Hyperpilot and dSPACE Bring AI-Generated Tests to the Entire Automotive Development Lifecycle

London, 5th August, 2026 — Hyperpilot today announced a new integration that allows engineering teams to generate tests directly from requirements and run them across the entire development lifecycle, using the dSPACE Test Automation SDK.

Modern vehicles already run on roughly 100 million lines of code, according to McKinsey, and are projected to reach 300 million by 2030. To put that in perspective, an F-35 fighter jet runs on around 25 million lines. The rise of the software-defined vehicle predates AI by several years; what’s changed is the pace. AI will accelerate how fast that software gets built, but validation won’t keep up. Every new feature, requirements change and software release adds more verification work.

The problem is creating and maintaining the tests that define whether a system works correctly in the first place. In safety-critical industries like automotive, the tests effectively define what “correct” means; the quality of the test suite determines how good, safe and reliable your product is.

A modern car contains up to 150 electronic control units running and between them are thousands of individual software units, each needing its own tests. For a single control unit, the test suite alone can run to tens of thousands of cases, and across the industry, verification and validation consume between 30 and 50 percent of all software development effort. Written manually, test suites move at the pace of engineering teams: authored line by line, updated in batches weeks apart, and reworked every time a requirement changes.

Hyperpilot Studio generates tests directly from requirements. Engineers don’t write test cases by hand, and they don’t prompt a chatbot until the output is usable. Hyperpilot Studio produces complete, executable test suites on its own.

Through the new integration, those test suites export as native dSPACE Test Automation SDK executables. They run, unchanged, across Software-, Hardware-, and Vehicle-in-the-Loop (SiL/HiL/ViL) setups alike to produce one workflow that keeps requirements, software and tests in sync throughout development.

“In safety-critical systems, tests are the specification,” said Elie Talj, Co-Founder and CEO of Hyperpilot. “Software design can already scale, thanks to Hyperpilot’s Algorithm Discovery Engine. The next challenge is making sure validation scales with it. By combining Hyperpilot with dSPACE’s Test Automation SDK, teams can autogenerate thousands of high-quality tests in minutes, straight from requirements, and run them in any setup they choose.”

Hyperpilot Studio moves at machine pace. It generates hundreds of tests per minute for each software unit, and because it works on many units in parallel, output scales to thousands of tests per minute. It produces the complete, traceable suite for a control unit in minutes, and for a full vehicle programme within days. When a requirement changes, the affected tests regenerate at the same speed, so the suite never falls behind the design.

Engineers don’t leave the loop; they move up it. Instead of writing and porting scripts, they review coverage, judge edge cases, and sign off, while Hyperpilot Studio handles the volume. And for teams that send test-writing to outside suppliers today, the most immediate effect is simpler still: the work comes back in-house.

Test-driven development has always been the goal: tests first, then software to pass them. For embedded teams it stayed out of reach because hand-authoring tests was slower than writing the code itself. Hyperpilot removes that constraint allowing tests to be generated automatically, at the speed requirements change.

With the new Test Automation SDK, dSPACE recently expanded its portfolio with a software development kit (SDK) that significantly simplifies automated test execution in Python in software-in-the-loop (SIL) and hardware-in-the-loop (HIL) environments. The SDK allows development and validation teams to create test cases entirely in Python and execute them in both SIL and HIL setups. Users benefit from automated, end-to-end AI-supported test workflows. Further development of the SDK will be open-source and enables users and partners to help shape the solution.

End-to-end, code-based test automation is at the heart of the solution. Instead of working with different tools and interfaces, users describe their tests as easy-to-understand Python scripts. An abstracted programming interface ensures that the same tests can be reused in different test environments. Switching from tests on SIL simulation platforms such as dSPACE VEOS to HIL tests on systems such as dSPACE SCALEXIO is done exclusively via the configuration – the test logic itself remains unchanged.

Hyperpilot and dSPACE are onboarding a limited number of joint pilot programmes with vehicle manufacturers and suppliers. Teams interested in running the workflow on a live programme can get in touch with either company.

About Hyperpilot

Hyperpilot is an AI-native engineering platform for safety-critical systems development. Powered by an engineering foundation model, the platform automates the generation of requirements, tests and control software, so engineering teams can move faster without lowering the bar on safety and quality.

About dSPACE

dSPACE is the world’s leading provider of simulation and validation solutions for developing connected, autonomous, and electrically powered vehicles.T he company employs more than 2,900 people. Its end-to-end tools are used by virtually every major vehicle manufacturer and supplier, as well as by companies in aerospace, defence, industrial automation and medical technology.