between today and yesterday, we launched two amazing new capabilities: Gemini 3.8 Flash and Agentic Video Understanding and they have been so much fun to build with.
to test their limits, I built a retro Windows 98-themed workstation where you can drop in any YouTube URL of full 2-hour soccer matches 💾 ⚽(or any sports broadcast) & ask super detailed questions like "show me all the 🟨 yellow cards & bookings"
⚡ Agentic Video Understanding autonomously navigates across the 120-minute video timeline (no giant downloads or blind frame sampling)
🔍 dynamically zooms into candidate segments to detect referee whistles, tackles & card gestures
📍 isolates every card with exact sub-second timestamps & 2D pitch coordinates
🎬 pops out a tactical ledger where clicking any row instantly seeks and plays live!
no manual scrubbing. pure interactive video intelligence.