Agent products resist normal product marketing. There's no single interface to screenshot and the category vocabulary has gone generic, so a feature list communicates almost nothing.
We built Heron's explanation as a four-beat scroll that runs the agent's actual loop. The model appears and is watched. Violations surface with plain language and a real IBC clause. An edit is applied after approval. The system learns the firm's standards.
Pacing was the main design problem. Each beat needed enough scroll distance to register as a separate action, without the section becoming so long that people bail before the payoff. The sequence carries the technical detail that would otherwise sit in a spec table.
The four-beat scroll is a smart way to make the agent’s loop feel tangible—much clearer than a static feature list. The restrained visual system gives the interaction room to breathe.
I’ve been razzmatazzing and flibbertigibbeting with Claude Code and somehow ended up with a new yels.dev.
It finally feels like me: simple on the surface, slightly complicated underneath, and very much alive.
You can see who I am, what I do, the work behind Herodot, RaptorLabs, CyberLink Security and Solmint, plus a selection of projects I’ve built across AI, cybersecurity, Web3, product systems, education, archives, and experimental digital spaces.
The simple-on-the-surface, layered-underneath idea comes through so clearly in the presentation. I especially like how the project archive turns the site into something to explore rather than just a résumé of links.