> How do you think about competing with ChatGPT Canvas or Anthropic's artifacts, when these are shareable, native experiences in their products where users already work?

The flexibility is amazing for static content and playing around with visuals, the experience is just more like a whiteboard than a dashboard. It's hard to do both well in the same place. For reporting I want live connections, consistent logic, the ability to trace provenance, and a more opinionated starting point for the UI.

We started with an extremely flexible surface but there are just a ton of things you don't want to leave up to the agent to implement and we gradually layered those in. It's no fun having to prompt the agent to expose a "view source" affordance, "run" button, or working data labels. But it's a lot of fun building whatever visualization you want and generating a dashboard without a billion clicks in some SQL-abstraction UI.

> Is a "dashboard" limited to analytics or are you trying to expand it to include written reports?

We weakly support written reports today (technically possible with markdown blocks in dashboards for commentary) but will do more to support them in the future for exactly the reasons you called out.

We actually built a more notebook-like artifact for this but cut it to focus on dashboards since they seemed to be a bigger pain point for users. One-off reports can be hit or miss with a chat or coding agent today but static reporting is at least supported with some effort. Live reporting with connection infrastructure, provenance, etc. is much harder to pull together.

Kevin Kelly is still writing through The Technium [0], which might scratch some of the itch but is more an island than a colony like Whole Earth was.

Time for a hippie futurist revival?

[0] https://kk.org/thetechnium/

Highly recommend spending some time in the Whole Earth publication archives if you haven't had the chance.