New Delhi: At the firm’s DevDay event, OpenAI have introduced two new tools, Codex Alpha for developers and AgentKit, a toolkit for building and deploying AI agents. AgentKit is a complete set of building blocks available in the open AI platform designed to help users take agents from prototype to production. It is everything users need to build, deploy, and optimise agent workflows with much less friction.
This 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 DevDay, including the launch of the ability to build an application directly inside ChatGPT, which has hit 800 million weekly active users. AgentKit includes a few core capabilities, the first of which is the AI Agent Builder.
Evals for Agents introduces tools to measure AI agent performance, including step-by-step trace grading, datasets for assessing individual agent components, automated prompt optimisation, and the ability to run evaluations on external models directly from the OpenAI platform. AgentKit includes access to the OpenAI 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.
