Build And Optimize Agent Eval Workflows With Kiln

---
name: "Build and optimize agent eval workflows with Kiln"
slug: "build-and-optimize-agent-eval-workflows-with-kiln"
description: "Use Kiln to create eval datasets, rate outputs, optimize prompts and models, and ship the same AI task or agent definition from a local workbench into production code."
github_stars: 5072
verification: "security_reviewed"
source: "https://github.com/Kiln-AI/Kiln"
author: "Kiln AI"
publisher_type: "company"
category: "Monitoring & Alerts"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "Kiln-AI/Kiln"
  github_stars: 5072
---

# Build and optimize agent eval workflows with Kiln

Use Kiln to create eval datasets, rate outputs, optimize prompts and models, and ship the same AI task or agent definition from a local workbench into production code.

## Prerequisites

Kiln Desktop or Python 3 with kiln-ai, model provider API keys or local Ollama

## Installation

Install or set up from the source-backed instructions:

Install Kiln Desktop from the official download page for a no-code eval workbench, or install the open Python library with pip install kiln-ai when the workflow needs to run from code.

- Source: https://github.com/Kiln-AI/Kiln

## Documentation

- https://docs.kiln.tech

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/build-and-optimize-agent-eval-workflows-with-kiln/)