Operations | Monitoring | ITSM | DevOps | Cloud

AI Reliability, Part 2: When the Datacenter Becomes the Bottleneck

In Part 1, we talked about all the hidden complexity inside AI systems: the pipelines, GPUs, embeddings, vector databases, orchestration layers, and everything else that quietly determines how reliable an AI-first product really is. But all of that software still rests on something far less glamorous: the physical infrastructure underneath it.

How to use AI to analyze and visualize CAN data with Grafana Assistant

Note: A version of this post originally appeared on the CSS Electronics blog. Martin Falch, co-owner and head of sales and marketing at CSS Electronics, is an expert on CAN bus data. Martin works closely with end users, typically OEM engineers, across diverse industries, including automotive, maritime, and industrial. He is passionate about data visualization and AI—and he’s been working extensively with Grafana Assistant.

Using AI + Rollbar's Session Replay to Understand Complex Errors

Front‑end bugs are notoriously hard to reproduce. By the time an error shows up in your monitoring tool, the most important context is already gone: *what the user actually did*. By letting an AI agent like Copilot analyze Rollbar's session replay data directly, teams can move from *“something broke”* to *“here’s exactly why it broke”* in minutes, not hours.

Using AI + Rollbar's Session Replay to Understand Complex Errors

Front‑end bugs are notoriously hard to reproduce. By the time an error shows up in your monitoring tool, the most important context is already gone: what the user actually did. Session replay helps—but only if someone has the time and patience to scrub through recordings, correlate events, and form a hypothesis. That’s where Rollbar’s MCP server, paired with an AI agent like Github Copilot, changes the game.

Agentic AI demands a new data architecture #ai #telemetry

Clint Sharp explains why traditional schema-on-read systems cannot handle the query loads of the future. Agentic telemetry requires a 360-degree view, but structuring data only when you read it is too slow for AI-driven workloads. The solution is using LLMs to drive the cost of building parsers to near zero. Tools like Copilot Editor allow teams to map data to OCSF instantly, effectively building factories of parsers to handle the scale of agentic AI.

A better way to monitor your AI agents in .NET apps

We launched agent monitoring earlier this year, allowing our users to instrument LLM usage and tool calls in their applications. However, we only had Agent Monitoring support for Python and JavaScript. We’ve been working on creating an Agent Monitoring SDK for.NET — specifically for Microsoft.Extensions.AI.Abstractions.

This Month in Datadog - December 2025

For our last episode of 2025, we’re focusing on Datadog releases announced at AWS re:Invent. Join Jeremy to see how you can manage logs at petabyte scale in your infrastructure, eliminate unneeded costs in Amazon S3 buckets, build agentic workflows, and detect credential leaks. Later in the episode, Scott spotlights how you can connect your AI agents to Datadog tools and context with our MCP Server.