Head over to our on-demand library to view sessions from VB Transform 2023. Register Here
While every day in this year brings new announcements in enterprise software and generative AI, there is a whole other side to development that receives a fraction of the headlines: maintenance.
The truth is, nearly every new piece of software that is created and released requires ongoing monitoring and manual updates in order to ensure it remains not only secure, functional, and efficient but avoids the “technical debt” that accumulates over time.
While these tasks have traditionally fallen upon developers within software organizations, a new startup, Grit, thinks it has found a better solution: a generative AI-powered developer assistant. Today, the company is emerging with a $7 million funding round led by Peter Thiel’s Founders Fund and Abstract Ventures with support from Quiet Capital, 8VC, A* Capital, AME Cloud Ventures, SV Angel, Operator Partners, CoFound Partners and Uncorrelated Ventures.
Grit is announcing the open beta of its new eponymous AI tool that automatically analyzes a program’s codebase, tracks it over time and suggests updates and improvements as if it were another member of the development team.
VB Transform 2023 On-Demand
Did you miss a session from VB Transform 2023? Register to access the on-demand library for all of our featured sessions.
“Traditionally, software engineering was very artisanal,” explained Grit CEO and cofounder Morgante Pell in a video interview with VentureBeat. “You have experts who go in with scalpels and modify code line-by-line. But what we’re seeing with generative AI is it’s much easier to generate new code. So we just need new tools that are able to move code at scale, like bulldozers.”
How does it work?
Pell knows the travails of keeping software updated firsthand, having previously worked at Google Cloud on infrastructure for the service.
“Seeing how many of our customers were not tech companies, but had so much software that was essential to their business they were having to maintain” ignited a lightbulb of inspiration within Pell’s brain.
If there was a way to automate that maintenance, it could “do the work that engineers don’t want to so that software can keep running smoothly.”
“Right now, engineers are interrupting their more interesting work to do maintenance,” Pell said. “It’s the work nobody wants to be doing in the first place.”
Instead, with a CTO or authorized developer’s permission, Grit can be installed as a GitHub app or connected to GitLab, where it scans a company’s code repository and builds an index of it.
The index is “stored ephemerally,” according to Pell, and uses a highly optimized search tool to understand where to make changes in application codebase according to pre-set goals.
“We don’t actually keep any customer code, long term,” Pell explained. “We just keep it when we’re doing that particular change and then delete things afterward.”
Using the natural language query interface to Grit’s signature app, developers can express their high-level goals while Grit handles implementation details.
Grit doesn’t just make changes automatically. It first shows a developer or a team of developers the changes it plans to make, then asks for approval. If a developer wants to modify the proposed changes, they can simply type a message to Grit in natural language like another member of the team.
“Instead of an engineer having to go in and proactively make a change, Grit can just look and say, ‘OK, you’re out of date on this version, and we’re going to suggest the upgrade and we’ve already generated the change to do the upgrade,’” Pell said. “So the engineer, all they have to do is click one button and say ‘approved.’ They don’t even have to open their editor to do their change.”
Early results show promise
Though just a year old, Pell said Grit has already saved customers such as Faire and PromptLayer huge amounts of time.
“We’ve had projects where they were projecting that was going to take them six months of engineering effort to do the project, and with Grit, that got it done in a week,” said Pell.
Right now, Grit’s primary customer base is “later-stage technology companies” and some firms in fintech. Pell told VentureBeat that the primary use cases so far have been for the modernization of old codebases. He says the tool’s “sweet spot” is working alongside teams of hundreds of engineers, allowing them all to offload their maintenance tasks to it simultaneously.
Grit’s angel investors include Vercel’s Guillermo Rauch, Adobe’s Scott Belsky, and entrepreneur Sahil Bloom.
VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.