OpenAI Pushes AI Agent Capabilities With New Developer API

OpenAI has introduced a new Responses API to help developers create AI agents that can perform tasks independently using the company's AI models. The Responses API will eventually replace the current Assistants API, which is planned to be retired in the first half of 2026. The new API allows users to develop custom AI agents that can scan company files and navigate websites, similar to the functions available through OpenAI's Operator agent. However, OpenAI acknowledges that its Computer-Using Agent model is not yet reliable for automating tasks on operating systems and can make unintended mistakes. The company describes the new API as an early iteration that it will continue to improve over time. Developers using the Responses API can access the same models that power ChatGPT Search, including GPT-4o search and GPT-4o mini search, which can browse the web to answer questions and cite sources. The added web search ability dramatically improves the factual accuracy of OpenAI's AI models, with GPT-4o search scoring 90 percent on the SimpleQA benchmark. Despite these improvements, the technology still has significant limitations, including issues with navigating websites and making factual mistakes. OpenAI has also released the open source Agents SDK, providing developers with free tools to integrate models with internal systems and monitor agent activities. The Agents SDK follows OpenAI's earlier release of Swarm, a framework for orchestrating multiple agents, and is designed to help developers implement safeguards and improve the overall performance of their AI agents.