---
type: "Evidence Item"
title: "Introducing AgentKit, new Evals, and RFT for agents"
description: "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."
resource: "https://openai.com/index/introducing-agentkit"
tags: ["appendix-iii", "benchmark", "openai"]
timestamp: "2025-10-06"
category: "benchmark"
publisher: "OpenAI"
cope_score: 90
confidence: 0.9
---

# Introducing AgentKit, new Evals, and RFT for agents

# Claim

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.

# Relevance

Appendix III, section one: model and benchmark capability evidence

# Oracle Verdict

OpenAI is describing a frontier or production capability that pushes directly on the thesis. The important signal is not the marketing language; it is the widening set of tasks now being routed through model-driven execution rather than ordinary software or headcount.

# Metadata

* Publisher: OpenAI
* Category: benchmark
* Sector: Software engineering
* Capability: Agent platform and API infrastructure
* Cope score: 90
* Confidence: 0.9

# Related Concepts

* [Live evidence index](index.md)
* [Thesis](../thesis.md)

# Citations

[1] [Introducing AgentKit, new Evals, and RFT for agents](https://openai.com/index/introducing-agentkit)