User Guides
Runs
Comparisons Guide
Fire a prompt at multiple models simultaneously and compare cost, latency, and output side by side.
Evaluations Guide
Score model outputs against a rubric or gold standard answer and get per-criterion reasoning.
Scores Guide
Check text you already have against your documented standard, and get a per-criterion verdict that quotes the exact phrase at fault.
Agent Analysis Guide
How to read an agent analysis and turn each finding into a fix.
Benchmark Guide
Save a run configuration, schedule it on a cadence, and track quality and cost drift over time.
Reference
Prompting Guide
How to write prompts that produce reliable, comparable results across models.
Results Guide
How to read your results: how scores are calculated, what affects them, and how to use the diagnostic judge to find out why.
Diagnostics Guide
How the diagnostic judge works, what it flags, and how to act on findings in comparisons, evaluations, and benchmarks.
Presets Guide
Save a run configuration once and invoke it by name from the dashboard, the API, or your agent. Your team's standard, callable everywhere.
Rubric Guide
How to write criteria that produce reliable, consistent judge scores, and how to fix them when they don't.
Inference Parameters Guide
What temperature, seed, max tokens, and the other inference parameters do, and why getting them right is the difference between a benchmark and a lottery.
Monitoring Guide
How LLM Prover detects changes in model quality, cost, and latency, and how to configure alerts so you know before users do.
MCP Recipes Guide
Hand your AI agent a ready-to-paste playbook that runs LLM Prover tools in order, polls for results, and reports back in plain language.
Config
System Prompts Guide
When to use system prompts, how to write them, how they interact with rubrics and context stores, and how to A/B test two system prompts on the same model.
RAG Store Guide
How to create a context store, upload documents, and get reliable retrieval in comparisons, evaluations, and benchmarks.
Compliance Store Guide
Upload regulations or policies as a compliance store and score model outputs against specific clauses.
BYOE Guide
Register any OpenAI-compatible endpoint and benchmark your own models against any model in the registry.
No docs match your search.