Honeycomb’s observability platform increasing trust in AI

Observability is a critical component of artificial intelligence systems, offering insight into the results from large language models and AI agents.

Honeycomb.io uses OpenTelemetry’s open-source framework to give users a way to visualize and analyze their telemetry data. Its momentum stems from the need for trust and transparency around AI and provides a potential solution for monitoring increasingly complex software systems. The AI boom means that observability is more important than ever, according to Christine Yen (pictured), chief executive officer of Honeycomb.

“With the advent of AI assistants and a lot of the code-generation capabilities that have burst on the scene over the last couple years, as teams adopt those technologies, they realize … that the more code they have, the more problems they tend to have. And as more code is being pushed to production … the need for that code to be reliable and predictable and basically do what the engineers expected, that problem just gets bigger.”

Yen spoke with Dave Vellante at AWS re:Invent, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed the recent updates to Honeycomb’s platform and the role of observability in building customer trust. (* Disclosure below.)

Honeycomb expands observability AI tools

The Digital Operational Resilience Act report for 2025 showed that use of AI coding assistants is increasing and tech platforms’ stability is decreasing, according to Yen. She describes observability as a truth-teller that reveals what your software is actually doing. Since AI is more prone to hallucinations than other technologies, giving customers that reassurance is essential.

“Whether it’s humans or not, there needs to be feedback loops between what the code is doing in production, and frankly, what you think it is,” Yen said. “When that balance of autonomy has shifted and there’s AI agents doing even more autonomous things than just generating code that is run … so that humans can go in later and validate the decisions that an AI made.”

Honeycomb’s platform is now available as a private cloud offering and will soon incorporate Dynatrace’s OpenTelemetry standards for metric data, updates that aim to give customers greater transparency and control over their data. There is a broader concerns about AI displacing human workers, Yen acknowledged, but she argues that human context and intuition remain essential

“One of the studies … comes from the medical industry, where folks have been trying to automate, or at least augment, what doctors do for years,” she said. “One of the things that they found was that when doctors leaned on automation first … they actually found that their skills of diagnosis began to atrophy. Whereas when a doctor had a hypothesis and then backed it up with all the automation and tools at their disposal, they were able to make better diagnoses.”

Honeycomb has also made its Canvas experience generally available. Yen describes it as Honeycomb’s copilot, a workspace that combines an AI assistant with an interactive notebook for visualizing traces and query results.

“It leverages all of the technologies that we’ve become accustomed to … and applies it to an observability tool” she said. “Where this class of tooling historically has felt very technical, maybe overwhelming to someone new to a team, with Canvas, it is easy and natural.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of AWS re:Invent:

(* Disclosure: Honeycomb sponsored this segment of theCUBE. Neither Honeycomb nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE