14Every sentence the model writes must link to a source span. Design the citation system.▼mediumHarveyGleanAnthropic1 replies○ sign inCitations are the trust interface of enterprise RAG, and the easiest thing to fake badly. Covers inline citation generation, span verification, and the verification-rate metric that interviewers actually want.Open full answer →
23Design an AI contract-review workflow (clause extraction, risk flags, citations) that skeptical lawyers will actually trust▼hardHarveyAnthropicHebbia1 replies◆ premiumHarvey's signature design question. The twist: the architecture is the easy half. The graded half is designing for reviewer trust, where one hallucinated clause costs more than a hundred correct ones earn.Open full answer →
49Build multimodal RAG over 10,000 PowerPoint decks that answers chart queries and cites the exact slide.▼hardGleanHebbiaMicrosoft1 replies◆ premiumSlides are the worst RAG corpus: text in shapes, meaning in charts, the message in the image. A query like 'the blue bar chart with Q3 revenue' fails if you embed only the extracted text, and citing the wrong slide number kills trust instantly.Open full answer →
52A customer wants a deep-research agent over their private docs and the open web. Design it so stakeholders trust the citations.▼expertOpenAIAnthropic◆ premiumDeep-research agents run unsupervised for twenty minutes and their report goes straight to an executive. The failure mode is not a crash, it is confident citations that do not support the claims. Most candidates design the retrieval and skip the verification pass, the run budget, and the freshness story.Open full answer →
91Tag every part of a generated sentence that came from a source, merging overlaps and listing the sources that contributed.▼hardNewHarveyAnthropic2 replies◆ premiumThe signature coding problem at a legal-AI company, and it is interval merging wearing a product costume. The candidates who struggle are the ones who start matching before deciding what a match even is.Open full answer →