Try the redesigned human-in-the-loop interaction flow — execution plan review, mid-task modification, and sign-in handoff.
Hi! This prototype was built directly in code using Claude Code. As a designer, I enjoy building products and polishing them. Every interaction, from the typing animations to the exact moment the split view slides in, was implemented and iterated by hand.
It took a bit longer than a static mockup, and I spent quite some time polishing it even though it's a prototype. I believe interaction design only truly comes alive when you can actually feel the timing. Building it live also surfaced many ideas that wireframes never could. You can see how some of these UI components evolved from this process on the Design Evolution page.
A quick note: if you run into any weird bugs, or if the simulated agent forgets its script and gets stuck, please bear with it — it's still just a prototype. Have fun playing around with it! 👾
What's in the Demo
Take your time with it. The typing animations are intentional and paced to feel like the agent is actually thinking.
Before the agent runs, it presents a step-by-step execution plan for your review. Approve it as-is, or modify individual steps before anything begins. This is the primary human-in-the-loop checkpoint.
Mid-task, the agent encounters a step requiring Google authentication. Rather than failing silently, it pauses, explains why it needs your help, and hands control back cleanly.
