I joined Olalekan Elesin (HRS Group), Mallika Rao (Netflix), and Martin Reynolds (Harness) for an InfoQ Live panel moderated by Renato Losio. The conversation centered on how AI is changing DevOps and SRE practices — moving beyond reactive monitoring toward predictive, automated delivery and operations.
The real problem: human attention waste
The panel quickly aligned on what AI should actually solve in operations: reducing the cognitive load of triaging without context, filtering signal from noise, and cutting through alert fatigue. Before you automate remediation, the bigger win is helping humans make faster decisions. AI that summarizes, correlates, and explains is already transforming on-call workflows — and it does not require full autonomy to deliver value.
Trust before automation
A recurring theme was the trust gradient. You start with read-only AI that summarizes and recommends. Then you move to deterministic, well-scoped automations — the kind where the blast radius is known and rollback is trivial. Full autonomous remediation stays reserved for scenarios where you have high confidence and low irreversibility. The group was clear: explanation matters more than accuracy for building stakeholder trust. If the AI can show its reasoning, people will tolerate imperfection.
Context engineering as the new discipline
I made the case that context engineering — providing the right signals, documentation, and structured knowledge to AI systems — is becoming as important as the models themselves. With expanding token windows and tools like MCP servers, the bottleneck is not model capability but the quality of context you feed it. Good observability foundations (distributed tracing, solid documentation, knowledge management) become prerequisites, not nice-to-haves.
Where the human stays in the loop
The panel drew a clear line: decisions that affect customer experience, involve SLA implications, or are irreversible must retain human oversight. The opportunity is not replacing human judgment but compressing the time from alert to informed decision. AI handles the grunt work of correlation and hypothesis generation; humans own the business tradeoffs.