$ loading_
Build, evaluate, and optimize AI systems with RAG, agents, fine-tuning, and datasets.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Kiln" yet — see the docs or source repo.
Use Kiln to design an evaluation workflow for my RAG question-answering system, including test set creation, accuracy metrics, citation quality checks, and failure analysis.
An actionable RAG evaluation plan with metric definitions, dataset structure, and optimization recommendations.
Use Kiln to generate a high-quality synthetic training dataset for a customer support assistant, covering common questions, complex follow-ups, and refusal cases, organized in JSONL format.
A structured synthetic dataset plan or examples ready for fine-tuning preparation and quality review.
Use Kiln to analyze my AI agent workflow, identify weak points in tool usage, prompt design, and task decomposition, and propose optimization experiments.
Diagnostic findings, evaluation ideas, and an iterative optimization roadmap for the agent system.
Evaluate AI safety classifier robustness against decomposition, obfuscation, and multi-agent attacks.
Turn any data source into an MCP server for direct AI querying.
Run prompt and RAG evaluations through MCP clients with hosted backend execution.
Intelligent RAG tool that chooses between private knowledge and web search.
Turn unstructured documents into a searchable knowledge base for AI agents.
Evaluate AI agent outputs for CI gates, regressions, and canary promotions.