To say that the software teams at General Motors face unique challenges is an understatement. The automotive company has reached milestones in robotics, self-driving tech and more. But one of the most impressive challenges that the team takes on every day is balancing the pace of AI with the precision required for automotive software.
According to Senior Researcher Arun Adiththan and Software Architect Daniel Struck, the key to using AI safely in automotives is a tightly controlled engineering process.
“AI is most useful when it works inside a structured engineering loop and produces bounded first drafts that engineers can verify,” they said.
To that end, Adiththan and Struck look for opportunities where AI can remove friction — while still leaving human engineers firmly in control of decision-making.
What Does General Motors Do?
General Motors designs, builds and sells vehicles and automotive parts, and also provides software-enabled services worldwide.
“AI delivers its most practical value in automotive software when it helps engineers catch issues earlier, start difficult work faster and keep reviewable progress moving through the development lifecycle,” Adiththan and Struck said. “Even high-friction work becomes easier to start when AI provides a first draft. Together, these gains reduce friction where engineers lose time across the lifecycle.”
Built In spoke with Adiththan and Struck about how their teams use cutting-edge AI to build faster and better automotive software without sacrificing quality, reliability or reviewability.
How is AI changing how your teams build products, solve problems or get work done?
Artificial intelligence is rapidly reshaping software development, but vehicle programs demand more than fast output. In a software-defined vehicle, speed only matters when the resulting software remains readable, testable, maintainable and reviewable inside a tightly controlled engineering process.
GM teams used that lens in a broader research effort across the software development lifecycle. The question was not whether AI could generate code, but where it could reduce friction without weakening the discipline production software requires. Across very different kinds of engineering work, the same pattern emerged: AI is most useful when it works inside a structured engineering loop and produces bounded first drafts that engineers can verify.
Across that lifecycle, GM’s work kept returning to the same question: Where can AI remove friction while keeping engineering judgment firmly in control?
“Across that lifecycle, GM’s work kept returning to the same question: Where can AI remove friction while keeping engineering judgment firmly in control?”
How does your team use AI while maintaining quality, reliability and human judgment?
The difficulty is that automotive software cannot tolerate casual use of AI. A test artifact can miss the intent of a requirement. A cleaned-up embedded C function can still break logic, violate Motor Industry Software Reliability Association coding standards or fail to compile when returned to its module. The central question is not simply whether a model can produce output, but whether that output can withstand engineering scrutiny.
One of the clearest findings from the research was that outcomes depended less on the AI model itself than on how tightly the task was defined around it. When the model was given a narrow, well-scoped task, its output could be checked against a known expectation. When the scope was left open, quality became less reliable. That led to a basic rule for the work — every AI interaction had to be bounded tightly enough that the reviewing engineer could tell whether the result was correct. For real-time compliance guidance, that meant turning experienced-developer knowledge into explicit checking patterns so that each recommendation could be reviewed on its own merits rather than accepted on the model’s judgment alone — the idea behind the Intelligent Virtual Advisor.
The research also exposed clear limits. Larger models often performed better overall, but training also affected outcomes even among models sharing the same architecture. Logical issues in generated code still required human review. Fine-tuning also helped, but compliant code must be selected carefully. Context-window constraints were also a factor, as quality degraded with input size, making segmentation and review essential.
How does your team identify what could move faster or be built better?
GM research followed the friction — the points in the lifecycle where engineers consistently lose time. That friction commonly appears during active development when general-purpose tools lack the domain knowledge to surface violations as they are introduced, leaving issues to accumulate until formal review catches them. It also appears in maintenance, where legacy code carries years of implicit assumptions that make modernization slow and make large, embedded functions expensive to refactor manually. In these areas, the research applied LLM-based methods to produce bounded first drafts that engineers could evaluate and refine, rather than author from nothing.
The need for bounded, reviewable progress becomes clearer in the workflows themselves. Requirements and behavioral intent are carried forward into test cases, then scripts, then executed checks, with engineers reviewing each handoff, so traceability is preserved.
How has AI impacted the workflows on your team?
AI delivers its most practical value in automotive software when it helps engineers catch issues earlier, start difficult work faster and keep reviewable progress moving through the development lifecycle. It shortens the time between introducing a problem and catching it, surfacing quality violations during coding instead of at formal review. Even high-friction work becomes easier to start when AI provides a first draft. Together, these gains reduce friction where engineers lose time across the lifecycle.
That pattern also appears in the measured and observed results. When the work was kept narrow enough to review, smaller-scope refactoring reduced cyclomatic complexity (a standard measure of function complexity) by about 30 percent, validation work pointed toward a more scalable requirement-to-script workflow and expert guidance systems such as Intelligent Virtual Assistants were able to improve the quality of support without moving approval out of engineers’ hands. None of that removes accountability from engineers. AI accelerates the path to a candidate; engineers decide what clears the bar.
