Learn AI and agentic DevOps
Where agents genuinely help, where they are oversold, and how to introduce them safely.
What does the Learn AI and agentic DevOps track cover?
This track covers what distinguishes agentic systems from automation and AIOps, which operational tasks they suit, how to judge their output, and a sequence for adopting them without creating a new class of incident.
The route, in order
The distinction from scripted automation and AIOps, and why legibility is the safety property.
Fit predicted by how cheaply a wrong answer can be detected.
Compressing the phase that consumes most incident time.
When determinism is worth more, and the agent-decides-script-executes pattern.
Pattern extraction, novelty and rate detection.
Seasonal baselines and why feedback should teach rather than suppress.
What you should be able to do afterwards
- Distinguish agentic systems from automation and from AIOps
- Judge whether a task suits an agent by how cheaply its output can be verified
- Design an adoption sequence that starts read-only and expands on evidence
- Recognise when a deterministic script is the better answer
Questions about this track
No. The track is about operational judgement (where these systems help, how to verify their output and how to bound their access), rather than about model internals.
The principles are general. DevOpsArk is used as a worked example of grounding, execution traces and approval gates, because those are the properties the material argues for.
Where to go next
Learn DevOps
Start here if DevOps is a word you use more confidently than you would like.
Learn Kubernetes
For people who have to run Kubernetes, not just deploy to it.
Learn observability
What each signal is for, how to make them join, and how to keep the bill sane.
Learn DevSecOps
The controls that reduce the most risk, in the order worth doing them.
Learn cloud operations
Running infrastructure across providers without three of everything.
See it working rather than reading about it
Connect a cluster read-only during a demo call and look at the concepts in your own environment.