
Piyaz · Where people and agents share one understanding
让团队和代码代理在任务计划和依赖关系上保持一致。
mrsuit · HN
Piyaz – keep your team and agents aligned as software projects grow
完整作品展
技术栈
60 projects

让团队和代码代理在任务计划和依赖关系上保持一致。
mrsuit · HN
Piyaz – keep your team and agents aligned as software projects grow

将您的文档转化为AI知识库,快速生成带来源的答案。
@tim_edgert · X
Launched Echo — an AI tool that turns your agency's scattered docs into instant, cited answers

评估AI系统是否符合负责任和道德AI实践。
@TheWhiz351 · X
I built two versions of the same responsible AI app using different vibe-coding platforms. Perplexity Computer: Base44: Try both. Which has the better design and user experience? #VibeCoding #ResponsibleAI

文档解析 API,准确提取表格、公式和结构化数据给 AI 代理。
g418572664 · V2EX
做了一个文档解析与记忆工具,专门辅助给传统行业做 AI 落地的老哥 现在 AI+的工作还挺常见的,就像大佬们说的,“所有行业的产品可能都会用 AI 重新做一遍”。最常见的就是各种 agent ,说要用 AI 赋能传统行业啥的,代替人类专家去处理海量的复杂资料、进行深度分析并做出决策。 举个例子,金融行业的“智能审计与尽调 Agent”。 过去,银行或投资机构想要给一家企业贷款或投资,需要人类审计师去读几十份、每份几百页的招股书和财务报表。现在虽然有了 AI ,但把文件一股脑全丢给它是不现实的,且不说烧 token 的问题,这些文档里有无数的跨行、跨列单元格表格,普通工具一拉,表格数据全串行了。如果 AI 把“第一季度利润”和“第二季度支出”的信息碎在一块,那得出的财务分析就完蛋了。 所以,现在要真想开发出一个能干活,还确保正确率的 agent ,就需要一个专业的、AI-native 的解析工具,把复杂的表结构和章节层级完整还原出来。我做的工具 Knowhere 就是干这个的: https://knowhereto.ai/?utm_source=v2ex 它能把复


协作平台,初创公司可在其中建立合作伙伴关系,自动分割收益
@RealPasternak · X
Tight on cash? Use rev-share collaborations to get what u need to scale instead of having to pay upfront sets it up for u automatically

RESACH analyzes 10 years of scientific literature to surface high-impact research questions, limitations, and unexplored opportunities with evidence directly from papers.
@anishka_25 · X
Research shouldn't be difficult checkout !

通过AI聊天界面查询公司文档和内部指南。
@DD_Ferel · X
We built IntelliBase AI: a smart knowledge base that "learns" directly from your company's own documents, so HR & Ops teams can ask questions naturally instead of digging through files one by one. 🌐 Interested in trying it for your team? Comment or DM us

分享最高 20 GB 文件,采用零知识加密和自动链接过期。
@clickswave · X
vibe coded slop

在代码合并时强制执行策略并审计AI辅助的更改。
@Scyloq · X
Currently building SentrAI. The merge-time control plane for AI-assisted software development. Enforce policy, audit every AI-generated change. Just finished an interactive demo and would love your honest feedback. Built with @Lovable

RabbitHole:根据你的知识生成个性化学习指南,含测验、抽认卡和练习。
@CosmeValera · X
I just launched the beta and would love to hear your feedback! You can play around with it and create your own custom guides here: 🔗 Any RTs, replies, or feedback are hugely appreciated! 🤝 #buildinpublic #indiedev #SaaS #AIwrapper

探索按学习先决条件组织的Manthan概念卡片,无需登录。
mohith-sarma · HN
Manthan a MCP server to store Concept cards with prerequisite links