A coding agent generates a Python service. It works locally. It passes tests. Someone says "deploy it." Now what?
Does anyone know if it is stateful or stateless? What the DNS requirements are? Whether it needs cert-manager configured? How it rolls back if the deploy fails at 2 AM? The coding agent does not know. The engineer who prompted it might not either. And the SRE team — if there even is one — is already buried under the last three services that got thrown over the wall.
Speed of creation without speed of operationalization just means you accumulate technical debt faster. Kubernetes won — it is the de facto orchestration layer for production workloads. But Kubernetes expertise is thinning out across the mid-market at the exact moment complexity is increasing. Clusters are running, workloads are deployed, and when something goes wrong nobody has the institutional knowledge to diagnose it.
This is exactly the kind of problem agents should solve, not by replacing Kubernetes expertise but by encoding it. A control plane that provisions clusters across AWS, GCP, and Azure. That configures cert-manager and external-dns. That investigates a failing pod and determines whether the problem is in the app or the cluster. That writes the postmortem without a human spending four hours in dashboards.
The industry is pouring resources into making code generation faster. Fine. But the constraint on enterprise software delivery was never "we cannot write code fast enough." I've made the case elsewhere that automating a business process is software engineering, not vendor selection — and that means everything after the code exists is the work. Build the operational agents alongside the coding ones, or learn the hard way.
Sources
Related Essays
The Operationalization Gap: Where AI Demos Go to Die
The gap between an AI demo and an AI deployment is called software engineering. Most organizations are not equipped to close it, and that is where all the value lives.
Start With the Mirror, Not the Model
Pick one process your business actually runs. Record people doing it. Now you have something an agent can act on — and a foundation for measuring whether it works.
The Demo Is Not the Deployment
A French CTO with twelve Claude Max seats can ship from his laptop and watch his product team file tickets and wait. That gap is the real problem.
Key takeaways
- Speed of generation without speed of operationalization just means you accumulate technical debt faster.
- Kubernetes won, but Kubernetes expertise is thinning out across the mid-market exactly when complexity is increasing.
- Agents should encode operational expertise, not replace it — provisioning, cert-manager, rollbacks, and postmortems are the next frontier.
FAQ
What is the production strategy gap?
It is the moment after a coding agent finishes when nobody knows whether the new service is stateful, what its DNS requirements are, how it rolls back, or who owns it at 2 AM. The code exists. Production is still a mystery.
Should agents replace SREs?
No. They should encode SRE knowledge so a thinning bench of Kubernetes experts can scale across more services. The control plane that provisions, configures, and investigates is the missing piece.