AI Workflows & Teams
Organize processes, materials and responsibilities so work can be repeated and shared.
Make a one-off method repeatable and transferable
Recommended reading
Should AI Work Live in a Project, Folder, or Conversation?
Give projects, files and conversations distinct roles, with an established place for important results.
RAG
- RAGAgentic RAG vs. Traditional RAG: Five Differences That MatterAgentic RAG can rewrite queries, change retrieval methods, and check its own results. Compare that loop with traditional RAG and when the added complexity helps.
- RAGEnterprise RAG: From Go/No-Go to EvaluationA document-Q&A experiment follows RAG from go/no-go through evaluation and optimization, comparing retrieval quality with the scale limits of context stuffing.
- RAGQuery Rewriting Raised This RAG Score from 77 to 88A RAG optimization record links retrieval diagnosis to query rewriting and verification. See why some proposed improvements were selected and others deferred.
- RAGHow to Diagnose RAG Retrieval QualityDiagnose RAG answers by labeling retrieved chunks and tracing failed questions. The experiment separates retrieval problems from the model's ability to answer.
- RAGWhat 200 Files Revealed About RAG Data PreparationControlled document-Q&A experiments compare RAG, keyword search, and context stuffing, showing how information scale changes the appropriate retrieval approach.
- RAGSix Decisions to Make Before Building a RAG PipelineA RAG build record explains choices in chunking, embeddings, vector storage, and search configuration, including the alternatives and compromises at each step.
- RAGDoes Your Knowledge Base Really Need RAG?Before building RAG, test a document knowledge base against simpler baselines. This experiment examines context stuffing and the limits of keyword retrieval.