AgenticOps · AIOps · Observability

Matheus Arrais

Worldwide Tech Leader, Cloud Operations & Principal Solutions Architect, AWS

Teaching cloud operations to run themselves, safely.

With 20 years in IT, I turn complex cloud ecosystems into resilient, self-healing environments. I lead AWS's worldwide Cloud Operations technical community — 2,200+ specialists designing operational solutions at scale — with deep expertise in AIOps, agentic operations, and modern observability.

I own the Cloud Operations track at AWS re:Invent, AWS Summits and AWS re:Inforce. I also run the AWS Cloud Operations Blog channel, which publishes 50+ posts a month from authors across AWS: 13,000+ posts to date and over 10 million unique views.

Matheus Arrais at AWS re:Invent
AWS re:Invent.
Now

What I'm working on.

Updated October 2026
My focus

Agentic operations, in two halves.

AI for Operations

Agents that run operations, inside guardrails.

  1. 01 · Detect

    Agents watch the signals and catch problems before customers do.

  2. 02 · Diagnose

    They connect related alarms and find the likely cause.

  3. 03 · Act

    Routine, reversible fixes run on their own: restart, scale out, roll back.

  4. 04 · Guardrails

    Risky changes escalate to a person, and autonomy grows as trust is earned.

Operations for AI

Running AI workloads in production with the same rigor.

  1. 01 · Observe

    Trace every model and agent call: latency, token usage, errors and cost.

  2. 02 · Evaluate

    Measure answer quality and drift, not just uptime.

  3. 03 · Guard

    Apply safety guardrails and keep an audit trail of what agents did.

  4. 04 · Optimize

    Keep cost and capacity predictable as usage grows.

See the AgenticOps Ladder →

Blog

From the blog.

All posts →
The numbers

Two decades, in four figures.

Full résumé: experience, writing, talks, credentials →
Contact

Building trustworthy autonomy? Let's talk.