Get started
What is Maihem
Maihem automatically evaluates your AI workflows. Easily find failures and understand their root causes to improve your AI agents.
In Maihem, an agentic workflow is any language-based AI workflow, from single LLM calls to complex agentic workflows.
How-to guides
Step-by-step guides with examples of how to evaluate your AI agent
Reference
Read our detailed documentation
How it works
1
Install Maihem SDK
2
Add our decorator functions to each method in your agent's workflow
3
Upload or generate a dataset
4
Maihem automatically detects failures in your agent and suggests improvements