AI 今日热榜 — 汇集全球顶尖来源的最新 AI 新闻、研究和趋势，为您节省宝贵时间

@harryjwang · X

I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age

@MrTechPM · X

Built this because I was tired of job hunting feeling like a second full-time job. JobFlow automatically tracks applications from your inbox, organises your job search, and gives AI-powered guidance throughout the process. Still early, feedback helps...

rohanrecommends · Product Hunt

Fuzzy AI We warm your prospects before reaching out