Operations | Monitoring | ITSM | DevOps | Cloud
The Place Where Modern Operations & Technology Come Together
AI Powered MSPs: Faster Value, Bigger Returns
In a crowded MSP market, standing out takes more than great service. See how BigPanda customers are using AI-driven operations to differentiate their offerings, boost profitability, and maximize their ServiceNow investment.
From Keyword Search to Ask AI: How We Upgraded AppSignal's Docs Experience
Documentation search is often the last thing devs think about, until someone posts publicly that they couldn't find a basic answer, or your support queue fills up with things that are genuinely in the docs. We decided to get ahead of that. This is the story of how we went from a minimal keyword-only search on our docs to a conversational Ask AI experience.
Shipping trustworthy code with Chunk CLI
AI coding agents are fast. They generate functions, refactor modules, and wire up boilerplate faster than any human. What they don’t do by default is enforce the conventions a specific team has agreed on: the lint rules, the review patterns that senior engineers flag on every PR. A generated diff looks clean until someone runs CI or reads it carefully.
Sentry + Claude Agents: Automatic Bug Fixes from Root Cause to PR
Seer, Sentry's AI debugger, automatically analyzes your issues and finds the root cause. Now you can pass that analysis directly to a Claude agent - a managed agent session in the Claude Console at platform.claude.com. Once it's done, a link to the branch appears in Sentry so you can review and merge the PR. This video walks through how the integration works and how to set it up in under two minutes.
The Claude Bill is Too Damn High #speedscale #claude #aiagents #aicoding #devops #llms
Stop overpaying for AI reasoning by trading expensive GPU cycles for efficient, deterministic testing. This video explores how tools like linters and traffic replay can complement Claude, helping you fix bugs more accurately while cutting token usage by up to 50%. Visit: speedscale.com to learn more.
How is Agentic AI fundamentally different from earlier automation?
Autonomous operations has been the goal for years. But most “automation” never got us there—it just helped teams keep up. Now that’s changing. Agentic AI introduces a fundamentally different model:– Purpose-built agents, not static workflows– Real-time decisioning, not predefined rules– Collaboration across agents, not isolated tasks Instead of automating steps, agentic AI enables systems to **reason, adapt, and act**—at a speed and scale humans simply can’t match. That’s what turns autonomous operations from a long-standing ambition into something actually achievable.
How Diffusion Transformer Models Power Hyper-Realistic AI Avatar Videos
The AI avatar videos from a year ago still had a tell. The mouth movement was a little off, the facial expressions were a bit stiff. It was a quality that made it obvious that you were looking at a digital human and not a real one. The uncanny valley issue was not a small aesthetic problem, it was the only thing that stopped the practical adoption of anything other than novelty use cases.
Run Local LLMs on Mac to Cut Claude Costs
Part of the motivation for this post is how cloud API economics are shifting: Anthropic is moving large enterprise customers toward per-token, usage-based billing (unbundled from flat seat fees), which makes “always call the API” a moving cost line for teams at scale. A hybrid or local layer is one way to keep spend bounded while you still use premium models where they matter.
What Is AI Agent Observability? Why Cost Is The Signal You're Missing
Your LLM observability stack probably handles individual model calls well enough. Latency, token counts, error rates, maybe even evaluation scores....