Operations | Monitoring | ITSM | DevOps | Cloud

AI agents are only as smart as the data you feed it

AI is only as useful as the context you give it. An autonomous observability agent can unlock serious value from your telemetry, but only when the foundation is right: good telemetry, a strong data layer, and efficient access to the data. Annie Freeman and Lewis Isaac had a lot to say about this at AWS Summit London this week! hashtag#Observability hashtag#AI hashtag#AWSSummitLondon hashtag#DevOps hashtag#OpenTelemetry.

Why Mandating AI Tools Backfires on Engineering Teams

Responsible AI adoption for engineering teams starts with culture, not compliance. In this GitKon talk, Rizel Scarlett (Tech Lead of Open Source DevRel at Block) shares how Block helped thousands of engineers actually want to use AI tools, including Goose, Cursor, Claude Code, and more, without mandates, vibe coding disasters, or security gaps.

Rootly's Dan Sadler: why AI coding tools are driving more incidents + why reliability is the product

Cortex co-founder and CTO Ganesh Datta sits down with Dan Sadler, VP of Engineering at Rootly. Dan explains how Rootly treats reliability as a product feature rather than just a technical metric, and why culture might be the most impactful element of building reliable systems.

Voices You Can't Trust: Securing K-12 Communications Against AI Deepfake Threats

It starts with a voice you recognize. A call from the superintendent asking for an urgent update. A voicemail from a principal requesting sensitive student information. A message that sounds authentic, because it is, at least on the surface. The tone, cadence, and even the subtle inflections are exactly right. But the request isn’t. AI-powered deepfakes are rapidly reshaping the threat landscape for K–12 schools, turning trusted communication channels into potential points of vulnerability.

Human First, AI Second: Cycle's Approach to AI Coding in 2026

It is easier than ever to launch a product from scratch. Today, AI can make your team of two feel like a team of ten almost overnight. Enterprises across the tech industry are completely restructuring engineering teams to double down on AI coding, often incentivizing engineers for the sheer amount of code they push. The AI revolution is incredible. So, you would be crazy not to hop on the vibe coding train right? Well it depends on what exactly you are building.

When agents orchestrate agents, who's watching?

You used to monitor services. Then you started monitoring AI calls inside services. Now your AI agent is spinning up other AI agents to complete tasks. Your old monitoring instincts need to evolve. This isn't hypothetical. Agentic architectures are already in production. Coding agents are calling search agents; orchestrators are spawning specialized sub-agents for retrieval, planning, and execution. Teams are shipping these systems faster than they're figuring out how to watch them.

What does using AI for post-mortems actually mean?

Everyone is using AI to help with post-mortems now. The pitch is obvious: post-mortems are time-consuming, the blank page is brutal, and AI is very good at producing structured, confident-sounding documents quickly. We're not here to push back on that. We've built AI into our own post-mortem experience, pulling your Slack thread, timeline, PRs, and custom fields together and giving your team a meaningful starting point in seconds. We think that's genuinely valuable, and the teams using it agree.

GPT Image 2 Brings Visual Work Closer

Most AI image tools are easy to praise in a vague way. They can generate striking pictures, imitate styles, and turn a short prompt into something that looks impressive enough to share. But that kind of praise has started to feel cheap. The image model market is crowded now, and "it makes beautiful images" is no longer a meaningful claim by itself.