Honeycomb, a leading observability platform used by high-performing engineering teams to investigate the behavior of cloud applications, today announced that it is the first observability platform to launch fully-executing Natural Language Querying using generative AI for its new capability, Query Assistant. This development dramatically scales the platform's query power and makes observability more usable for all engineering levels.
By leveraging OpenAI, Honeycomb's new Query Assistant enables developers at all levels to ask questions in plain English instead of a query language. Generative AI then builds a relevant, modifiable query, eliminating the prerequisite for advanced knowledge of query-based languages like SQL. KPMG explains that "by lowering barriers to entry for new developers on complex codebases, generative AI also will allow companies to do things that were previously impossible." Integrating AI into Honeycomb's query engine is a huge step towards making it possible for everyone on an engineering team to understand code behavior and performance without needing deep familiarity with their code or querying languages.
Honeycomb's new Query Assistant is a distinctly different approach to AI compared to what's been done historically by traditional APM and ops tools that apply AI to data analytics for features like automated alerting. This capability uses generative AI to enhance human intuition by allowing users, no matter how seasoned, to ask questions and get fast feedback on what's happening with their code.
"Slack sends vast amounts of events to Honeycomb that have different definitions and data taxonomy depending on context," said Ryan Katkov, Director of Engineering Observability at Slack. "Now, with access to Query Assistant, our engineers can more easily ask questions using natural language and get answers faster without needing deep knowledge of our haystack."
Query Assistant joins Honeycomb's other human-first, machine-assisted debugging tools, such as BubbleUp. Used by engineering teams to quickly answer complex problems in their code, BubbleUp uses machine analysis to cycle through billions of high-cardinality data points (fields like userId, shoppingCartId, and orderId, etc.), visually compares problematic user experiences to healthy ones, and identifies the differences. This dramatically accelerates the debugging process by eliminating the time-consuming and error-prone legacy APM workflow of jumping from metrics dashboards to individual logs and traces to guess at problematic patterns.
"The best developer tools are increasingly going to be the ones that get out of your way and become invisible," said Charity Majors, CTO of Honeycomb. "Observability shouldn't require you to master complicated tools or languages that force you to constantly switch context and piece together clues to get answers to complex problems. The only thing observability tools should encourage you to focus on is your own curiosity about what's happening in your system."
Honeycomb believes that delivering superior user experiences is a team sport and makes significant investments in making observability usable for all. This is showcased in our unique pricing model that has no additional charge per service, host, memory, custom field, or seat as well as our collaborative team features like the ability to share query histories. With the addition of Query Assistant, anyone on the team can easily understand how their application code is behaving in the hands of real users in unpredictable and complex cloud environments. This new capability is a great first step for Honeycomb R&D to further explore how AI can be incorporated into the product to enhance the Honeycomb user experience.
Query Assistant is available to all Honeycomb users. As of today, it is an experimental feature that can be turned off by teams. No user data is passively sent to OpenAI, and no data is retained for training models. To learn more about Query Assistant and how to start using it today, visit our blog: https://bit.ly/44l7we2.
About Honeycomb
Honeycomb provides observability for high-performing engineering teams so they can quickly understand what their code does in the hands of real users in unpredictable and highly complex cloud environments. Honeycomb customers stop wasting precious time on engineering mysteries because they can quickly solve them and know exactly how to create fast, reliable, and great customer experiences. HelloFresh, Stripe, Slack, Fender, Vanguard, LaunchDarkly, and many more rely on Honeycomb for fast incident response, performance optimization, and safely accelerating release cycles. Learn more at www.honeycomb.io and follow us on Twitter and LinkedIn.