AI workflows don't seem to be suited to image-based environments like Smalltalk's, though.
Unless you give them a tool which lets them execute arbitrary code in the running image.
Or at least this works wonderfully in Clojure via the nREPL.
On the other hand, ai agent harnesses work a bit like image based system - think: claude --resume
Unless you give them a tool which lets them execute arbitrary code in the running image.
Or at least this works wonderfully in Clojure via the nREPL.
On the other hand, ai agent harnesses work a bit like image based system - think: claude --resume