Operations | Monitoring | ITSM | DevOps | Cloud

Innovation Week Day 2: Observability for AI, and Observability With AI

AI is reshaping the SDLC in two directions at once. AI-generated code is shipping faster and with less human supervision than ever before, while agents and LLMs are running directly in production, where they behave very differently from traditional software: non-deterministic, with a wider blast radius than any single function or component, with no stack trace to catch when something goes wrong.

Honeycomb Innovation Week: Observability With AI With Kale and Taylor

Watch this video to see the re-imagined Canvas in action, where auto-investigation has already ranked your hypotheses before you open the tab, multiplayer agents build on each other's work in real time, and a custom skill encoding your team's own runbook can reprioritize the entire incident before you've had your morning coffee.

Observability for the Agent Era: Day 2 | Launches

Honeycomb's Innovation Week: Observability for the Agent Era (May 12-14) For Day 2 of Innovation Week, Honeycomb's product and engineering teams will take you inside the new capabilities purpose-built for the agent era. Expect live demos, real scenarios, and a hands-on look at what it means to own observability for the Agentic era, with AI in Honeycomb to observe AI in production. A 3-Day Virtual Event for Teams Building the Future May 12: Get insights on how the best engineering teams are tackling the challenges of the agentic era.

Honeycomb Innovation Week: Debugging Agentic Workflows with Ken Rimple

Canvas skills are how your team's runbooks and tribal knowledge become an active part of the investigation instead of a document someone has to remember to open. Pre-built skills cover the most common investigation patterns out of the box. Custom skills let you encode the specific context, thresholds, and decision logic your team has accumulated, so every auto-investigation starts with your best thinking already applied.

Innovation Week Day 1: The SDLC Is Collapsing, and Observability Has Never Mattered More

The software development lifecycle is collapsing. The multi-stage pipeline that defined how software got built and shipped for decades is compressing into rapid loops of intent and validation, with agents now part of the teams building and running it. Day 1 of Innovation Week was about what that shift means for how software gets validated, where observability fits, and the problems that have always been hard but are now genuinely urgent.

Making Semantic Conventions Work for You With OpenTelemetry Weaver

Your dataset has hundreds of attributes. Some are self-explanatory: http.response.status_code, server.address. Others are not: meta.refinery.reason, dataset.slug, sli.latency_target_ms. If you don't know what an attribute means, you can't write a good query. And if an AI agent doesn't know what it means, it guesses.

Span or Attribute in OpenTelemetry Custom Instrumentation

TL;DR: Attribute. More information on one event gives us more correlation power. It’s also cheaper. When you want to add some information to your tracing telemetry, you could emit a log, create a span, or add a piece of data to your current span. Adding a piece of data to your current span is the best! Usually.