# Kiln AI Docs

## Kiln AI Docs

- [Welcome to Kiln AI](https://docs.kiln.tech/readme.md): Rapid AI Prototyping and Dataset Collaboration Tool
- [Quickstart](https://docs.kiln.tech/docs/quickstart.md): Download our app for MacOS, Windows or Linux
- [Tasks](https://docs.kiln.tech/docs/tasks.md): What a task is, how to create one, and when to use single-turn or multi-turn
- [Models and AI Providers](https://docs.kiln.tech/docs/models-and-ai-providers.md): Connect to Ollama, OpenAI, OpenRouter, AWS, Azure, Vertex, Together, Fireworks, and more
- [End to End Project Demo](https://docs.kiln.tech/docs/end-to-end-project-demo.md): Video walkthrough of creating tasks, evals, fine-tuning, synthetic data gen, and more!
- [Optimizers](https://docs.kiln.tech/docs/optimizers.md): Tools to build the optimal AI system for your task
- [Fine Tuning](https://docs.kiln.tech/docs/fine-tuning.md): Create custom fine-tuned models for your use case
- [Fine Tuning Guide](https://docs.kiln.tech/docs/fine-tuning/fine-tuning-guide.md): Fine tuning 9 Models in 18 minutes
- [Train a Reasoning Model](https://docs.kiln.tech/docs/fine-tuning/guide-train-a-reasoning-model.md): Built a reasoning model, like o3 or R1, for your use case
- [Fine Tuning for Tool Use](https://docs.kiln.tech/docs/fine-tuning/fine-tuning-for-tool-use.md): Build fine-tuned models for calling a set of tools, like MCP
- [Evals](https://docs.kiln.tech/docs/evals-and-specs.md): Powerful tools to measure and optimize your AI systems
- [Evaluations](https://docs.kiln.tech/docs/evals-and-specs/evaluations.md): Evaluate the quality of your models/tasks using state-of-the-art evals
- [Eval Builder](https://docs.kiln.tech/docs/evals-and-specs/specifications.md): The Kiln Eval Builder combines evals, synthetic data generation, automatic judge prompt creation, and judge alignment into one easy to use feature
- [Judge Types](https://docs.kiln.tech/docs/evals-and-specs/judge-types.md): Score your evals with LLM judges, or with fast deterministic checks that cost nothing to run
- [LLM Judges](https://docs.kiln.tech/docs/evals-and-specs/llm-judges.md): Grade your task's output with a model and a rubric you write
- [Code Judges](https://docs.kiln.tech/docs/evals-and-specs/code-judges.md): Score your evals with a custom Python function
- [Evaluate RAG Accuracy: Q\&A Evals](https://docs.kiln.tech/docs/evals-and-specs/evaluate-rag-accuracy-q-and-a-evals.md): Know your Kiln Search tools find the right answer with RAG evals and synthetic Q\&A data
- [Evaluate Appropriate Tool Use](https://docs.kiln.tech/docs/evals-and-specs/evaluate-appropriate-tool-use.md): Test your model's ability to appropriately invoke tools
- [Tools & MCP](https://docs.kiln.tech/docs/tools-and-mcp.md): Connect powerful tools to your Kiln tasks
- [Code Tools](https://docs.kiln.tech/docs/tools-and-mcp/code-tools.md): Write a Python function that runs as a tool, and can call other tools
- [Connect to Existing Agents](https://docs.kiln.tech/docs/tools-and-mcp/connect-to-existing-agents.md): You can connect Kiln Evals to existing agents on any platform, using MCP
- [Prompts](https://docs.kiln.tech/docs/prompts.md): How to use our prompt optimizer, prompt generators, or create your own prompt
- [Automatic Prompt Optimizer](https://docs.kiln.tech/docs/prompts/automatic-prompt-optimizer.md): Find the best prompt for your task, automatically.
- [Prompt Generators](https://docs.kiln.tech/docs/prompts/prompt-generators.md): Prompt generators build prompts for you combing best practices and data from your dataset
- [Documents & Search (RAG)](https://docs.kiln.tech/docs/documents-and-search-rag.md): Add knowledge to your AI systems with docs & search
- [Agents](https://docs.kiln.tech/docs/agents.md): Building Agentic AI systems has never been easier
- [Skills](https://docs.kiln.tech/docs/skills.md): Load more instructions, depending on the goal (Progressive Prompt Enhancement)
- [Synthetic Data Generation](https://docs.kiln.tech/docs/synthetic-data-generation.md): Generate synthetic data for fine-tuning or evaluation
- [Synthetic Data Guides](https://docs.kiln.tech/docs/synthetic-data-generation/synthetic-data-guides.md): Improve your synthetic data generation
- [Generating Synthetic Data](https://docs.kiln.tech/docs/synthetic-data-generation/generating-synthetic-data.md): Improve evals or fine-tuning with synthetic data
- [Input Templates & Feature Engineering](https://docs.kiln.tech/docs/input-templates-and-feature-engineering.md): Filter and format model inputs
- [Issues](https://docs.kiln.tech/docs/issues.md): Kiln Issues are an AI-native issue tracker for AI teams
- [Reasoning & Chain of Thought](https://docs.kiln.tech/docs/reasoning-and-chain-of-thought.md): Improve your model's quality with inference time scaling
- [Reviewing and Rating](https://docs.kiln.tech/docs/reviewing-and-rating.md): Ratings help multi-shot prompting, fine-tuning, evals, and more
- [Collaboration](https://docs.kiln.tech/docs/collaboration.md): How to collaborate with your team using Kiln
- [Automatic Git Sync](https://docs.kiln.tech/docs/collaboration/automatic-git-sync.md): Git, even if you've never used a terminal
- [Organizing Datasets](https://docs.kiln.tech/docs/organizing-datasets.md): Tag, Filter, Sort, Import, Freeze and Split
- [Structured Data / JSON](https://docs.kiln.tech/docs/structured-data-json.md)
- [Keyboard Shortcuts](https://docs.kiln.tech/docs/keyboard-shortcuts.md)
- [Privacy](https://docs.kiln.tech/docs/privacy.md): Kiln is private by design
- [Repairing Responses](https://docs.kiln.tech/docs/repairing-responses.md): "Teach the model, you will" - ML Yoda
- [Troubleshooting & Logs](https://docs.kiln.tech/docs/troubleshooting-and-logs.md): How to troubleshoot errors from the logs
- [Productionizing Kiln](https://docs.kiln.tech/docs/productionizing-kiln.md): How to take ideas from the lab (Kiln) into your product
- [Contact Us](https://docs.kiln.tech/docs/contact-us.md): We'd love to chat!
- [Python Library Setup](https://docs.kiln.tech/developers/python-library-quickstart.md): pip install kiln\_ai
- [Rest API](https://docs.kiln.tech/developers/rest-api.md): Call Kiln over HTTP
- [Kiln Data Model](https://docs.kiln.tech/developers/kiln-datamodel.md): How Kiln projects are structured