Detect Auto, a Fargo-based startup leveraging artificial intelligence to transform auto repair shops and dealerships, has successfully closed a $748,000 seed funding round. This seed round was “led by gener8tor 1889 with participation from Groove Capital and angel investors,” CEO Jonathan Cabak said.
The funds will boost the development of Detect Auto’s AI platform, aiming to improve auto repair processes through advanced computer vision technology. This milestone follows Detect Auto’s participation in the gener8tor North Dakota accelerator program.
We had the privilege to interview CEO Jonathan Cabak to learn more.
Q&A with Jonathan Cabak
Q: How does Detect Auto specifically use AI and computer vision to enhance the auto repair process? Can you elaborate on the technologies behind your platform?
A: We use AI in a couple of different ways to help repair shops and dealerships. Our primary application is our computer vision system that identifies vehicles and if a person is working on said vehicle. From there, we’ve trained our own proprietary model that identifies what work a technician is completing at any given time so shop owners can get a “real-time” view of how their repairs are getting completed. It’s like a Domino’s pizza tracker but for your car’s repairs.
If you want to get really into the weeds, our platform works by feeding an image into a neural network that our team trained. The best way to describe how our system works is that we’ve fed it so much data over the past two years that the network has effectively “learned” what features we care about tracking, and we use those insights to provide our customers with actionable steps they can take to make improvements.
One major disclaimer—we don’t use facial recognition in any of our products. Our whole platform was built with privacy in mind, and we’re very intentional about what data we collect and how it’s processed.
Once we’ve collected our image data from cameras we install into auto shops and extracted the relevant data, we combine these predictions with our customers’ software management platforms to provide context to our data. For example, we may read the license plate of a vehicle, figure out what jobs are supposed to be worked on, and then pair that data with our camera feed to determine exactly when those jobs are being worked on. When we first started the company, we were around 75% accurate. Over the past year, we’ve just cracked 95% accuracy which is something we’re really proud of.
Q: What challenges did Detect Auto face during the initial development of your AI platform, and how were they overcome?
A: It’s expensive to train your own model, especially if you don’t already have specialized hardware like a high-end GPU. To the credit of our team, we’re exceptionally scrappy, and we figured out that we could repurpose my old computer to train our models. We had that computer running 24/7 for months on end—it’s a miracle we were able to make that work.
Another problem we faced was collecting a diverse dataset. When we installed in our first stores last year, we realized the initial model we had trained was actually overfit to our training dataset.
This meant that we had exceptional performance with our test shop, but new customers initially experienced long onboarding times as we had to fine-tune our model to suit their shop’s unique arrangements. We’re still working through this, but with over a million annotated images, we’re well on our way to having the best dataset in the automotive space. This ties into the last issue we faced—annotating images to describe what’s inside of them is very time-consuming. Our initial approach was to just brute force our way through it, but that was a mistake on our part. We’ve since started utilizing more advanced machine learning techniques to drastically reduce the number of images we need to label for a shop. This cut our onboarding time down from a month to under three days.
Detect Auto’s Experience with the gener8tor North Dakota Accelerator Program
“Honestly, we probably wouldn’t still have a company if it weren’t for gener8tor. They taught us so much about how to obsess over customer feedback, expand our sales pipeline, and properly structure our business so that we could be poised to receive future investment capital. I think it was an incredible opportunity to surround our team with other entrepreneurs who were also doing whatever they needed to do to make their business succeed—it’s a motivating atmosphere to be in.” – Jonathan Cabak, Co-Founder, Detect Auto.
Q: Can you share any success stories or case studies where Detect Auto’s technology significantly improved repair efficiency or accuracy for a client?
A: In general, our platform is exceptionally good at monitoring how work gets completed. If an outlier (good or bad) is detected, we can compare this data against our baseline data to understand exactly what caused these differences in efficiency. For example, one of our first dealership customers wanted us to focus on their express service jobs (oil changes, tire rotations, etc). We found that certain technicians who were really efficient in their repairs were experts at multitasking. These technicians would make sure that tasks that didn’t require them to be in the repair bay working on the car (i.e. draining oil for an oil change) were run concurrently with other tasks they needed to complete (i.e. getting the new oil filter from the parts department). Less efficient technicians didn’t follow this process and saw their efficiency suffer. By using our system, the store was able to increase their efficiency 34% which equates to saving seven minutes per oil change.
What is the gener8tor 1889 Fund?
Gener8tor 1889 is a venture capital fund that invests in early-stage startups in North Dakota, with investments ranging between $250K and $750K. Named after the year North Dakota achieved statehood, it’s industry-agnostic, supporting startups regardless of their sector. The fund is part of a broader support ecosystem provided by gener8tor, which includes various accelerator programs designed to propel high-growth startups with capital, mentorship, and access to a network of investors and corporate partners.
Q: How does Detect Auto’s solution integrate with existing systems in auto repair shops and dealerships? Are there any requirements for users to get started?
A: We connect with their Shop Management Software (SMS) or Dealer Management Software (DMS) to pull data for each repair order completed in the shop. The only requirement we have for our users is that they allow us to integrate with their data (which usually means clicking a button to provide us access). Other than that, our team handles the rest from the camera installation to onboarding and training.
Q: What feedback have you received from early users of your AI platform, and how has it influenced the platform’s development?
A: The first thing we heard was that people don’t want to just look at our data—they want to use it to improve the way they do business. Our first attempt at this was a basic dashboard that, candidly speaking, missed the mark. The data and insights were there, but it took too long to find them. Now, our team has been actively working with our customers to train them how to identify issues quickly and then use our platform to design effective solutions to resolve these issues.
Otherwise, the feedback has been largely positive. The industry needs this data to understand how work gets done, and until our platform launched, the only way to get it was by manually entering everything a technician did while working on a car into their SMS or DMS. With Detect Auto, technicians can stay focused on repairing vehicles and getting their customers back on the road while management teams can use our data to help service customers more efficiently than ever before.
Q: Can you discuss the competitive landscape for AI technologies in the auto repair industry and how Detect Auto differentiates itself from other solutions?
A: Most of the buzz about AI in the automotive industry centers around chatbots and handling phone traffic. It’s all about how can customers get better access and visibility to what’s going on with their vehicle while it’s in the shop.
Our platform takes this a step further by focusing on understanding how work gets done in real time. With our camera platform providing us with best-in-class data on how long repairs are actually taking, Detect Auto can provide customers with a window into the repair process that they’ve never previously had access to.
Q: What are the long-term goals for Detect Auto following this seed funding round? Where do you see the company in the next five years?
A: We’re looking to hit the ground running this year—our team has built out an exceptional platform, and we want to get it in front of as many shops as possible. If we enter 65 new stores this year, our team will be really happy.
We also want to continue expanding our product’s capabilities, especially when it comes to how other industries can leverage our technology. We’ve essentially created a passive monitoring system that identifies inefficiencies in processes and proactively recommends solutions to improve.
In the next five years, I want Detect Auto to be the core piece of technology that shops use to manage their operations. We’re an analytics platform that collects data that has previously been impossible to collect, so the possibilities are endless. I also want to see that our customers still love our product and that our team is still (or more) dedicated than we are now.
Lean More
detectauto.com
Facebook | Search “Detect Auto”
Linkedin | /company/detect-auto/