Startup Honeycomb today debuted a new artificial intelligence tool that promises to help developers more easily troubleshoot application errors.

Dubbed Query Assistant, the tool is powered by generative AI software from OpenAI LP. Query Assistant will become available as part of Honeycomb’s namesake observability platform. The tool will complement a number of existing machine learning features that Honeycomb offers to ease software troubleshooting.

Honeycomb, officially Hound Technology Inc., provides an observability platform that companies use to detect and fix technical issues in their applications. The platform makes it easier to pinpoint the cause of malfunctions such as latency increases. It can ingest billions of rows’ worth of troubleshooting data, according to Honeycomb

The San Francisco-based startup is backed by $148.9 million in funding. Following its most recent $50 million raise last month, Honeycomb disclosed that its platform is used by more than 600 companies.

Software teams can query the application data stored in Honeycomb to diagnose technical issues. A developer could, for example, write a query that surfaces all the errors encountered by an application in the past week. Historically, such data analysis required familiarity with the SQL language. 

Query Assistant, the new generative AI tool the startup debuted today, is designed to simplify the task. It provides the ability to analyze application issues using natural language prompts. Developers can describe what data they require to carry out troubleshooting and have the tool automatically generate the corresponding query.

According to Honeycomb, the tool can analyze multiple types of application data. It also provides the ability to visualize technical information in graphs for easier access. When necessary, developers with advanced requirements can manually customize Honeycomb’s AI-generated queries.

By reducing the amount of time and effort required to analyze troubleshooting data, Query Assistant can potentially help developers fix technical issues faster. In the process, the tool promises to ease the learning curve for new users. Interacting with application logs using natural language prompts avoids the complexity associated with custom query code. 

“The best developer tools are increasingly going to be the ones that get out of your way and become invisible,” said Honeycomb co-founder and Chief Technology Officer Charity Majors. “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.”

Query Assistant will complement an existing AI tool called BubbleUp that Honeycomb ships with its platform. Often, understanding the cause of an application error requires analyzing data from multiple sources. When a developer reviews a set of data points about an error, BubbleUp can automatically surface related information to speed up the troubleshooting process. 

Image: Honeycomb