Honeycomb.io, the creators of observability, announced a series of new AI capabilities and two major product milestones, including the general availability of Honeycomb Metrics and the expansion of its Model Context Protocol (MCP) integrations across leading AI development tools.
As AI agents become both primary contributors to and consumers of production software, these releases position Honeycomb as the first observability platform purpose-built for that reality—giving agents the structured data and direct platform access they need to monitor, debug, and optimize systems autonomously, according to the company.
“Observability was built for a world where humans wrote the code and humans read the dashboards,” said Graham Siener, SVP of product at Honeycomb. “That world is changing fast. AI agents are writing more code, deploying more services, and increasingly need to understand what's happening in production themselves. We're building Honeycomb for that reality: where your AI coding agent can investigate a production issue with the same telemetry your best SRE uses, and where more code shipping faster doesn't have to mean more things breaking.”
Honeycomb is launching a series of new AI capabilities designed to remove manual, time-intensive observability tasks and bring functionality closer to where customers work every day. These capabilities include:
- Speed up migrations, onboarding, and production investigations with Honeycomb Agent Skills, now available for Claude Code, Cursor, and dozens of other agents. Migrate legacy telemetry to OpenTelemetry, get expert advice on instrumentation, and create boards, triggers, and SLOs during onboarding to Honeycomb.
- When an alert fires or an SLO burns, Honeycomb Automated Investigations jumps into action with the same playbooks and instincts your best SREs use. The capability can autonomously detect issues, conduct investigations, and recommend solutions.
- The new Honeycomb Slackbot brings Canvas into Slack, allowing you to use natural language to ask questions, investigate alerts, get summaries, and explore observability data. It also provides evidence-backed analysis with its “Chain of Thought” logic to detail which tool calls were made, the exact parameters passed to those tools, and how the agent adjusted its plan when a specific tool output was unexpected or irrelevant.
- Honeycomb Pipeline Intelligence is an AI-powered feature designed to simplify telemetry pipeline creation and management at a time when AI-driven systems are generating observability data at unprecedented scale. It automatically detects log types, chooses appropriate parsers, and builds pipelines according to established best practices—handling much of the configuration work on its own. What previously required days of manual effort per log source can now be completed in minutes, with only minor adjustments left for engineers to fine-tune.
Honeycomb Metrics now offers both time series and event-based models on one platform with a unified query experience, eliminating this tradeoff. Teams can seamlessly pick up existing OpenTelemetry metrics workloads in Honeycomb and utilize event-based collection to capture all the custom metrics and dimensions they need without worrying about runaway costs, preserving the rich context that AI-powered investigations depend on, the company said.
Honeycomb is expanding the capabilities of its MCP to embed observability directly into the AI-powered development and operations tools engineering teams already use.
Honeycomb Metrics is generally available to all Honeycomb customers now. MCP expanded capabilities and Agent Skills for Claude Code, Cursor, the AWS DevOps Agent, and additional platforms are also available now. Honeycomb Slackbot and Automated Investigations are available in early access.
For more information about this news, visit honeycomb.io.