Zendesk for StartupsUp to 2 years free for startups + AI Agents & Copilot
Promoted
Yansu
AI that learns how you work and turns it into software
704 followers
AI that learns how you work and turns it into software
704 followers
Yanshu learns from the work you already do. It spots repeated tasks across files, messages, and workflows, then turns the best patterns into apps and automations. No process mapping or blank canvas—just the routines worth systemizing. Use it to automate recurring work, build lightweight internal tools, and speed up daily ops without writing code.
Naise AI
Turning repetitive routines into software automatically is a massive leap from building workflows from scratch on a blank canvas. One critical question though: how does Yanshu distinguish between a 'good' repetitive routine worth systematizing, and a repetitive 'bad habit' or inefficient workaround that shouldn't be automated?
Tycoon AI
The first time I tried Yansu I was thinking it was another "describe what you want and we'll generate it" tool.
It's not — it works the other way around: the AI watches first, then offers. By the time you'd think to write a prompt, the crystal already exists.
That inversion is the real product.
Impressive automation depth! But third-party APIs are constantly changing, and the text formats used by users are unpredictable. How resilient are your agents to user interface/API changes in integrated tools such as Notion or HubSpot? Do they adapt automatically, or is the entire workflow interrupted until the person corrects the request?
@bozhao I like the idea of discovering workflows from what people already do instead of asking them to start with a blank automation canvas. Most users don’t know how to “design a workflow,” but they definitely know the repetitive work they keep doing every week.
Yansu
@alpertayfurr Exactly, we want to help everyone breaks down the barriers. We want to help the majority of users to cross the "chasm" and be a builder. Yansu is the guide that helps you.
@bozhao That makes a lot of sense. The “chasm” is usually not the user’s intent, it’s the translation layer between what they want and how a tool expects them to build it. Curious how you think about keeping that guidance simple without hiding too much control from advanced users.
Yansu
@alpertayfurr very much our intention.
DeckSpeed
Really like the positioning of Yansu as “serious coding” rather than just another AI code generation tool. In real-world software projects, the hard part is rarely just producing more code — it’s aligning intent, specs, edge cases, team knowledge, and long-term maintainability. The idea of combining spec-driven development, scenario simulation, human QA, and traceable code feels very relevant for teams building complex products. Excited to see more AI coding platforms move from vibe coding to reliable engineering outcomes. Congrats on the launch!
@hanzhizhang0405 Thank you — really appreciate this.
From a design perspective, that’s exactly what feels important to us: moving beyond “generate more code” toward clearer intent, better alignment, and a product experience teams can actually trust in real workflows.
DeckSpeed
@miltonheyan Thanks! 🙏 If you give it a spin, I'd love to know what the first crystal Yansu suggests for you turns out to be — sometimes the surprises are the best part.
Wow. this looks promising! i'm always wondering how i can automate tasks, but i have to do an audit manually and then write on clickup to create an automation. it would be great if there is a process that automatically spots tasks to automate!