Thoughts, stories and ideas.
The teams moving fastest with AI are the ones who already had strong delivery discipline. The patterns map directly. If continuous delivery never took hold for your team, AI won't fix that. It'll make the gap visible faster.
Vibe coding, spec engineering, loops, graphs. The labels keep changing because the model keeps changing. Every practice you build to compensate for today's model has a half-life, and the model is what's setting the clock.
I've had versions of this conversation with founders, CTOs and engineering leaders every week this year. The three reasons they give for waiting are all real concerns — and all three are pointing at the wrong problem.
Engineers have been using code they didn't write for decades — NPM packages, Stack Overflow pastes, codegen they never read. Nobody called it slop. Then the author changed...
Six months into 2026, the difference between teams using AI effectively and teams still evaluating it isn't a head start anymore. It's a different way of working entirely. And the gap isn't just widening — teams are actively moving in opposite directions.
CVE volume is accelerating and most teams are running scripts that can't keep up. We used an agent to build a scanner that queries three databases, classifies and scores every CVE on actionability. The agent spent tokens once. The workflow runs every morning without it.
Infrastructure was the first use case we looked at with swamp. Then users started solving security, finops, and validation problems with the same model. By the fifth time, it was hard to treat it as a coincidence. We'd built an automation primitive, and infrastructure was just where we'd pointed it.
Most SRE work follows a pattern. An alert fires, you check the metrics, pull the logs, form a theory, fix it. Then you do the same thing next week. That sequence is a workflow. When agents can execute it and produce structured data at every step, the work changes shape.
Every IaC tool promised "any system." Few delivered once you tried to use it in your own business. Provider ecosystems were designed for humans who can fill in the gaps. Agent ecosystems need a different contract. That's what extensions are built for.
Every company has this person. The engineer who every production change flows through because they're the only one who knows the constraints. If you're thinking about putting AI agents anywhere near your infrastructure, encoding what that person knows is the first problem to solve.
The sovereign cloud movement is forcing a question the industry has been avoiding. When you have to move off a hyperscaler, the bottleneck isn't the new provider's APIs. It's how precisely you can express what you actually need. Intent is becoming the architecture that matters most.
AI agents are probabilistic. The same prompt doesn't always produce the same output. That's not a problem to avoid. It's a problem to engineer around. Typed schemas, validated execution, deterministic workflows. The agent reasons freely. The system keeps it honest.
High trust doesn't mean no guardrails. It means everyone understands the direction well enough to act independently within it. When you pair that with the right systems, every person on the team can advance the product every day.
Every codebase has the rearchitecture that never gets prioritised. We split ours into six parallel workstreams and shipped it in eight days, start to finish. The hard part wasn't speed. It was coordination.
When agents can build anything in an afternoon, the temptation is to build everything. The products that survive are the ones where someone had the discipline to say no.