Mintlify leverages AI to automatically generate documentation from code – TechCrunch
Mintlify, a startup developing software to automate software documentation tasks, today announced it has raised $2.8 million in a funding round led by Bain Capital Ventures with participation from TwentyTwo Ventures and Quinn Slack , co-founder of Sourcegraph. CEO Han Wang said the proceeds will go towards product development and doubling Mintlify’s core three-person team by the end of the year.
Mintlify, based in Ithaca, New York, was co-founded in 2021 by Han Wang and Hahnbee Lee, both software engineers by trade. Wang previously co-launched Foodful, a startup that developed a cloud-based monitoring system for cows, and Pe•ple, an online customer community platform that was acquired by Tribe in early 2021. Lee was co-founder of Pe•ple before briefly joining Duolingo as an engineer.
Wang said the idea for Mintlify came from his and Lee’s experiences in software development, which involved working with documentation that wasn’t always comprehensive or of the highest quality. Their findings align with a 2017 GitHub survey, which found that 93% of developers consider incomplete or outdated documentation to be a pervasive problem.
“We’ve worked as software engineers at companies at every stage, from startups to big tech, and found that they all suffered from poor documentation, if it even existed,” Wang told TechCrunch. in an email interview. “Documentation is the lifeline for junior engineers and those getting started with new codebases. It helps senior developers save time explaining their code to others in the future. For public and open source products source, documentation has a direct impact on user adoption.
Mintlify aims to address documentation challenges with automation, especially automatic documentation generation. The company’s platform reads code and creates documents to explain it, leveraging technologies like natural language processing and web scraping.
Wang declined to elaborate on the technical underpinnings of Mintlify, but generating documentation from code is entirely possible with today’s AI techniques. This is evidenced by the fact that Mintlify has several competitors taking similar approaches, including Documatic, whose AI system automatically generates changelogs and explanations from code in addition to documentation.
Wang says Mintlify provides “significantly” better quality results than rivals and, unlike some, doesn’t require developers to host documentation on a cloud service. “Mintlify’s mission is to solve documentation rot by developing continuous documentation into a standard practice for software teams,” Wang added. “[W]hen engineering managers actively seek solutions for better documentation practices, … that’s where we come in.
Beyond documentation generation, Mintlify regularly checks for “obsolete” documentation and detects how users interact with the documentation to improve its readability. (Wang pointed out that the platform stores no code and encrypts all user data at rest and in transit.) Mintlify, which is free for individual developers, also integrates with existing systems, including Slack, Dropbox, and GitHub to automate task management and development. workflow.
According to Wang, adoption of Mintlify’s free plan has increased 20% every week since its launch in January. With a user base now exceeding 6,000 active accounts, the company plans to focus on a premium offering geared towards enterprise customers.
“The pandemic has standardized a decentralized and asynchronous work environment. This has made high quality documentation essential to achieve effective communication, integration and product development,” Wang said. “Our expansion into workflow automation addresses the challenge by targeting engineering leaders with our existing fanbase serving as champions.”