1
We’ve built vykee.co as an onboarding tool. Idea = make SaaS interfaces easier to understand, by hiding advanced features for new users.
One of the main features is a tagging system that allows the SaaS company to tag elements, and group multiple elements into one feature. So basically we have an UI layer of the frontend (complete with unique identifiers and annotations for every element and feature).
I think this UI layer could be pretty useful to LLMs: If we put all that UI info in a simple llms.md file (like a robots.txt but for LLMs), they could understand the interface much better than having to parse the hmtl or rely on screenshots.
Now – this would only be helpful for browser-based agents.
We’ve had this discussion where some argue it would make much more sense to bet on MCP instead of browser-based agents, since it’s the standard and more widely adopted. The idea being to set up an MCP and connect it to the tagged frontend elements.
Do you think it still makes sense to bet on browser-based agents?
Thanks!
Hypothesis: Simple software is better for user activation.
The problem: As time goes on, any software becomes more cluttered with features, which make it less simple and therefore harder for new users to use. They try the software, they don't get it, they leave. -> The company loses out on money.
The solution: Most SaaS companies try to counteract this by using ……… PRODUCT TOURS. Product tours make the problem even worse, by further cluttering the software more and hence make it even harder to understand. Also, many users just skip them and get annoyed.
The REAL solution: Software should be simple in the beginning – only basic functionality. Advanced and non-essential features should be hidden for new users (with the option to show all features of course). Advanced features should be revealed when a user is "ready" to use them.
Am I missing something?