Operations | Monitoring | ITSM | DevOps | Cloud

Without experiment infrastructure to help you test your LLM applications, every research session starts with the same questions: What have we tried previously? What were the numbers? Which prompt version produced that result? Why did we discard that approach? The answers live in scattered notes, terminal history, and half-remembered conversations. Each handoff between sessions loses context. In practice, iteration can slow down as teams get bogged down in testing and analysis.

Last week, we launched a major update to Canvas, our investigation workspace. The new Canvas has evolved from an AI co-pilot you chat with to a place where your whole team, human and agent, can work the same problem on the same surface. Auto-investigations begin the moment a trigger, SLO, or anomaly fires. Custom skills encode your team's runbooks so every agent investigates with your team's expertise built in.

AI observability covers performance, quality, reliability, safety, and cost. Most tools handle the first four. Here's what each pillar means, which tools cover which, and why cost is the dimension enterprises keep missing.

Your dashboards are green. Your thresholds are calm. Then a cascade failure starts and you don't know until users flood your status page. Traditional monitoring is reactive by design. Anomaly detection in observability changes that equation entirely.

Last week, we introduced Agent Timeline, a powerful new observability experience purpose-built for debugging AI agent workflows in production. Agent Timeline uniquely connects AI-layer visibility to full-stack observability by organizing telemetry around an agentic conversation. A conversation contains one or more agent executions, each of which may contain LLM calls, tool invocations, handoffs, retries, human escalations, and downstream system calls.

Today we’re launching Lightrun AI Skills, structured, repeatable investigation workflows built for AI coding agents. With Lightrun MCP, agents like Claude Code, Codex, and Cursor can already instrument live production services and reason over live runtime evidence without a redeployment. But AI agents remain non-deterministic by design, using the same tool differently every session.

Customers regularly come to us looking to solve their observability problem by connecting the dots from frontend to backend. It sounds straightforward in theory, but in practice it's one of the hardest problems in modern application monitoring. The frontend monitoring tools they already have in place tend to be proprietary or narrowly scoped to frontend needs, leaving them without the context-rich backend data that makes real triage possible.

Honeycomb is proud to share that we have achieved the Amazon Web Services (AWS) Financial Services Competency. This recognition validates our technical expertise and proven customer success in assisting financial services organizations with building, running, and understanding their production systems on AWS. Securing this competency is a direct response to our customers’ feedback in this space: observability in regulated, high-stakes environments requires more than dashboards and alerts.