GitHub’s Wake-Up Call & the Rise of DevOps AI Agents - Issue 8
> _ -
Hey Everyone👋
This week in VibeOps: GitHub’s CEO warns engineers, F5 release an AI for DevOps tool, and the future of DevOps looks more agentic than ever
We have a lot prepared for you, so grab your coffee and let’s see what the AI agents are up to this week.
The CEO of Github is telling engineers to embrase ai or get out
GitHub CEO Thomas Dohmke says engineers must embrace AI or risk falling behind. With tools like Copilot automating up to 90% of coding in the coming years, the role is shifting from writing code to guiding AI and focusing on higher-level problem-solving.
F5 Launches AI Assistant for DevOps
F5 has launched a new AI Assistant that helps DevOps, SecOps, and NetOps teams automate tasks using natural language. Integrated into BIG-IP, NGINX One, and Distributed Cloud, it can even generate and optimize iRules on the fly which streamline complex configurations and increase efficiency
🔗 F5.com
Upcoming Events
Stakpak Ship It
Missed our last Stakpak Ship It? You missed out on us:
Upgrading EKS with an AI Agent
But don’t worry, our next Stakpak Ship It session is around the corner
🗓️ Every Wednesday at 10:00 GMT-7 on Discord Live.
P.S.: Don’t forget your coffee
Learning Resources
Every week, we come across interesting blogs, papers, and tutorials that help us level up as a DevOps team. Here are some of the coolest ones we found this week. We hope they inspire you, too.
What is Agentic DevOps?
DevOps is changing fast. In this post, James Governor, Nicole Forsgren and Gene Kim break down how AI agents are now taking real actions in CI/CD pipelines not just giving suggestions.
They also explains why AIOps is being redefined, and how developers are shifting to Vibe Coding
🔗 The Blog
The Future of DevOps Automation
In this episode of Agentic DevOps, Bret shares his favorite AI terminal, and talks about prompt injection risks, and explores how containers, SWE Bench, and tools like Devstral are shaping AI-powered DevOps workflows.
CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering
CoE‑Ops introduces a novel approach to AIOps by coordinating multiple specialized LLM-based experts to answer DevOps related questions more accurately. Instead of relying on a single model, CoE‑Ops uses a task classifier to route queries to the most relevant expert agent, improving performance across areas like fault diagnosis, deployment, and anomaly detection. In tests on the DevOps EVAL benchmark, it outperformed existing models by up to 14%, showcasing how collaboration between AI agents can boost reliability in complex cloud operations.
A quick favor (helps a lot):
To make sure this doesn’t land in spam…
Reply to this email and just say: “Got it” or “Let’s gooo” or drop your favorite emoji.
That tiny reply tells your inbox you actually want this — and it tells me you’re real. btw, we read every single message.
One Last Thing
VibeOps is made by the community for the community, so reply to these emails with all your cool AI use cases for DevOps and any cool AI tools that you use, and we will feature them in our next issue
Written with 💚 (and a lot of synthetic caffeine) by the VibeOps team ☕🤖