Kiln News & Updates

What is Kiln?

Kiln is a Fine-Tuning tool. Build better AI systems with evals, RAG, agents, synthetic data, fine-tuning, and prompt optimization. Kiln is free to use. It is available on macOS. It is aimed at developers, data scientists and ai teams.

Kiln helps build, evaluate, and optimize AI systems. It includes features like no-code synthetic data generation, fine-tuning, and dataset collaboration. Designed for teams to create reliable AI models.

Built for developers, data scientists, ai teams and product managers.

Key capabilities

Features

No-Code Synthetic Data Generation
Generates synthetic data without coding.
Fine-Tuning
Adjusts models to specific tasks.
Dataset Collaboration
Enables team collaboration on datasets.
Cloud Or Local
Supports deployment in cloud or local environments.
Public API
Python Library Setup
SSO / SAML

Use cases

Evaluate AI systems using built-in evaluations
Optimize AI models with prompt optimization techniques
Generate synthetic data for training models
Collaborate on datasets with team members
Deploy AI models in cloud or local environments
Integrate with external services via public API

Popular use cases

Build Apps Without Code

Who it's for

Pros & cons

Pros

Free plan available
Public API available
Integrates with Azure, OpenAI, Anthropic, Hugging Face

Cons

No documented limitations yet.

Pricing

Free.

Kiln plans
Plan	Price
Individual	Free
Enterprise	Custom

See current pricing on Kiln's website

Integrations

AI models

GPT 4o

Developer & API

Public REST API available

SDKs: Python SDK, python SDK, Python

Open source· 5.1K stars· 381 forks

API documentation Source code

Security & compliance

SSO
SAML

As stated on Kiln's website — not independently verified by AiByts.

FAQ

What is Kiln?

Kiln is a Fine-Tuning tool. Build better AI systems with evals, RAG, agents, synthetic data, fine-tuning, and prompt optimization. Kiln helps build, evaluate, and optimize AI systems. It includes features like no-code synthetic data generation, fine-tuning, and dataset collaboration. Designed for teams to create reliable AI models.

Is Kiln free?

Yes, Kiln is free to use.

How much does Kiln cost?

Kiln offers 2 plans: Individual (Free) and Enterprise (Custom).

Does Kiln have an API?

Yes, Kiln offers a public REST API for building custom integrations.

What platforms does Kiln support?

Kiln is available on macOS.

Who should use Kiln?

Kiln is built for developers, data scientists, ai teams, product managers and machine learning engineers. Common uses: evaluate AI systems using built-in evaluations, optimize AI models with prompt optimization techniques, generate synthetic data for training models and collaborate on datasets with team members.

What does Kiln integrate with?

Kiln integrates with Azure, OpenAI, Anthropic and Hugging Face.

Is Kiln open source?

Yes, Kiln is open source.

What are the best alternatives to Kiln?

Similar tools on AiByts include Browserbase, Tinker, Respan, Pinecone and Respira for WordPress.

Kiln news & updates

Introducing Seahaven: Synthetic Worlds for Agent Evals and RL
Seahaven is an open source Python framework for building synthetic worlds for AI agents: stateful, resettable, parallel environments for evals and RL.
Kiln BlogOct 8, 20265 min read
Auto-optimizing Jev: half the errors, 1/7 the cost
We pointed our autoresearch loop at Jev, a classifier that can't be fine-tuned. It ended up making half as many mistakes as a reasoning model, for a seventh of the cost and a thirtieth of the latency.
Kiln BlogSep 21, 202617 min read
We made our launch video with Claude Code (and open-sourced the tool)
Kiln just launched v1. We made the launch video in Claude Code. Along the way we built and open-sourced videowright: the tool we wished we'd had.
Kiln BlogMay 20, 20266 min read
Git-Backed SaaS: SaaS Without the Service
Kiln uses git for everything you'd normally need a database for, with the instant-syncing user-experience of SaaS. Every API call is a commit. Every read is a local file.
Kiln BlogMay 14, 202611 min read
Why Your Agent Probably Needs Skills
Kiln has added agent skills support! Here's what skills are, why progressive disclosure works, and how to use them in your agents.
Kiln BlogMar 18, 20263 min read
Introducing Kiln Prompt Optimizer
Kiln will now automatically find the ideal prompt for your task, guided by your own evals. Performance gains that blow away manual optimization, and even beat fine-tuning.
Kiln BlogFeb 23, 20263 min read
The Requirements Layer Your AI System is Missing
Most AI teams think they have a testing problem. But the real issue is they aren't defining what "good" actually means. Learn how specs can transform your AI development workflow.
Kiln BlogFeb 9, 20267 min read
Kiln Eval Builder & AI Assistant for Evals and Synthetic Data
Introducing Kiln Eval Builder — a guided assistant that helps you build accurate evals, synthetic data, and judge prompts in minutes instead of hours.
Kiln BlogFeb 4, 20262 min read
RAG Isn't One Size Fits All: Here's How to Tune It for Your Use Case
Great RAG comes from a tight iteration loop. Learn how to systematically improve each layer of your RAG system using Kiln and LanceDB.
Kiln BlogDec 1, 202513 min read
New in Kiln: RAG Q&A Evals, Tool Use Evals, Reranking, Semantic Chunking, an MCP server, and more!
Our new v0.23.0 app release includes powerful new features for RAG, evals, and more!
Kiln BlogNov 14, 20253 min read
Introducing Kiln Agent Builder
Kiln now supports building agentic systems in as little as 5 minutes. Also new is Local RAG: build RAG systems without any third party services.
Kiln BlogOct 14, 20253 min read
New in Kiln: Search Tools/RAG, Document Library, and Synthetic Data V3
Introducing our biggest release ever! Build state-of-the-art RAG systems in minutes, with drag-and-drop!
Kiln BlogSep 23, 20252 min read
New in Kiln: Tool Calling and MCP
We just added support for tool-calling and MCP (Model Context Protocol) to Kiln! This new feature includes:
Kiln BlogSep 9, 20252 min read
End to End AI Project with Evals, Synthetic Data, and Fine-Tuning
A video walk through of Kiln project from start to finish. The project we build is open source and available on GitHub.
Kiln BlogAug 6, 20258 min read
I wrote 2000 LLM test cases so you don't have to
I've been building Kiln AI: an open tool to help you find the best way to run your AI workload. Testing different models to see which ones work best is a huge part of this process.
Kiln BlogJul 21, 20257 min read
Kiln Release v0.18.1: Evals V2, Synthetic Data V2, Kiln Issues, New Models, and more!
Our new release is our biggest ever! Read about how we improved evals, synthetic data, and a whole new concept: Kiln Issues.
Kiln BlogJul 17, 20253 min read
Many Small Evals Beat One Big Eval, Every Time
Evaluating AI products is notoriously difficult. In this article we walk through how to make it approachable, maintainable, and iterative using many small evals instead of one large eval.
Kiln BlogJun 27, 20258 min read
Distillation in Practice: Ablating Gemma 3 27B with synthetic data from Sonnet 4
A hands-on experiment fine-tuning Gemma 3 27B using synthetic data from Sonnet 4, achieving performance that rivals GPT-4o on specific tasks while being smaller and cheaper to run.
Kiln BlogMay 30, 20255 min read