For a long time now, I have been asking agents for diagrams and little HTML pages constantly. They’re often much better than another few paragraphs of explanation. The problem is that the interfaces we use still treat them like tool calls/chat transcripts. A diagram appears in the transcript and starts scrolling away. An HTML explainer opens in a browser tab. The agent might have just spent ten minutes building me a much better representation of the system than prose could give me, but there’s nowhere for that representation to become part of the conversation. I can’t naturally point at one box and ask “why does this call this?”. I can’t put the implementation beside the diagram and ask the agent to keep them in sync. An hour later, when I need the same explanation again, I’m often back to asking for another one. The better the artifacts get, the stranger this feels. If diagrams, pages, code, traces and notes are going to become the things I use to understand an agent’s work, they need somewhere to live: somewhere both of us can see, change, and point at. They ARE the topic of discussion. And this philosophy should not only apply for HTML explainers or mermaid diagrams, but everything a human+agent pair needs. Every file in the git dir with lsp code nav, browsers that the agent is using for testing, browsers I am using to check linear, and anything else. That’s what I built easl for, and its grown WAY past that. Now, I keep everything I work on in boards, and have live updating scripts pulling from gh/linear/etc and updating a kanban-style board, I can refrence any ticket, PR, decision with a click, and ask about it. Moving from chat transcripts to infinite board of artifacts allows us humans to keep our context as state on the screen, and not text thats scrolling away from us every second, in 10 different sidebar threads

easl

The scriptable infinite board for human<->agent interaction

The scriptable infinite board for human<->agent interaction