amrangaye
Joined 17 years ago
Joined 17 years ago
I’ve done several projects that would take months to complete otherwise with “vibes coding”, including: an African fairy tale generator for my daughter, a farm management system for the ministry of agriculture in my country, a Gambian political comic strip creator, a system that generates ten minutes summary podcasts of all my country’s news etc. I’ve also had great success with clients - and got them to sign on much faster - by just putting together a quick demo now that I show them instead of sending a proposal and pitch deck describing what I’ll build for them. It makes them so much more excited and we can make changes almost in realtime.
I’ve noticed a lot in the industry and even on hn, that coders - especially long time ones - tend to “look down” on vibes coding, the same way they did with scripted languages back in the day, and I imagine the same way with compilers. I think this will generally fade out as it becomes industry standard, but in the meantime sometimes I see comments on hn that are so discouraging and cynical it makes me wonder if the person actually tried it out or had just pre judged it. I also think the phrase “vibe coding” is a terrible name, cause it makes it sound like a lazy way of doing things. It’s so much more than that, and lets you think and plan at the idea level. Things like planning your system before you ask it to implement also help a lot.
Which is what leads to my issue: cognitive overload, and very high context switching costs especially as I'm usually on multiple work and "hobby" projects at a time, with multiple projects spread across term tabs, IDEs and Claude remote on phone.
So I built a "Workshop" to tinker. It analyses all the projects I'm working on currently as git repos on disk, then builds project pages complete with summary and a full control and data planes including its own startup method, commits being made etc. It does some agent introspection so it's able to display all agents running on machine in unified view.
But the "killer" feature for me is the "Pulse" - this contains human readable summary of what's happening with each project and agent in real time. So one use case is an "overnight view" - I set up architecture and design, assign the agent a goal, then wake up next morning to quickly scroll through the results. It also lets you track changes happening in real time ("We finished adding an export function for receipts, containing your company logo and signature" to summarize a feature across 10 commits).
I also added other useful to me utils such as being able to append a ? To any command in its inbuilt terminal and it'll convert it from English to a cli command waiting for you to confirm, for example; a system load monitor; a network sniffer, sys admin tools etc. all written in Rust, which I've never written a line of :)
Will put it online but need to clean it up first it's very specific to my use cases so not sure it'll be useful to others.