currently, teams can interact with agents in ChatGPT and Slack, with more surfaces coming soon. Agents can join the conversations and workflows where work already happens, helping teams move work forward with less coordination.

Turning Best Practices into Shared Agents

Knowledge is often scattered across people and systems. Workspace agents give teams a way to turn that knowledge into a reusable workflow: one that follows the right process, uses the right tools, and can be shared across the organization.

For example, OpenAI's accounting team built an agent that prepares key parts of month-end close, from journal entries to balance sheet reconciliations to variance analysis. It completes the work in minutes, generates workpapers with the underlying inputs and control totals needed for review, and follows internal policies. The agent is available in ChatGPT for anyone on the team to use, or can be added to Slack channels so the team can ask it questions and collaborate around its outputs.

Because agents have memory and can be guided and corrected in conversation, they improve as teams use them. Over time, agents become a practical way to keep team knowledge current: build once, improve through use, then share or duplicate for new workflows.

Staying in Control with the Right Safeguards

When delegating work to an agent, users remain in control. They decide what tools and data it can use, what actions it can take, and when it needs approval. For sensitive steps-like editing a spreadsheet, sending an email, or adding a calendar event-agents can be required to ask for permission before proceeding.

After sharing an agent, analytics help users see how it is being used, including how many runs it has completed and how many people are using it.

Enterprise Governance and Visibility

Workspace agents come with enterprise-grade monitoring and controls, so admins can protect sensitive data while giving teams a safe way to move faster with AI. ChatGPT Enterprise and Edu admins can control which connected tools and actions user groups can access. Admins can also manage who has access to use, build, and share agents. Built-in safeguards help agents stay aligned with instructions when they encounter misleading external content, including prompt injection attacks.

The Compliance API gives admins visibility into every agent's configuration, updates, and runs, so they can monitor and control how agents are being built and used. Admins can also suspend agents if needed.

Soon, admins will also be able to view every agent built across their organization in the admin console, including usage patterns and connected data sources.

Early Feedback from Customers

Early testers of workspace agents are already seeing more consistent results and time freed up for higher-value work.

"The hard part of building an agent is not the model. It's the integrations, memory, the user experience. Workspace agents collapsed that work, so one of our Sales Consultants built, evaluated, and iterated a Sales Opportunity agent end to end without an engineering team. It researches accounts, summarizes Gong calls, and posts deal briefs directly into the team's Slack room. What used to take reps 5-6 hours a week now runs automatically in the background on every deal."

  • Ankur Bhatt, AI Engineering, Rippling

Availability and Pricing

Workspace agents are available in research preview for ChatGPT Business, Enterprise, Edu, and Teachers plans. For Enterprise and Edu plans, admins can enable agents using role-based controls.

Workspace agents will be free until May 6, 2026, with credit-based pricing starting on that date.

What Comes Next

OpenAI plans to keep adding capabilities in the weeks ahead to help teams get more work done with less manual effort. This includes new triggers that can start work automatically, better dashboards to understand and improve performance, more ways for agents to take action across business tools, and support for workspace agents in the Codex app.

Teams do their best work when knowledge is easier to find, processes are easier to follow, and people can get help in the flow of work. Workspace agents are an early step toward that future: AI that works alongside people in the tools and conversations where work already happens, helping teams spend less time coordinating work and more time creating, building, and making decisions that move the business forward.