Documentation
Learn how to install, configure, and use Bandito to optimize your LLM applications.
Getting Started
Install Bandito, create an account, and start tracing your LLM calls in minutes.
Observing Traces
See what's happening in your LLM application — cost, latency, patterns, and quality signals.
Grading
Grade your LLM outputs in the terminal. Human grades power judge calibration, quality analysis, and improvement testing.
LLM-as-Judge
Scale your quality evaluation beyond manual grading. Define a rubric, calibrate it against your human grades, then score all traces automatically.
Assertions
Run programmatic checks against your traces. Assertions are Python functions — write any check you can express in code.
Datasets
Create curated collections of traces for regression testing, comparison, and offline evaluation.
Analysis
Deeper analysis surfaces for cost/quality/latency optimization, drift detection, and eval coverage.
AI Coding Tool Integration
Connect Bandito with Claude Code, Cursor, or other AI coding tools.