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.
Hi everyone. This is Bo. One of the builder of Yansu.
We set out a vision of bespoke software at scale. All of the software in the future will tailored to your exact needs and drifting with you as you change and grow.
However, we see two challenges. First, not everyone has the time, energy or intention to build for themselves. Second, for those building they have to tinkering with it a lot to build the right thing and continue managing it.
We solve this with two new ideas:
Switching the relationship between software and human/user. Software is the proactive actor and human/user is the reactive one. Software is proactively and automatically created for you. You don’t have to wage any energy on it.
Observe your screens and summarize and understand your intentions without you explicitly telling the AI. This solves the drift and tinkering problem.
When these two ideas comes together, you have an app that is:
Continuously understand, build and refine knowledge about you and the entities that relate to you.
From observation and understanding it proactively builds the right app for your exact needs:
Take over your current task and automatically complete it via Hand-Off
Understand your daily patterns and generate scheduled automations.
Understand your unique challenges and options and create bespoke desktop apps just for you.
We believe these capabilities not just right one for future and also extremely powerful today. Hand-off feature has many WOW moments for me and I am still blowing away by it.
Give it a try and let us what do you think. We are here to answer questions and discuss about roadmap and the thinking behind it.
Have fun!
Bo
PS. Since many asked about privacy. I want to share how we think about it. Trust and Privacy is the most important element for us. It is the value we do not trade off. How does it reflect in the app: 1. All information are stored locally 2. All OCR/audio are processed locally 3. We proactively remove ANY PII information 4. Users have full control of what app can be observed 5. Users have quick action can stop it anytime
The “software drifts with you” framing is strong, but it also raises a governance question for teams. For solo users, local observation + hand-off makes sense; for businesses, I’d want a clear audit trail of what was observed, what automation was generated, what action was suggested, and whether a human approved it. Is Yansu thinking about a team/admin mode where proactive automation can be reviewed before it becomes part of the workflow?
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?
What’s the most surprising entity relationship Yansu has discovered about a beta user that the user themselves hadn’t explicitly realized?
How do you think about pricing for something that builds unique software per user—subscription, usage-based, or outcome-based?
I like that this starts from observing real workflows instead of asking users to manually design automations from scratch. Turning repeated work patterns into lightweight internal tools feels much more natural for teams that want automation without spending weeks setting up complex systems.
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!
When Yansu detects a repeated pattern, does it surface that to the user for confirmation before building the automation, or does it make judgment calls autonomously about what's worth systemizing?
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?
Congratulations on your launch!
Had a question: I do have a memory.md in Claude and I have configured such that Claude will keep adding new learnings into that file and that is messy. Because Claude decides what to store into that memory over time, and it ends up storing a lot of fluff.
Is Yansu sort of an "Obsidian" + "memory.md" which automatically updates over time?
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.
Yansu watching how you work and building the automation before you ask is a fundamentally different take on AI productivity. I've seen too many AI assistant tools that just surface a chat box. We've been building in the customer success for ops-heavy SaaS teams space, and Yansu touches on something we think about a lot. How long does it typically take before Yansu starts producing something useful?
@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.
Congrats on launching. What tasks can it automate... marketing, dev or more? Is there a landing page I can see the most common use cases?
The correction flow matters a lot here because “AI inferred intent” should never become “AI quietly changed the wrong thing.”
Does it have a library of public workflows for common tasks? A marketplace like n8N where someone can create a workflow, list it publicly and then monetize it.
How do you avoid the “filter bubble” problem where Yansu only reinforces your current habits instead of exposing you to better unknown workflows?
About Yansu on Product Hunt
“AI that learns how you work and turns it into software”
Yansu launched on Product Hunt on May 25th, 2026 and earned 344 upvotes and 96 comments, earning #3 Product of the Day. 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.
Yansu was featured in Productivity (652.8k followers), Artificial Intelligence (469.8k followers) and Maker Tools (2.8k followers) on Product Hunt. Together, these topics include over 235.2k products, making this a competitive space to launch in.
Who hunted Yansu?
Yansu was hunted by Justin Jincaid. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Yansu stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Justin Jincaid
Hi everyone. This is Bo. One of the builder of Yansu.
We set out a vision of bespoke software at scale. All of the software in the future will tailored to your exact needs and drifting with you as you change and grow.
However, we see two challenges. First, not everyone has the time, energy or intention to build for themselves. Second, for those building they have to tinkering with it a lot to build the right thing and continue managing it.
We solve this with two new ideas:
Switching the relationship between software and human/user. Software is the proactive actor and human/user is the reactive one. Software is proactively and automatically created for you. You don’t have to wage any energy on it.
Observe your screens and summarize and understand your intentions without you explicitly telling the AI. This solves the drift and tinkering problem.
When these two ideas comes together, you have an app that is:
Continuously understand, build and refine knowledge about you and the entities that relate to you.
From observation and understanding it proactively builds the right app for your exact needs:
Take over your current task and automatically complete it via Hand-Off
Understand your daily patterns and generate scheduled automations.
Understand your unique challenges and options and create bespoke desktop apps just for you.
We believe these capabilities not just right one for future and also extremely powerful today. Hand-off feature has many WOW moments for me and I am still blowing away by it.
Give it a try and let us what do you think. We are here to answer questions and discuss about roadmap and the thinking behind it.
Have fun!
Bo
PS. Since many asked about privacy. I want to share how we think about it.
Trust and Privacy is the most important element for us. It is the value we do not trade off.
How does it reflect in the app:
1. All information are stored locally
2. All OCR/audio are processed locally
3. We proactively remove ANY PII information
4. Users have full control of what app can be observed
5. Users have quick action can stop it anytime