In an agentic loop, the model can keep calling multiple tools for each specialized artifact (like how claude webapp renders HTML/SVG artifacts within a single turn). Models are already trained for this (tested this approach with qwen 3.5 27B and it was able to follow claude's lead from the previous turns).
I turned Markdown into a protocol for generative UI
21–30 of 72 posts
Re: I turned Markdown into a protocol for generative UI
#22The bots that read the instruction and yet add the emoji to the _beginning_ of the PR title though. Even bigger red flag I guess?
Re: I turned Markdown into a protocol for generative UI
#23Very cool. I'm imagining using this with Claude Code, allowing it to wire this up to MCP or to CLI commands somehow and using that whole system as an interactive dashboard for administering a kubernetes cluster or something like that - and the hypothetical first feature request is to be able to "freeze" one of these UI snippets and save it as some sort of a "view" that I can access later. Use case: it happens to build a particularly convenient way to do a bunch of calls to kubectl, parse results and present them in some interactive way - and I'd like to reuse that same widget later without explaining/iterating on it again.
Re: I turned Markdown into a protocol for generative UI
#24I quite like this! I've been incrementally building similar tooling for a project I've been working on, and I really appreciate the ideas here. I think the key decision for someone implementing a flexible UI system like this is the required level of expressiveness. To me, the chief problem with having agents build custom html pages (as another comment suggested) is far too unconstrained. I've been working with a syst…
Thanks! Really interesting to hear you're working on something similar.
You're right that the level of expressiveness is the key design decision. There's a real spectrum:
- pre-registered blocks (safe, predictable)
- code execution with a component library (middle ground)
- full arbitrary code (maximum flexibility).
My approach can slide along that spectrum: you could constrain the agent to only use a specific set of pre-imported components rather than writing arbitrary JSX. The mount() primitive and data flow patterns still work the same way, you just limit what the LLM is allowed to render.
Would love to hear what you learn if you explore it!
Re: I turned Markdown into a protocol for generative UI
#25would be nice if it wasnt just ui but other form like voice narration, sounds ect
Re: I turned Markdown into a protocol for generative UI
#26Very cool. I'm imagining using this with Claude Code, allowing it to wire this up to MCP or to CLI commands somehow and using that whole system as an interactive dashboard for administering a kubernetes cluster or something like that - and the hypothetical first feature request is to be able to "freeze" one of these UI snippets and save it as some sort of a "view" that I can access later. Use case: it happens to buil…
Exactly this!
Right now this uses React for Web but could also see it in the terminal via Ink.
And I love the "freeze" idea — maybe then you could even share the mini app.
Re: I turned Markdown into a protocol for generative UI
#27I quite like this! I've been incrementally building similar tooling for a project I've been working on, and I really appreciate the ideas here. I think the key decision for someone implementing a flexible UI system like this is the required level of expressiveness. To me, the chief problem with having agents build custom html pages (as another comment suggested) is far too unconstrained. I've been working with a syst…
Thanks! Really interesting to hear you're working on something similar. You're right that the level of expressiveness is the key design decision. There's a real spectrum: - pre-registered blocks (safe, predictable) - code execution with a component library (middle ground) - full arbitrary code (maximum flexibility). My approach can slide along that spectrum: you could constrain the agent to only use a specific set of…
Will do! I'm using a JSON DSL currently, I wonder if there's a best choice for format that is both at the correct level of expressiveness and also easy enough for the LLM to generate in a valid way. I do think markdown has advantage of being very trivial for LLMs, but my current JSON blocks strategy might be better for more complex data.... will play around.
Re: I turned Markdown into a protocol for generative UI
#28I see potential to take over Notion's / Obsidian's business here. Imagine highly customizable notebooks people can generate on the fly with the right kind of UI they need. Compared to fixed blocks in Notion
Re: I turned Markdown into a protocol for generative UI
#29The streamed execution idea is novel to me. Not sure what’s it significance ?
I have been working on something with a similar goal: