
Referee.chat — An AI Panel Works Your Goal, a Referee Rules
设定目标和标准,由AI小组评估,裁判用引用来源做出判决。
nadermx · HN
Referee.Chat - Set the goal. An AI panel works. Referee clears it done
完整作品展
技术栈
60 projects

设定目标和标准,由AI小组评估,裁判用引用来源做出判决。
nadermx · HN
Referee.Chat - Set the goal. An AI panel works. Referee clears it done

Build and grow your community with channels, conversations, hubs, and events. Create a space where your people connect and engage.
@GammsApp · X

用 Onbookr 管理预约、同步日历、自动发送提醒。
@helloukey · X

将会议转换为结构化规格和用户故事供 Linear 或 Shortcut 使用。
@tryspectr · X

在利比亚查找清洁公司和工人,提供评分、价格和联系方式。
@sofianelshwihdy · X
Check out what I just built with Lovable!

Navigate connected inboxes in one place on web, iPhone, or through MCP. Frey keeps consented meeting notes, organises tasks and projects, and surfaces missed decisions.
@getfreydom · X
Frey — every inbox, one place. Founders can navigate the Gmail and Outlook accounts they choose, carry source-linked work into meetings and projects, and review decisions with evidence attached.

在旧金山的酒吧与足球迷见面,选择球队身份,加入实时球迷聊天。
@Sanjayyb7 · X

Crie um canal privado de feedback com sua marca antes que seus clientes reclamem no Reclame Aqui, redes sociais ou lojas de apps. Widgets, roadmap público e changelog — tudo white
@teles2o · X

创建和管理共享看板上的任务,AI代理可通过MCP自动更新。
@kelviakanban · X
AI agents are great at writing code. Remembering to update the task board? Less great. So we built Kelvia: a shared Kanban where Claude Code, Codex and Cursor can move tasks, comment and log time through MCP. You can also see exactly what they broke 😅

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

MeetTalky 用AI记录和转录会议,构建可搜索的企业知识库。
@dojopy · X
🚀 Your meetings should create decisions, not paperwork. MeetTalky transcribes, summarizes, generates subtitles, and extracts action items automatically with AI. Less note-taking. More building. Try it: #AI #Productivity #Meetings #SaaS #BuildInPublic #ArtificialIntelligence

发现本地活动并加入,与志趣相投的人联系。
@nextisonme_ · X
Nextisonme, a social app based on the concept of Treat and Meet