Honeycomb.io 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.
"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 everyday. 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 is able to 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 the vast majority 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.
With Honeycomb Metrics now generally available, Honeycomb gives engineers — and the AI agents working alongside them — seamless access to all telemetry data in one place.
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 starting today.
MCP expanded capabilities and Agent Skills for Claude Code, Cursor, the AWS DevOps Agent, and additional platforms are available now.
Honeycomb Slackbot and Automated Investigations are available in early access.
The Latest
Enterprises today operate in a real-time environment where uninterrupted access to trusted data has become a baseline expectation for users, applications and automated systems. Traditional DataOps models, built on manual effort and human triage, cannot keep pace with this always active demand. AI agents are emerging as the operational backbone, ensuring consistent data availability, reinforcing trustworthiness and enabling a level of scale that manual processes cannot achieve ...
For decades, trust in the digital workplace rested on familiar signals. We trusted faces on video calls, voices on the phone, and emails that appeared to come from people we knew. These cues felt human and intuitive. They anchored how decisions were made, approvals were granted, and access was authorized. AI-powered deepfakes have quietly broken that model ...
Cloud migration was supposed to be a one-way door. For most enterprises, it turns out it isn't. Cloud data repatriation is a real and growing trend. A new survey ... finds that 89% of organizations plan to expand their on-premises infrastructure footprint over the next two years — and 75% have already moved at least some workloads back from public cloud in the past 24 months. The findings point to a broad rethinking of where data belongs ...
Over the past few years, large language models (LLMs) have revolutionized the software industry. Given their ability to excel at multi-step reasoning, LLMs have helped enterprises streamline workflows and adapt to the unknown. However, employing such models comes with sky-high costs, latency issues, and limited flexibility. In the realm of IT operations, it is generally wiser to employ smaller, domain-specific models instead ...
For years, DevOps teams operated under a simple assumption: collect enough telemetry, and you can find and fix any problem. That assumption is breaking down. Modern enterprises now operate across microservices, hybrid cloud environments, APIs, Kubernetes, and highly automated delivery pipelines. Releases happen continuously, dependencies shift constantly, and failures spread faster than teams can diagnose them ...
New Relic surveyed IT and engineering leaders from the media and entertainment (M&E) sector to understand what's working — and where challenges persist with their observability practices. The findings reveal how M&E organizations are navigating rising platform complexity, audience expectations, and AI-driven change. Below are five takeaways that stand out ...
Let me start with something I've seen play out more times than I can count. A team hits a wall with the cloud. Costs creep up, then spike. Performance starts to feel inconsistent. Someone in finance asks a simple question like "why did this double?" and nobody has a clean answer ... Maybe this isn't the right place for everything. That realization feels like a breakthrough, like you've identified the problem. In reality, you've just identified the starting line ...
In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ...
In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...
When most people think about cybersecurity, they picture firewalls, encryption, and access controls — technical tools designed to protect systems and data. But beneath the technology lies a deeper set of principles about trust, decision-making, and resilience ... The best leaders don't eliminate risk. They manage it intelligently. And in many ways, cybersecurity offers a surprisingly useful playbook for doing exactly that ...