金融商业1 week ago
Verdict · Hire on evidence. Put it in writing.
基于证据分析比较候选人，生成招聘决策文件。
facundobon · HN
Verdict – AI hiring verdicts where every score cites the CV verbatim
完整作品展
技术栈
60 projects
基于证据分析比较候选人，生成招聘决策文件。
facundobon · HN
Verdict – AI hiring verdicts where every score cites the CV verbatim
用CompetitorSearch描述竞争对手，获得实时网络搜索的并排分析和档案。
@Wagner__kent · X
Good day Gainframe, built CompetitorSearch — describe your competitors, get a live web-searched side-by-side breakdown + full dossier on each. Selling it outright (Mistral+Tavily+Vercel, 156 visits/19 searches/10 users). Happy to walk you through it.
分析文本以识别 10 种有毒和 7 种健康的沟通模式。
@WEreFrame · X
Underrated...well I wouldn't say that because I'm just starting, but overlooked maybe. The impact on humanity will be noticed across the globe. Stop reacting. Start reFraming.
发现各平台热门内容创意,用你的风格转化为原创作品。
@davidtostscale · X
AI评分和抄袭检测工具，支持评分标准和成果导向教学。
@ProfDeskApp · X
Let's connect. Building giving teachers their night back.
每周自动追踪竞争对手的定价、功能和消息变化。
@Caden1Fenn · X
Intel Brief — tracks what your competitors change (pricing, features, positioning) and delivers it to your inbox weekly. Built for indie SaaS founders.
检查论文中的AI写作和抄袭，在提交到Turnitin前自查。
PaperCheck — 论文提交前自查工具，提供 Turnitin 查重 + AI 写作检测报告，帮助学生在正式提交前发现问题
为会议前的参与者生成有来源的研究简报。
@dhanushkenkiri · X
Building If you ever wanted to know about someone online this is your go to place. Also, let's connect!
记录交易、追踪权益曲线和性能的交易日志应用。
@NimraWeb3 · X
So I vibe coded my own with Lovable TradeBook. Log trades w/ session, killzone, model, grade, R:R + screenshots, track multiple accounts, get a real dashboard (equity curve, win streaks, pair/session breakdowns). Demo: GitHub:
管理学术会议：提交和审阅论文、处理日程安排和注册。
@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
