When a field-deployed heavy autonomous vehicle goes down, every hour at a customer site costs millions, making rapid root-cause diagnosis critical. Autonomous Solutions, Inc. (ASI), the company behind Mobius®, a best-in-class OEM-agnostic industrial autonomous fleet orchestration system, partnered with Gritmind to build AI-powered software that compresses an investigation that historically took up to several days into one that takes minutes.
Why this mattered
ASI automates machinery for agriculture, logistics, construction, landscaping, and other heavy industrial markets. At the center of their platform is Mobius, which lets a single operator control the full job site of autonomous vehicles simultaneously — including steering, transmission, acceleration, braking, and ignition — from thousands of miles away. That adaptability is a core competitive advantage: ASI customers can deploy across mixed fleets and scale from remote operation to full automation without swapping platforms. But it also means that when a vehicle goes down, the incident investigation spans a complex, multi-subsystem environment.
Why this mattered
ASI automates machinery for agriculture, logistics, construction, landscaping, and other heavy industrial markets. At the center of their platform is Mobius, which lets a single operator control the full job site of autonomous vehicles simultaneously — including steering, transmission, acceleration, braking, and ignition — from thousands of miles away. That adaptability is a core competitive advantage: ASI customers can deploy across mixed fleets and scale from remote operation to full automation without swapping platforms. But it also means that when a vehicle goes down, the incident investigation spans a complex, multi-subsystem environment.
ASI’s customers operate in places where downtime is paid for in millions per hour. When a truck stops unexpectedly, ASI’s engineers treat it as an incident. Each incident generates gigabytes of log data covering minutes of vehicle time. Root-cause determination historically required anywhere from several hours to multiple days of senior engineering effort, during which the truck could remain out of service for extended periods as associated losses accumulated.
Amid recent growth, ASI’s leadership saw an opportunity to leapfrog the existing approach to incident response: not optimize the steps but rebuild the workflow AI-first. Gritmind and ASI worked together to build an AI workflow that helps locate the digital needle in a multi-system haystack, pointing engineers to the most likely root causes.
What Gritmind built
A multi-agent AI system that investigates an autonomous-vehicle incident end-to-end:
A multi-agent AI system that investigates an autonomous-vehicle incident end-to-end:
- Parses raw vehicle logs automatically, at gigabyte scale per incident.
- Reconstructs the incident timeline.
- Hands off to specialist sub-agents by domain (brake, throttle, planning, and others) to examine their part of the logs and report back.
- Surfaces candidate root causes with click-through evidence to the source log lines.
- Visualizes how events propagate across vehicle subsystems (the team calls this the evidence board flowchart).
- Let the engineer pin the verified findings. The user owns the final summary, not the model.
How we built it
Three decisions compressed the timeline.
Three decisions compressed the timeline.
- Twenty-five user interviews in three days, on-site, with engineers in the room.
Gritmind ran user research at ASI’s site with engineers attending every session. Bringing engineering into user interviews, rather than translating findings through documentation, made the rest of the build possible. The team had usable personas and pattern recognition before they left. - Engineers building from observation, not tickets.
During the interviews, a Gritmind engineer noticed a recurring pain point: users couldn’t easily see how a failure had propagated across vehicle subsystems. He turned that observation into a feature, the evidence-board flowchart, that no PM had requested, and no designer had specified. - AI-native from day one.
On this project, AI showed up from day one, both in the process and in the product. During discovery, the team used AI to synthesize user-research notes and draft personas in real time. Then the team carried that AI-native posture through the proof of concept itself, where a multi-agent architecture became the system, not a layer on top of one.
The product decision that made it land
Early usability testing surfaced something more interesting than accuracy. It surfaced calibrated trust. Some engineers were skeptical of AI conclusions. Others trusted them too quickly.
Early usability testing surfaced something more interesting than accuracy. It surfaced calibrated trust. Some engineers were skeptical of AI conclusions. Others trusted them too quickly.
Through user research, an intentional product change was made. The AI no longer writes the incident summary. It produces a list of candidate problems with supporting evidence. The engineer pins the ones they’ve verified. The summary is the engineer’s, not the model’s. Skeptical users get the verification surface they want. Optimistic users are forced to slow down enough to check. Trust but verify is the team’s North Star on the product.
Outcomes
Three weeks after the on-site workshop, the proof-of-concept was running end-to-end. Verified results:
Three weeks after the on-site workshop, the proof-of-concept was running end-to-end. Verified results:
- Three days → 20 minutes. A documented past incident was reproduced and resolved in 20 minutes, with the AI's analysis verified as accurate against the original engineering write-up. Similar gains held across other validation cases.
- 30 minutes, by a non-specialist. A customer-support engineer, not a senior engineer, pulled an untouched incident from the queue, used the AI investigation tool, and pinpointed a vehicle electrical fault in roughly half an hour. The result widens the pool of talent who can resolve incidents, freeing senior engineers from being the bottleneck on every case.
- One hour vs. seven days. A support incident that had sat in engineering's queue for seven days was resolved during a one-hour user training session on the new tool.
- Pulled, not pushed. Support engineers testing the AI root cause tool are advocating that it become the standard for incident analysis, rather than needing to be sold on it.
“Manual investigation is an incredibly time-intensive process. If you can get to seventy-five percent trust and twenty-five percent verify, you’re already saving millions of dollars in engineering and investigation time.”
- Rod Lewis (ASI Development Manager)
What’s next with ASI
With the system in active use, Gritmind and ASI are turning to the next set of high-value problems. One priority is integrating additional on-vehicle data directly into Mobius, so investigations no longer require manual data transfer between the vehicle and the investigation workflow. A second is optimizing the investigation tool cost profile so the system scales economically across the large, mixed-OEM customer fleets that Mobius is designed to support. A third is extending the same AI-native pattern to adjacent operational workflows where senior engineering time is the bottleneck. The savings show up in two ledgers: engineer-hours pulled from incident archaeology and customer downtime.
With the system in active use, Gritmind and ASI are turning to the next set of high-value problems. One priority is integrating additional on-vehicle data directly into Mobius, so investigations no longer require manual data transfer between the vehicle and the investigation workflow. A second is optimizing the investigation tool cost profile so the system scales economically across the large, mixed-OEM customer fleets that Mobius is designed to support. A third is extending the same AI-native pattern to adjacent operational workflows where senior engineering time is the bottleneck. The savings show up in two ledgers: engineer-hours pulled from incident archaeology and customer downtime.
Why this project, and what it means for yours
Some workflows absorb AI as a layer. Others only work when AI is load-bearing from day one. Knowing which call is right, technically and economically, is what Gritmind brings to a partnership. ASI’s approach to root cause investigation shows what happens when the rebuild is the right call: senior engineering hours freed from log archeology, customer downtime reduced when the stakes are millions per hour, and a leadership team with the foresight to skip the middle and ask for the end-state.
Some workflows absorb AI as a layer. Others only work when AI is load-bearing from day one. Knowing which call is right, technically and economically, is what Gritmind brings to a partnership. ASI’s approach to root cause investigation shows what happens when the rebuild is the right call: senior engineering hours freed from log archeology, customer downtime reduced when the stakes are millions per hour, and a leadership team with the foresight to skip the middle and ask for the end-state.
The same instinct that produced Mobius, a platform built to adapt to customers rather than require customers to adapt to it, is what led ASI to rebuild incident response with AI at the core instead of patching what was already there. This is the difference between a company that uses AI and a company built to win with it.
Ready to turn insights into impact?
Every bottleneck has a root cause. Whatever challenge you’re facing, we can help you solve it together.