Operations | Monitoring | ITSM | DevOps | Cloud

cloudzero

Token budgets: capping AI agent and LLM spend

Aug 19, 2026 By Doug Bonderud In CloudZero
AI costs are changing. As noted by research from EY, outputs that cost just $0.04 in 2023 now cost $1.20, a 30x increase over just three years. It’s worth noting that task operations and complexity have also changed. In 2023, the process was simple. Users input a question, retrieval engines found relevant data, and AI models returned a response. Today, many tasks are handled by orchestrated AI agents capable of much more complex reasoning and analysis.
Read Post

Why AI agents don't need infrastructure running 24/7

Aug 19, 2026 By Upsun In Upsun
AI agents don't need a server sitting there while they wait for the next prompt. They need infrastructure that shows up, does the job, and disappears. In this Product Highlights conversation, Nicolas Gommenginger, director of product at Upsun with more than four years leading the platform's core functionality, breaks down Upsun's newest primitive: task containers. His take: "What really triggered us to go ahead and implement it is the rise of AI agents, because tasks are something ideal for running them." We get into.
View Video
grafana

Knowledge Graph as context for LLMs: demonstrating decisive RCA and faster production performance

Aug 19, 2026 By Sarah Constant In Grafana
On the product team here at Grafana Labs, we consider AI agents our users, too. That’s why we set out to test how well agents can debug incidents across the full stack, and how much better they perform with Grafana Cloud’s Knowledge Graph vs. using raw telemetry alone. Our early results are promising. In one real incident we replayed 16 times each way, an agent with Knowledge Graph context found the correct root cause 15 times, compared with just once using raw telemetry alone.
Read Post
harness

Harness Announces Capabilities that Enable Security at Machine Speed | Harness Blog

Aug 19, 2026 By Rahul Sood In Harness
Vulnerabilities used to move at human speed. A researcher found one, disclosed it, and defenders had days - sometimes weeks - to respond before it was weaponized in the wild. That window is gone. According to the Edgescan 2026 Vulnerability Statistics Report, it still takes an average of 55 days to fix a vulnerability - but the Zero Day Clock shows attackers going from disclosure to first exploit in as little as 6 hours.
Read Post
Why Tracking AI Overviews Is a Data Pipeline Problem, Not a Marketing One

Why Tracking AI Overviews Is a Data Pipeline Problem, Not a Marketing One

Aug 19, 2026 By OpsMatters In OpsMatters
Something quietly moved onto the ops backlog over the past eighteen months. Executives began asking whether the company appears in AI-generated search answers, and the request landed with whoever owns data collection rather than with the people who own the question.
Read Post

Copyright © 2026 OpsMatters™. All rights reserved.