Operations | Monitoring | ITSM | DevOps | Cloud

You can give AI agents everywhere fingers & eyes into your tool or service, by implementing an MCP (Model Context Protocol) server. It’s a great idea! It’s also a new kind of design and engineering. Jessica describes how it’s different from implementing an API or a GUI, and why it’s more exciting than either.

Did you miss Honeycomb's Observability Day San Francisco? Here are some highlights of the day.

Canvas is an AI-guided workspace inside Honeycomb that combines an AI assistant with an interactive notebook for visualizing query results and traces. You can ask a natural language question about your data and Canvas will immediately start exploring your traces, through multiple queries and other tools, to find the right next steps. Instead of having to write each query yourself, Canvas automatically proposes relational queries, comparisons, and visualizations that explain why an SLO fired or what changed after a deploy.

Modern teams face a persistent challenge: knowing when something goes wrong before their customers do. With architectures sprawling across dozens or hundreds of services, creating comprehensive alerting becomes an overwhelming task. You're left playing whack-a-mole with manual alert configurations, often missing critical issues or drowning in false positives. Today, we're excited to announce our solution to this challenge: Anomaly Detection (currently in alpha), Honeycomb's proactive approach to understanding and acting on service health.

Did you know you can define a calculated field in your Honeycomb queries? You can, and with the power of Honeycomb AI you can ask it to write the calculated field definition for you. Find out how in this short video.

In the months since we launched our public beta, we’ve been hard at work making Honeycomb MCP more useful and capable for agents and human operators alike. Our goal with this project has been, from the start, to allow AI to engage in the same kind of investigatory loops that we guide users towards. Many of the new features are designed expressly with this in mind, the most exciting of which is BubbleUp, now available in.

You can use your mobile tools to debug errors, but are you really looking at the root cause? With end-to-end observability, powered by Honeycomb's Mobile Android and iOS SDKs, you can see everything! We'll show you how to start from a mobile launchpad, view the errors, select a trace, and find that root cause.

Here, Pierre Tessier shows how he looks into partition load in Honeycomb's distributed datastore in production.

Jessitron takes you through a 3-minute demo of the Honeycomb Telemetry Pipeline. Our makes it easier to manage telemetry so you always have the data you need, when you need it, without trading off cost, control, or visibility.

What does it look like to notice & debug a problem in Honeycomb? Start with a Service Level Objective (SLO), and Honeycomb can tell you what's unusual about the events that are failing. Continue to dig into all your telemetry.