The technical documentation for chips within the semiconductor business is usually hundreds of pages lengthy. Preserving these paperwork up to date with each revision is a large carry, as is producing the manuals and tutorials for engineers who then implement these chips in their very own merchandise. And to make issues much more difficult, only a few merchandise solely use a single chip, even when they’re seemingly as easy as an influence software.
Driver, a startup popping out of stealth at present and saying an $8 million seed funding spherical led by GV, makes use of AI to chop this whole course of all the way down to just a few hours, whereas additionally giving companies the chance to generate user-specific documentation.
The corporate’s CEO and co-founder Adam Tilton launched (and offered) quite a lot of startups, together with wearables startup Rithmio, earlier than touchdown at Nike after it acquired his edge computing and machine studying startup Aktive. Whereas at Nike, he met his co-founder and CTO Daniel Hensley, who on the time was a part of the management group of a small agency that helped shoppers combine embedded gadgets and use machine studying. After leaving Nike, Tilton went to work at healthcare startup Ranges, the place he led sign processing for a {hardware} undertaking. To spherical out the group, additionally they introduced on Jimmy Hugill as co-founder and CFO.
“Throughout my career, I’ve done a lot of development for embedded technologies that were to then be used by others,” Tilton mentioned. “At Rithmio, we had a library of functionality that wearable product manufacturers could use to enable some functionality. At Nike, I was a consumer. I would buy components. I was on the selection committee to take the components — and then we were trying to build a product out of them. And I have just over and over in my career, had to work on this particular challenge.”
The documentation for these elements is usually very low stage, with instance code that may be old-fashioned and targeted on solely a single programming language.
“Daniel [Hensley] and I were doing a lit review to get deep into the technology and I had the idea that I should go into the PDF and pull out each of the different APIs, and go into the example code, and pull out the example code, and effectively get ChatGPT to do the thinking about how I’m supposed to do this in Python, because I wanted to wrap all of this into a Python program integrated into our automated testing system,” Tilton mentioned.
After seeing this, Hensley urged constructing a software program platform to assist engineers do that at scale — one which caters to each the suppliers of chipsets like microcontrollers, ASICs, and FPGAs, in addition to the engineers who then must translate these paperwork for their very own merchandise.
Even inside an organization, a lot of the interior documentation for constructing a sure product can grow to be outdated as new elements are launched. Driver, which is language-agnostic, goals to be an answer for these use circumstances, in addition to serving to consumers and sellers hold their inside documentation updated.
The corporate guarantees that it might probably velocity up a group’s understanding of a brand new codebase by 50% and save corporations weeks of worker time that will in any other case be spent writing documentation.
The corporate’s seed funding spherical was led by GV, with participation from Y Combinator and “over a dozen early-stage and angel investors.”
“We invested in Driver early given our excitement about the founders and the novel use cases of generative AI they are addressing with a large untapped market opportunity,” mentioned Luna Schmid, Companion at GV. “The founders have an incredible track record of building and bring extensive experience and hard-earned lessons from working with complex codebases. We believe Driver is a game changer for any team that needs to document complicated technology quickly and ensure it can be understood by all constituents.”
