Operations | Monitoring | ITSM | DevOps | Cloud

Recurring Office Hours with the AI SRE Agent Team Behind AURA

Building an agent and not sure how to approach something? Bring it. AURA office hours are recurring working sessions with the people who build it. The team has been talking to people trying out AURA and hearing the same good questions come up more than once. Office hours are the answer to that: a standing slot on a schedule, rather than one conversation at a time. The format is deliberately loose. Nobody is arriving with thirty slides to spend an hour talking at you. The session goes wherever the questions go.

When to Use Grafana Assistant vs. MCP vs. gcx: Part 3

When should you use gcx? If Grafana Assistant is the brain and Grafana MCP is the easy hand, gcx is the power hand. Built for AI agents working in the terminal, gcx gives them deep access across Grafana Cloud—so they can pull telemetry, verify code, automate workflows, and access places MCP doesn’t. Coding agents? gcx. Need the full Grafana Cloud surface? gcx. Automating in CI/CD? gcx. Here’s where it fits, and when to use it — explained by Nicole van der Hoeven.

Dataset Bias in Computer Vision: How to Audit Human Image Data

Dataset bias in computer vision cannot be evaluated from one demographic percentage. The distribution available to a model is shaped by where images came from, how subjects entered the collection, which examples were retained, how labels were defined, what visual conditions were represented and how evaluation data was constructed. A useful dataset bias audit therefore examines the complete data pipeline.

How AI Is Turning Job Search Into an End-to-End Digital Workflow

Job searching used to be a loose collection of tasks: a few bookmarked roles, a resume file named "final_FINAL," and a handful of half-finished applications spread across tabs. Now, it's starting to look more like an actual workflow-one with inputs, outputs, checkpoints, and iteration. That shift is partly driven by AI tools that help candidates move from "I should apply" to "application sent" with fewer dropped steps. Platforms like ResumeCoach are part of that wider trend: not just creating documents, but helping people build a repeatable process they can run again and again.

Vertical SaaS vs Horizontal SaaS: Which Model Works Best for Australian B2B Markets?

For Australian founders building a B2B SaaS product, choosing the right market can be as important as deciding what to build. A horizontal SaaS product serves businesses across different industries, while vertical SaaS focuses on one industry or clearly defined customer group. The difference affects product scope, customer acquisition, competition, and long-term growth. A broad market may offer more potential customers, but a focused market can make it easier to understand customer needs and build a product around a specific workflow.

Don't Break the Agent: Lessons in Token Optimization

This one is for the curious souls who wonder how somebody actually builds a harness optimizer — and, more to the point, how they know it works. When we launched JFrog Boost into public preview, we told the story of the bill that broke us and the 100 billion tokens we clawed back across JFrog R&D. What that post didn’t cover is the question that consumed most of our engineering time: how do you measure any of this?

You Aren't As Behind As You Think

If you look at the people posting to social media the most about AI, you’ll probably feel left behind. They’re running dozens or hundreds of agents and probably shipping more than you. But, they are not representative of the rest of the dev world. They are the 1% of the 1%. The thing that might be missed is that you reading their posts is probably separating you from a much larger cohort of devs that are still trying to figure out how to use AI effectively in their day to day work.

MCP Won't Replace Your Monitoring Tool

MCP is generating a lot of hype nowadays (but then again, almost anything that emerges in AI seems to attract hype). The anticipation around it is similar to the level of excitement that would break out if Apple were to finally introduce USB-C to iPhones. To be fair, though, some of that hype is warranted, considering the fact that MCP provides a standardized approach to connecting agents with third-party tools, which significantly simplifies this type of integration (hence the USB-C analogy).

How task containers give AI agents real infrastructure without idle cost

Infrastructure for AI agents usually forces a choice between two bad options. A sandbox is safe but blind, cut off from the data and services that would make the agent's output useful. Full access means paying to keep a container idle between runs, waiting on a prompt that might not arrive for hours. Task containers, which Upsun released on August 12, 2026, are built to avoid that choice. A task container is a single-purpose container defined in a project's.upsun/config.yaml file.

Why AURA Scratchpad Is Rad: Bound the AI SRE Agent Context Window

A big tool result does not have to be a big context cost. AURA moves it to disk and hands the model a pointer plus the tools to navigate what is there. A large MCP tool result can consume or overflow an agent's context window, and on a third-party server you do not control how much comes back. Scratchpad breaks the link between how big a tool result is and how much context it costs: the full output goes to disk, and only the slice the model asks for ever enters the window. Errors always pass through inline, so the model can react to them.