Operations | Monitoring | ITSM | DevOps | Cloud

tigera

Beyond the Prompt: AI Agent Design Patterns and the New Governance Gap

Apr 15, 2026 By Alister Baroi In Tigera
If you are treating Large Language Models (LLMs) like simple question-and-answer machines, you are leaving their most transformative potential on the table. The industry has officially shifted from zero-shot prompting to structured AI agent design patterns and agentic workflows where AI iteratively reasons, uses external tools, and collaborates to solve complex engineering problems.
Read Post

AI vs. Hype: Redefining Engineering Excellence with Ron Miller

Apr 15, 2026 By Harness In Harness
In this episode of "ShipTalk: Engineering Excellence," host Thomas Dockstader sits down with Ron Miller, editor at Fast Forward, to discuss the real-world impact of AI on software development. They dive deep into the maturity of AI-driven code, the rise of the "citizen developer," and why traditional writing and communication skills are becoming the new must-have for modern engineers.
View Video

Building Agent-Friendly CLIs - What we learned at Checkly

Apr 15, 2026 By Checkly In Checkly
Building Agent-Friendly CLIs: Why Your AI Agent Already Loves the Checkly CLI Stefan explains why products, docs, and CLIs must be AI-ready as coding agents rapidly become primary users of the Checkly CLI. He outlines key CLI features for agent workflows: Stefan demos how an agent initializes project-tailored Checkly setup from scratch without any human intervention and also shows how agents can entirely automate the incident life cylce from resolution to status page communication.
View Video
How AI-Powered Phishing Is Changing What 'Suspicious Email' Looks Like

How AI-Powered Phishing Is Changing What 'Suspicious Email' Looks Like

Apr 15, 2026 By OpsMatters In OpsMatters
For years, spotting a phishing email was almost a checklist exercise. Look for typos, watch for broken grammar, be suspicious of generic greetings like "Dear user," and check if the sender's address looks strange. That mental model worked because phishing emails actually looked bad. Which is no longer true. With the rise of AI, attackers can generate emails that are grammatically perfect, context-aware, and indistinguishable from legitimate business communication. The obvious red flags are gone. What used to look suspicious now looks completely normal.
Read Post
datadog

Offline evaluation for AI agents: Best practices

Apr 14, 2026 By Tom Sobolik In Datadog
If you’re building LLM-powered applications and agents, you’ve probably asked yourself: “How do I know if my changes actually made things better?” You can tweak prompts, adjust temperature settings, or try different models, but it’s not always easy to validate whether version B’s response is better than version A’s. Most teams fly blind in preproduction and rely on user feedback to see how well their application works in the real world.
Read Post

Copyright © 2026 OpsMatters™. All rights reserved.