ToolsThe story, in brief

Introducing AgentKit, new Evals, and RFT for agents

OpenAI just shipped three new agent tools. Here's why your prototype-to-production timeline just got shorter.

Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

OpenAI is releasing developer-facing tools (AgentKit, expanded evals, reinforcement fine-tuning) designed to accelerate agent deployment from research to production—a direct signal that agentic AI is moving from capability demos to operational workflows.

The key facts

6 to know
  1. AgentKit released for developers

  2. Expanded evals capabilities shipped

  3. Reinforcement fine-tuning (RFT) for agents added

  4. Focus on prototype-to-production acceleration

  5. October 6, 2025 release date

  6. Agent-specific developer tooling ecosystem expanding

Go to the source

OpenAI Blogopenai.com

Publisher excerpt: 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.
Read original report
Back to today's editionMore tools news

Keep reading

Related stories

More from Tools