founder & ceo @cloudgluedev - building the video context layer for AI.
prev ML, infra, engineering @snap, @aws, @rbcborealis, @arizeai & math/physics @uoft
We just launched Tinycloud into public beta 🌥️
It’s an AI agent for video work. It sees everything in your videos (transcripts, audio, visual context, on-screen slides, speaker patterns, and more) so you can query and make artifacts from them.
Think Claude Code but for doing work across your videos.
Try it and show us what you create → https://t.co/dfKusQCKIY 🧵
Excited to be in San Jose this week for ACM @CAISconf ! I'll be presenting our recent work at the AgentSkills poster session:
📚Tool-Skills vs. Workflow-Skills: Routing and Composition in a Multimodal Agent Harness
🔗 https://t.co/ri5I2wwMKq
@vytalow@ycombinator@ParasmaAI you’re underselling the role your background, tenacity, and clarity of communication played here. those arguably mattered just as much as the idea itself, if not more. congrats!
I highly recommend ‘lean customer development’, when you’re further along than the mom test:
https://t.co/2mou7S8Rbj
It dives into solving the chicken & egg problem of: how you need customer validation to build, but sometimes you need a working thing to show customers before they can validate.
@praeclarumjj Thanks Jitesh. Yes, absolutely correct on temporal grounding. Getting that right is table stakes for video understanding, especially for reasoning on longer form video. Thanks for sharing your work, we’ll check it out!
Tinycloud is in public beta ☁️
it's an AI agent for video work. point it at your videos and it sees everything: transcripts, audio, visual context, slides, speaker patterns, all of it.
ask it anything. or tell it what to build.