What "agentic AI" actually ships in the wild.
Most of the production agent work I do isn't really about the agent. It's about the harness — the boring stuff around the model that makes a thousand customer-shaped failures recoverable, observable, and cheap.
A model that's 95% correct in a notebook becomes 0% deployable without a harness that can: time out a runaway tool call, retry an idempotent step, fan out work, surface intermediate state to a human, and roll back side effects when the plan changes mid-flight.
The interesting research question of 2026 isn't "can the model do it." It's "what's the smallest, most legible scaffolding under which the model can do it the same way twice."
source & further reading
harshalgajjar.com — original article
Is wanting is the last thing for humanity to do
The blank box problem
The phone is the terminal now