921–930 of 1001 posts
I’m working on VineWall ( https://vinewallapp.com ), a network tunnel that helps you fight doomscrolling by making your internet slower when it detects you spent too much time scrolling. At this moment I’m working on improving the logic that decides when/how much to throttle the network.
It's a budgeting app I'm building for iOS and Android. It's an alternative to YNAB, Goodbudget, or Monarch, but the checking account and debit cards are built-in, so it avoids the unreliable syncing issues that make budgeting apps suck. It's named after the digital envelope system and helps you organize money into categories for bills, spending, savings, upcoming expenses, etc. Individual and joint accounts.
Right now I'm working on an upcoming paycheck detection system to automatically split your paycheck across your budgets.
Managing our above ground pool this summer and small hot tub in winter and continually asking "why isn't this easier" led to the development of Pool Pilot. Scan a test strip with your camera, water care recommendation checklist generates and you can order more supplies if needed easily from Amazon. Basically met my personal need and hoping it will help others too.
The fun technical bit: test strip chart colors can vary by manufacturer and even between production batches, but, the specific color chart that comes on a bottle should be accurate to those specific steps. Additionally, test strip colors are notoriously hard to match from photos. RGB comparison falls apart with lighting changes. After many interesting and considerations we calibrate of the specific test strip bottle and we use LAB color space and Anthropic's Claude vision model to read strips directly. This has worked exceptionally well in our testing and works with any brand;
The app also offers timers, history and much more. It has become a minor obsession.
React Native/Expo, Firebase backend, $10/year after 3 free tests (early tier pricing). Would love feedback from any fellow pool or hot tub owners.
Today I released the community plugins for Voiden.
This is a big one because one of the things I dont want is the API tool to become bloated with new features - so I want to allow anyone to build plugins to grow the tool.
I got laid off a while ago and I’m privileged enough to take time to reconsider what I want to do. I’ve been learning how to sketch which supports my bigger passion- printmaking. I’ve primarily been doing linocut which is carving negative space into linoleum, inking it up, and printing it on paper. I’ve got a membership at a local atelier and have branched out into drypoint, kitchen lithography, and what I guess is c…
I'll have to investigate LEGOpress.
Our thesis is that a lot of Data Engineering practiced today is non-differentiated across companies and they'd rather spend that time on differentiated tasks. What if we can abstract away a lot of the tedious parts of DE work and let companies focus on just the data they want to store, and the questions they have on their data?
So today, we have an MVP that manages the compute, storage, lineage, versioning and pipeline building for datasets. Would LOVE to get feedback on this or your early thoughts!
I think a lot of people have projects like this going at the moment, but I'm working on a deterministic (i.e. code / data persistence) layer that sits between agents and helps orchestrate their work. Basically an API wrapping a cyclic graph where rules govern the state transitions / graph traversal (i.e. rules around handing off work between agents and the associated review, rollback and human intervention escalation…
Five months into building product analytics for conversational AI. Started by targeting vibe coding tools like Lovable but realized most of them don't care about user experience yet. With monthly churn over 50%, they focus on acquisition, not retention. Now shifting to established SaaS companies adding AI assistants to their existing products. Some of them literally have people reading chats full time, so they actual…
Established companies adding AI assistants is interesting because they already have baseline metrics to compare against. They know what good user experience looks like in their domain, so when the AI chat experience is terrible, it's obvious.
What's the biggest gap you're seeing between what these companies think they need to measure vs what actually matters for AI chat quality?
Still working on Overtone, a tool that allows one to visualize the relationships documented in MusicBrainz, probably the largest crowdsourced music DB in existence, using graphs. You can right-click anything to expand into its subgraph. It already runs pretty smoothly. Next steps are adding a way to make playlists and listen to them right there, without leaving the page. Check it out and let me know what you think! A…