TRASE

The Foundation for Autonomous Engineering

Forge, Einride, DREV and Chalmers Industriteknik are collaborating on TRASE, supported by 4.5 MSEK in funding from Vinnova, Sweden's innovation agency. The project develops and deploys agentic systems for safety-critical R&D.

Agentic AI is making the generation of engineering work faster and cheaper. Requirements, analyses, code, and test cases can now be produced at a scale that was previously impossible. As generation accelerates, verification becomes the constraint. In safety-critical R&D, every artifact has to be checked against requirements, applicable standards, system architecture, design decisions, test evidence, and operational data. The relationships among these sources form the engineering context needed to verify agent output. Forge treats this context as the verification layer for agentic engineering.

Verification feedback and operational evidence reveal gaps, informing requirements and driving new system design, implementation, and tests. Once verified and approved, changes enter verification & validation and eventually operation, generating new evidence and engineering feedback. This creates an engineering flywheel in which every cycle strengthens the context available for the next. Agents help teams complete these cycles faster, while traceability and quality gates keep the work reviewable and under human control.

TRASE applies this approach across the engineering lifecycle at Einride and DREV. Forge Studio connects engineering data across tools and teams, giving agents the context needed to work across compliance, specification, implementation, verification, validation, and operational monitoring. Within the project, agentic systems work across requirements, domain knowledge, and test results. Forge records the supporting evidence, checks, and approvals. Defined quality gates determine what can enter the authoritative engineering record, with engineers retaining authority over consequential decisions.

Chalmers Industriteknik leads the development of a shared benchmarking framework for evaluating these capabilities. The framework measures agent capability, grounding in engineering context, traceability to evidence, and reliability across different systems and tasks.

TRASE combines industrial deployment, systematic evaluation, and accountable oversight to establish a rigorous foundation for autonomous engineering. The project helps engineering organizations develop and deploy safe and reliable systems faster, respond with agility to change and preserve human authority over critical decisions.