How to Test RAG Pipelines for Retrieval Quality and Answer Faithfulness
A RAG pipeline can fail in two different places, and one end-to-end score will not tell you which. Test retrieval and generation separately: score Precision@k and Recall@k…
TAGGED GUIDES
#evaluation
Explore the guides, ideas, and practical explanations in this topic.
5 published articlesHow to Write Acceptance Criteria for AI Agent Workflows
Acceptance criteria for AI agent workflows are the observable conditions an output must meet before it counts as complete: the expected artifact, the evidence behind it, its…
How to Document a Prompt Experiment for Other Users
A prompt experiment is only reproducible if the record captures more than the prompt text. Document the immutable prompt revision, its variable and output contract, the model…
How to Choose an AI Tool for Your Actual Workflow: A Practical Selection Guide
The right AI tool is the one that fits a specific task you already do, survives a fair test on your own examples, and earns a place…
How to Compare Local Language Models with Reproducible Tests
A reproducible local model comparison pins the model, runtime, hardware, prompt template, context settings, and sampling parameters before measuring quality, latency, memory, and failure rates. This guide…