Agile assumed all work is done by humans. Sprints, standups, retros, code review — every ceremony was designed around the pace of people coordinating with other people. That assumption held for twenty years. It doesn't hold anymore.

AI maturity is forcing a structural rethink of engineering organisations. Not a tooling upgrade — a rethink of who does what, who decides what, and how fast those decisions can travel. I started writing about this when I noticed that the teams adopting AI agents most aggressively were also the ones where coordination was breaking down fastest. Ceremonies built for human-speed iteration couldn't absorb machine-speed execution. The org chart hadn't changed, but the work inside it had changed completely.

This talk is the operating model that came out of that observation. It covers how product management changes when agents surface architectural trade-offs before sprint planning even starts — the PM doesn't disappear, the PM moves upstream toward intent. How team topology shifts from pipeline stages to autonomous cells that carry full context. How you codify security, cost, and capacity constraints so agents can move fast without humans becoming a bottleneck — or a rubber stamp.

The model draws on what I call the ISEE principles — Intent, Structure, Execution, Evidence — born from 28 years of engineering work and three years of advising engineering leaders on AI-driven development, from coding assistants to agentic platform engineering. You'll see what broke when organisations got the human-AI boundaries wrong, what they changed, and the specific patterns that held up across teams of five and teams of fifty.

You'll leave with a concrete way to evaluate your own org structure against the reality that AI doesn't just write code — it reshapes who decides what, and when they decide it.

Takeaways:
1. A decision-rights map for human-AI teams — a repeatable method to identify which decisions belong to humans, which to agents, and which need both, so you can redesign roles and reporting lines with intent, not
instinct.
2. How the PM, engineering, and platform roles actually shift — the PM doesn't disappear, the PM moves upstream. Engineers shift from execution to orchestration. Platform absorbs what three separate roles used to own.
You'll see where these transitions worked and where they created new friction.
3. The ISEE principles as an org-design diagnostic — Intent, Structure, Execution, Evidence as four questions to assess whether your organisation is set up for AI-native delivery or just bolting agents onto an Agile-era
org chart.