Build Hour: Workspace Agents in ChatGPT

Why It Matters

Workspace Agents enable businesses to automate complex, cross‑platform tasks without code, boosting productivity and ensuring policy compliance across teams.

Key Takeaways

• Workspace agents automate multi‑system tasks for whole teams
• Agents use natural‑language prompts to configure calendar, email, and drive integrations
• Memory and skill libraries let agents improve and follow company policies
• No‑code build process lets subject‑matter experts create agents quickly
• Enterprise admin controls provide granular permission and audit capabilities

Summary

The Build Hour session introduced OpenAI’s Workspace Agents, a new no‑code solution that lets teams create AI‑driven assistants capable of handling long‑running, cross‑system workflows. Hosted by product marketing and engineering staff, the demo showed how agents are built directly from natural‑language prompts, automatically wiring up tools such as Google Calendar, Drive, and Gmail, and generating a structured playbook that runs in the background. Key insights highlighted the agents’ ability to maintain memory, execute skills from existing tools, and operate under strict permission settings. The meeting‑prep agent demonstrated automated calendar scanning, external research, and formatted brief generation, while the software‑review agent illustrated policy‑driven ticket handling in Slack. Both examples emphasized rapid iteration through preview runs and the capacity for teams to share and remix agents without developer involvement. Notable quotes included Christina’s description of agents as “code‑ex powered” assistants that “gather the right context, keep going in the background, and be shared either in ChatGPT or Slack.” Hojun emphasized that the workflow requires no IT support, allowing subject‑matter experts to own the automation. The session also covered enterprise admin features such as granular tool access controls and audit logs. The implications are clear: organizations can accelerate routine knowledge‑work, reduce manual preparation time, and enforce consistent policies across departments. By democratizing AI‑agent creation, OpenAI aims to embed intelligent automation into everyday collaboration tools, potentially reshaping how enterprises manage meetings, compliance, and internal support.

Original Description

Build workspace agents in ChatGPT that can do work across your tools and help teams move faster. In this Build Hour, you’ll learn how to turn your team’s best practices into shared agents from start to finish.

Christina Huang (Engineering), Ho Joon Cha (Solutions Engineering), and Victoria Chernova (Product Marketing) cover: 

• How to build agents for common workflows that require multiple steps, tools, and sources of context 

• Using agent builder chat, choosing tools and connectors, and adding guardrails

• Testing, iterating, and sharing agents powered by Codex in the cloud

• Best practices and live Q&A 

👉 Workspace agents in ChatGPT: https://chatgpt.com/agents

👉 Workspace agents blog: https://openai.com/index/introducing-workspace-agents-in-chatgpt/

👉 How to guide: https://developers.openai.com/cookbook/articles/chatgpt-agents-sales-meeting-prep

👉 Sign up for upcoming live Build Hours: https://webinar.openai.com/buildhours

00:00 Introduction

01:22 Intro to Workspace agents

03:24 Demo: Meeting Prep agent

18:02 Demo: Software Review agent

27:34 Getting Started

29:53 Q&A