Introducing AgentKit, new Evals, and RFT for agents

What changed

Today, we’re releasing new tools to help developers go from prototype to production faster: AgentKit, expanded evals capabilities, and reinforcement fine-tuning for agents.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Introducing workspace agents in ChatGPT
• Introducing improvements to the fine-tuning API and expanding our custom models program
• Introducing vision to the fine-tuning API

• Introducing workspace agents in ChatGPT similarity 0.17
• Introducing improvements to the fine-tuning API and expanding our custom models program similarity 0.16
• Introducing vision to the fine-tuning API similarity 0.15