It’s a whole new era of working with AI. This year, we introduced new models, tools, and agents to help you build faster, take on more ambitious projects, and bring your products to more people.
Opening Keynote
Be there as OpenAI unveils what’s next. DevDay opens with a keynote packed with announcements—and new possibilities for what you can build with AI.
ClawLabs: Building Open Source Together
See how agents help small open-source teams build together. Explore workflows for sharing context across projects and working with contributors, with live demos of cloud sessions and computer use.
Codex Has Left The Laptop
Explore what’s new in Codex across the CLI, app, and web. Through live demos, see how to move from delegating individual tasks to letting Codex tackle entire problems and goals.
From Single Player to Multiplayer with Codex
Follow a 2am outage from the first Slack message to a reviewed fix. See how voice, Appshots, plugins, and meeting notes help a persistent personal agent investigate and keep the team informed.
How OpenAI Puts ChatGPT to Work
See how OpenAI’s teams use ChatGPT to manage launches, research competitors, and turn expertise into tools. Take practical ideas back to your own work.
Stack Overflow - From Idea to Product
See how small teams at Stack Overflow used Codex to build Stack Overflow for Agents and reimagine Stack Internal. Take away lessons for accelerating R&D and bringing new products to market.
Higgsfield - Building Agents That Provision Their Own Compute
Explore how Higgsfield agents choose models and provision their own compute. Learn when to use dedicated GPUs or hosted models, how to deliver predictable throughput, and where the approach can fail.
Stop Overpaying for Intelligence
Cut AI costs while preserving quality. Learn to measure cost per completed task, choose models and reasoning effort, and use prompt caching, Programmatic Tool Calling, and the Batch API.
Qodo - The Last Human Code Review
See how Qodo uses OpenAI to review AI-generated code. Explore an adversarial reviewer that challenges coding agents’ assumptions and output, and learn when model confidence still needs human judgment.