The hardest part of agentic AI in 2026 isn't getting the agent to do the work. It's knowing when to override it. The four-level autonomy ladder, the five signals an agent is going off the rails, and a real example of catching one before it shipped a quietly broken auth flow.
A fractional engineering engagement starts with a codebase you've never seen. You have ninety minutes to form a useful POV before the kickoff call. The seven-step triage I run, the two questions I bring back to the founder, and how AI tooling has accelerated the process.
A walkthrough of how I run 4–7 agent sessions in parallel through a normal engineering day. Morning background tasks, mid-morning pair programming, afternoon reviews, end-of-day ops. The interaction modes that work, the handoff protocol, and the trap that makes most agent workflows produce slop.
Most 'we delivered late' stories trace to one decision: the team scoped the first slice too big. The vertical-cut rule, the deploy-by-Friday filter, the pattern that breaks the heuristic, and a real before-and-after example.
Production AI, startup security, Elixir, and the engineering-leadership calls that come with them. One email a week with what I published, nothing else. Unsubscribe in one click.
Cookies & analytics
I use Google Analytics to see which posts get read and how people find this site,
nothing more. No ads, no third-party sharing. See the
privacy policy
for details, or change your mind any time via Cookie preferences
in the footer.