New side project: I'm making WebBee 🙈
It is a conversational web-dev agent – one that doesn't burn the planet or steal other people's code. They can turn English language into structured English language. Add components, install packages, scaffold pages, run framework CLIs. All that without requiring a ton of RAM or scraping open source :)
WebBee is a little silly, but fully deterministic, and you can teach them routine tasks.
It doesn't use LLMs but a neural network for intent classification, based on supervised learning.
This is way less resource-wasting.
If something isn't clear, they ask back before doing stuff. For example:
User: I want to add a component.
🐝 what do you like the component to be named?
MCP tools are a bit tricky for webbee. This is especially the case for multi parameter tools.
But whenever webbee struggles how to use a tool, it asks the user how to do that, and learns it.
@lea @astraluma this sounds like the kind of NLP project that's seemed like a slam-dunk to me as all of the *gestures* craze unfolds. It's a powerful tool for human-interface boundaries and it's sad to see so attempts to take advantage of our ability to do that deterministically!
Anywhere that I can read more about the design, or still cooking?
A really challenging task is to figure out how to enable webbee to find a fitting mcp server tool on their own based on a specific task. MCP servers expose tools along with a text description of what the thing does. This is easy for an LLM to understand, but hard for WebBee.
It didn't read the whole wikipedia. So, it doesn't really "understand", it matches trigram tokens, which works surprisingly well 🐝
Lea Rosema
The Doctor
SnoopJ
Jared White (ResistanceNet ✊)