{ "schema": "aiblocks-page/1", "id": "agency-engineering-rag-pipeline-engineer", "type": "agent", "name": "RAG pipeline implementation planner", "summary": "Plan a RAG pipeline that finds the right passages in your documents: chunking, search setup and a question set to score each change.", "headline": "RAG pipeline implementation planner", "subhead": "RAG means your AI looks up passages in your own documents, then answers from them. Describe your documents and the questions people ask. It plans how to split, index and search them, and how to test each change. You get a build plan and a score sheet.", "job": { "id": "build-software", "name": "Build and ship software" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-26", "inputs": [ { "type": "question", "required": true, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" }, { "type": "source_text", "required": false, "label": "Source text", "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link" }, { "type": "plan", "required": false, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" } ], "outputs": [ { "type": "plan", "required": true, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" } ], "you_give": [ "What your documents are, how many, how long, and in which languages", "Ten to twenty real questions people ask, with the document that holds each answer if you know", "Your current setup and where it fails (optional)", "Your stack and limits, such as database, language, hosting, speed and budget", "Who may see which documents (optional)" ], "you_get": [ "An audit of your documents, and a chunking plan that fits their layout", "Embedding and index choices, with a way to compare two or more on your own text", "A search plan that mixes keyword and meaning search, with filters", "A rule for whether to add re-ranking", "A test plan with question pairs and four scores to track", "A one-change-at-a-time improvement loop, and what to watch after launch" ], "use_when": [ "Your document chatbot gives wrong, vague or unrelated answers.", "You plan a chatbot over PDFs, help articles or contracts and don't know how to split and index them.", "You need to choose between search by meaning, search by keyword or both.", "You changed something and want proof that answers got better, not just a feeling." ], "skip_when": [ "You want a whole AI feature, with model choice and deployment. Use the AI feature planner.", "You want to improve a site or product search box. Use the Search Relevance Engineer agent.", "Your source data is messy, duplicated or broken. Use the Data pipeline designer first." ], "output_sample": { "input": [ "A description of your documents, or a sample of them", "Ten to twenty real questions your users ask", "Your stack and limits, such as database, hosting and speed", "Your current setup and where it fails (optional)" ], "prerequisites": [ "An AI that can read pasted text or files, such as Claude, ChatGPT or Gemini", "A way to run and score a pipeline, because your chat AI can't (optional)" ], "output": [ { "name": "Corpus audit", "contains": "Your document types, length, layout and languages, and the kinds of questions users ask." }, { "name": "Chunking plan", "contains": "How to split each document type, with size, overlap and the reason." }, { "name": "Embedding and index test", "contains": "Which models and index settings to compare on your own text, and how to score them." }, { "name": "Search design", "contains": "The keyword and meaning mix, metadata filters, passages fetched and the duplicate rule." }, { "name": "Re-ranking decision", "contains": "A rule for when to add re-ranking, based on your scores and delay limit." }, { "name": "Eval plan", "contains": "How to build the question set and track four scores after each change." }, { "name": "Monitoring", "contains": "What to log and the weekly check that spots drift." } ] }, "output_shape": "CORPUS AUDIT\n Documents: | | | | \n Questions users ask: | \n\nMETADATA PLAN\n