Operations | Monitoring | ITSM | DevOps | Cloud

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.

Send Honeycomb JSON or sophisticated OpenTelemetry. Traces, logs, metrics. Then add a few business-specific fields (or calculate them), and answer important questions on the fly.

Artificial intelligence is changing the way modern systems are built—and how teams are expected to and operate them. But as AI-driven complexity grows, so too does the need for deep, reliable, and fast visibility into what’s really happening inside our. In this timely and thought-provoking session, Christine Yen, CEO and Co-founder of Honeycomb, explores how practices must evolve to keep pace with.

When an alert triggers in Honeycomb, how do you want to hear about it? Send detailed information however you want it with custom webhooks.

Honeycomb Service Map is dynamically generated from traces. It shows all the connections between services, and you can narrow it down by any query-- for instance, see the services one particular user hit. And then, get to a trace with the full details. Service Map is a feature of Honeycomb Enterprise.

Our bot is hitting an error. We can see it in the distributed trace. Here, see what happened when we noticed it: Austin fired up Claude Code (hooked up to Honeycomb with its MCP tool) and got it to find the error, fix it, deploy, and check that the fix worked. It got a little overconfident at first, but the ending is happy. IRL this took 22 minutes; the video speeds up the AI agent interactions and cuts out waiting. This video includes Austin Parker, Jessica Kerr, and Ken Rimple.