🚀 OpenAI Introduces AgentKit for AI Agent Development! 🛠️

OpenAI CEO Sam Altman on Monday announced the launch of AgentKit, a toolkit for building and deploying AI agents, at the firm’s Dev Day event.  

“AgentKit is a complete set of building blocks available in the open AI platform designed to help you take agents from prototype to production. It is everything you need to build, deploy, and optimize agent workflows with way less friction,” Altman said.  

The launch highlights OpenAI’s push to increase developer adoption by making agent building faster and easier. It also signals a competitive move against other AI platforms racing to offer integrated tools for building autonomous agents for enterprises that can perform complex tasks, not just respond to prompts.

AgentKit was one of several announcements at OpenAI’s Dev Day, including the launch of the ability to build apps directly inside ChatGPT, which has hit 800 million weekly active users.  

AgentKit includes a few core capabilities. The first is Agent Builder, which Altman described as like Canva for building agents.  

“It’s a fast, visual way to design the logic, steps, ideas,” Altman said. “It’s built on top of the responses API that hundreds of thousands of developers already use.” 

The second capability of AgentKit is ChatKit, which provides a simple embeddable chat interface that developers can use to bring chat experiences into their own apps.  

“You can bring your own brand, your own workflows, whatever makes your own product unique,” Altman said. 

Evals for Agents introduces tools to measure AI agent performance, including step-by-step trace grading, datasets for assessing individual agent components, automated prompt optimization, and the ability to run evaluations on external models directly from the OpenAI platform. 

Finally, AgentKit includes access to OpenAI’s connector registry, so developers can securely connect agents to internal tools and third-party systems through an “admin control panel” while maintaining security and control. 

To prove how easy it is to use AgentKit, Christina Huang, an OpenAI engineer, built an entire AI workflow and two AI agents live onstage in under eight minutes.  

“This is all the stuff that we wished we had when we were trying to build our first agents,” Altman said, noting that OpenAI has already signed on several launch partners that have already scaled agents using AgentKit.