Yansu
AI that learns how you work and turns it into software
697 followers
AI that learns how you work and turns it into software
697 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.
Free Options
Launch Team
Render: Get up to $100K in startup creditsThe fastest way to deploy and scale apps and agents
Promoted
What happens when Yansu observes two competing intentions from the same user at different times of day—how does it resolve the conflict?
@andrew_paul11 that's a challenge very hard to solve. We will use the previous learning to resolve it. And sometime, it does get wrong. but during the daily dreaming, it will correct, learn, and reflect
How does Yansu handle scenarios where your observed behavior is inefficient, will it proactively suggest a better way or just replicate your existing patterns?
@fletcher_oliver It first replace, and then refine/readjust. The first version will replace, so even it is inefficient workflow, at lease you don't have to do it anymore. And then from learning your work, it will start refining it and share how and why with you before any actions.
Hand off automation sounds like a productivity superpower. can Yansu take over multi step tasks that span across three or four different software tools at once?
@dylan_russell Oh yesss. What's amazing is, it even understand your surroundings and make JIT adjustments
How does Yansu handle compliance in regulated industries where proactive software changes might violate audit trails or approval workflows?
@vespertine_dallarosa We always keep those in mind when we first started it.
1. All information are stored locally.
We proactively remove these informations (PII or other sensitive info).
We have a very comprehensive system that you can add non-tracking applications or period of time that stop observing at all.
This is interesting, but is there way to flag certain commands/actions to be executed only when I give confirmation? there is still a chance it can do mistake, right?
@ashishkingdom Yes, it can makes mistake. Just like a human can. And the best part is it learns from that. Also, you can always flag it before you give confirmation.
The correction flow matters a lot here because “AI inferred intent” should never become “AI quietly changed the wrong thing.”
@jamesmali absolutely, we ask before we build and we shares the intent behinds it.
Really interesting direction, especially the shift from “tools you configure” to “systems that interpret intent and act on it”. Curious how you’re thinking about the trust boundary in cases where the system proactively executes something the user didn’t explicitly initiate that’s usually where adoption either accelerates or breaks.
@new_user___1452026946a93788355af99 We always ask permission before building and share the intention from the start.