Teacher since July 2025
Fumiko Arai
Takes retrieval systems from demo to dependable: parsing, citations, freshness, retrieval evaluation and debugging
9
tutors built
4.6Sample
average from 14 reviews
267Sample
lessons taught by their tutors
About Fumiko
Most RAG demos work on the ten documents someone picked. I teach what happens after that: scanned PDFs, tables, documents that change every week, answers that cite the wrong page and users who ask things the documents never covered. My background is in document processing and internal knowledge tools, so I am practical about formats and sceptical of any setup that has not been measured. I also teach when not to build retrieval at all. Lessons usually start from a failure you bring, or one I provide, and work backwards to the cause.
Knows about
Tutors by Fumiko
9 tutors
Evaluating Retrieval Quality
Measure whether your retrieval finds the right passages with real queries, relevance labels and the right metrics.75 lessonsSampleFumiko Arai$11Debugging a RAG App That Answers BadlyDebugging a RAG App That Answers Badly
Trace each bad RAG answer to its real cause, from missing documents to ignored passages, and fix the most common.56 lessonsSampleFumiko Arai$8When Retrieval Is the Wrong ToolWhen Retrieval Is the Wrong Tool
Decide when RAG fits a problem and when a database query, tool call, longer prompt or plain search fits better.40 lessonsSampleFumiko Arai$5Planning a RAG Pilot for Company DocsPlanning a RAG Pilot for Company Docs
Scope a small, measurable pilot for an assistant over your company documents before anyone builds too much.37 lessonsSampleFumiko Arai$4Parsing PDFs and Messy DocumentsParsing PDFs and Messy Documents
Get clean, well ordered text, tables and page numbers out of PDFs, scans, slides and office files.36 lessonsSampleFumiko Arai$5Citations and Grounded AnswersCitations and Grounded Answers
Make RAG answers cite the right sources and check that every claim is actually supported by them.23 lessonsSampleFumiko Arai$7Questions over Tables and DatabasesQuestions over Tables and Databases
Answer questions over spreadsheets, document tables and databases correctly, with text to SQL done safely.Fumiko Arai$8Keeping a RAG Index FreshKeeping a RAG Index Fresh
Keep retrieval in sync with changing documents: updates, deletions, versions, permissions and re-embedding.Fumiko Arai$10Long Context Versus RetrievalLong Context Versus Retrieval
Choose between sending whole documents to a long context model and retrieving passages, using evidence.Fumiko Arai$6Recent reviews
What students said about Fumiko's tutors.
- Aarav G.Sample
We were about to build RAG for analytics questions. The counting example stopped us, and the batch extraction plus SQL approach works far better.
- Elena T.Sample
Useful for our architecture review. The checklist is short enough that people actually use it. A little brief on combining paths.
- Adaeze C.Sample
We cut our scope from everything to warranty questions for one team. The pilot plan fit on one page and our leadership approved it quickly.
- Thomas G.Sample
Measuring the baseline first was the advice I would have skipped. Glad I did not; it made our results credible.
- Darius N.Sample
The trick of rerunning with only the correct passage told us immediately whether to fix retrieval or generation. Practical lessons.
- Lucia M.Sample
The cause list in order is now pinned in our team channel. Half our bad answers were content gaps, not model problems. We stopped rewriting the prompt every day.