Practical AI · Thursday, October 29, 2026
Chris Schenkel and Andrew Dunlap from SEP presented a sense-making framework for software development teams utilizing AI, categorized by agent autonomy from individual human-in-the-loop modes to full dark factory autonomy. They emphasized that token budgets, domain knowledge, and verifiability constrain which mode fits best.
“There's six constraints that we found all our teams want to review when they're pinpointing the forces acting on them.”
“There's four modes that we commonly find our teams operating in... spread out by a level of agent autonomy.”