The technical documentation for chips within the semiconductor business is usually 1000’s of pages lengthy. Retaining these paperwork up to date with each revision is an enormous raise, 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 simple as an influence device.
Driver, a startup popping out of stealth at this time and asserting an $8 million seed funding spherical led by GV, makes use of AI to chop this complete 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 bought) 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 purchasers combine embedded units and use machine studying. After leaving Nike, Tilton went to work at healthcare startup Ranges, the place he led sign processing for a {hardware} mission. To spherical out the group, additionally they introduced on Jimmy Hugill as co-founder and CFO.
“All through my profession, I’ve performed a number of growth for embedded applied sciences that had been to then be utilized by others,” Tilton stated. “At Rithmio, we had a library of performance that wearable product producers may use to allow some performance. At Nike, I used to be a shopper. I’d purchase parts. I used to be on the choice committee to take the parts — after which we had been attempting to construct a product out of them. And I’ve simply time and again in my profession, needed to work on this explicit problem.”
The documentation for these parts is usually very low stage, with instance code that may be outdated and targeted on solely a single programming language.
“Daniel [Hensley] and I had been doing a lit assessment to get deep into the know-how and I had the concept I ought to go into the PDF and pull out every of the totally different APIs, and go into the instance code, and pull out the instance code, and successfully get ChatGPT to do the serious about how I’m supposed to do that in Python, as a result of I wished to wrap all of this right into a Python program built-in into our automated testing system,” Tilton stated.
After seeing this, Hensley steered 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 have to translate these paperwork for their very own merchandise.
Even inside an organization, a lot of the inner documentation for constructing a sure product can develop into outdated as new parts are launched. Driver, which is language-agnostic, goals to be an answer for these use circumstances, in addition to serving to consumers and sellers preserve their inner documentation updated.
The corporate guarantees that it may velocity up a group’s understanding of a brand new codebase by 50% and save corporations weeks of worker time that may 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 buyers.”
“We invested in Driver early given our pleasure in regards to the founders and the novel use circumstances of generative AI they’re addressing with a big untapped market alternative,” stated Luna Schmid, Accomplice at GV. “The founders have an unbelievable monitor report of constructing and convey intensive expertise and hard-earned classes from working with complicated codebases. We imagine Driver is a sport changer for any group that should doc difficult know-how rapidly and guarantee it may be understood by all constituents.”
