Nice one. Mermaid validation is a huge issue given how mermaid.js is architected.
I built a mermaid generation harness last year and even the best model at it (Claude Sonnet 3.7 at the time; 4o was okay, Gemini struggled) only produced valid mermaid ~95% of the time. That failure rate adds up quickly. Had to detect errors client-side and trigger retries to keep server load reasonable.
Having a lightweight parser with auto-fix like this back then would have simplified the flow quite a bit.
Agreed, nice idea in theory. But as a codebase owner I’d rather build tailored markdown files with a CLI agent to publish as my docs. And as a codebase consumer I probably only care about a codebase if I’m modifying or running it, which means a CLI agent makes the most sense and I can ask questions/generate .md files as we go.
Spotify's Soundtrap claims to have live collaboration, haven't tested it though so I don't know if it's actually realtime or just a step in that direction.
Garmin has an active/outdoorsy slant but out of the big smartwatch players they seem to fill that hole best, a good amount of their models emphasize button navigation and the touchscreen is optional.
I built a mermaid generation harness last year and even the best model at it (Claude Sonnet 3.7 at the time; 4o was okay, Gemini struggled) only produced valid mermaid ~95% of the time. That failure rate adds up quickly. Had to detect errors client-side and trigger retries to keep server load reasonable.
Having a lightweight parser with auto-fix like this back then would have simplified the flow quite a bit.