rohanrecommends · Product Hunt

Nautis The AI-native Operating System for founders.

@wrrkai_ · X

This week we're shipping Helping startups and growing businesses manage every customer conversation from one AI-powered workspace.

@AmiranAzaladze · X

* For all businesses * Just cancel all your integrations and CRM and switch to one single soft.

Hobbit — 青少年足球教练 AI 智能体。核心目标是培养小球员的"球商"。教案设计、战术图绘制、球队管理、球员肖像卡、海报、比赛报告一站搞定。免费起步，聊天免费，支持 8 种语言

@NFTMansa · X

Love seeing the builder community thrive! For anyone tackling group projects with AI, we built GroupGPT. It lets teams collab on AI prompts and custom agents in real time. Check it out:

@vitverb · X

hi :) One tap back to the work you meant to finish. No tasks to manage. Nothing to set up. Local-first

jackcollinshq · Product Hunt

YAGNI Proactive agent teams you manage like humans

@duke_can_c_u · X

Hi I’m the founder of a content collaboration platform for teams and creators, with focus on editorial workflows. Always looking to connect with people passionate about content, SaaS, and building great products.

@baptistedulac · X

time tracking for freelancers and agencies

@MarkZofMarkZ · X

- in process of updating it currently, making it better. How about you? What are you building?

@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

@KSertttttttt · X