AI-Driven Test Generation for Automotive Engineering
TestForge, built by Context64AI and Emposo, generates test cases from engineering specifications by reasoning over a knowledge graph — delivering a 700% productivity increase and 84% lower end-to-end cost.
Context64AI built a knowledge graph from our specifications, requirements, and CAN bus documentation. Their agents follow our engineers’ actual workflow.
— Engineering Lead · Emposo
Challenge
Automotive OEMs face competing demands at once: expanded test coverage, accelerated timelines, and reduced cost. For Emposo and their customers, test-case creation was a significant organizational constraint:
- Test engineers manually produce test cases from intricate specifications
- HMI, infotainment, and vehicle-bus systems demand highly specialized, granular testing
- Manual processes are time-intensive, costly, and susceptible to error
Cost Baseline
The economics made the bottleneck concrete:
- ~1,000 test cases required ~100 engineering days (~€49,600)
- ~5,000 test cases per project, across ~6 projects annually
- ~€1.5M in annual spend on test creation
Solution: TestForge
Context64AI and Emposo developed TestForge, an AI-powered platform that generates test cases from sophisticated engineering specifications.
Implementation Strategy
- Constructed a knowledge graph incorporating customer specifications, functional requirements, existing test cases, and CAN bus / protocol documentation
- Deployed AI agents that replicate the actual workflow of a test engineer
- Fed generated test cases back into the graph, enabling iterative learning and continuous improvement
The approach centered on reasoning through structured engineering knowledge rather than scraping unstructured information.
Context64AI built a knowledge graph from our specifications, requirements, and CAN bus documentation. Their agents follow our engineers’ actual workflow.
Impact
How test-case creation changed, before and after TestForge:
- ~100 engineering days per batch → ~16 days (7× faster)
- Baseline cost → 84% reduction end-to-end
- Manual, linear effort → 700% productivity increase, with continuous improvement
Because every generated case flows back into the graph, the system keeps getting better at matching the engineering team's intent — turning a one-time automation into a compounding capability.
Key Takeaway
Test automation alone addresses execution, not the creation bottleneck. By anchoring AI in structured engineering knowledge and genuine engineer workflows, TestForge converted test creation from a manual expense center into a scalable, self-improving system.
Challenge
Automotive OEMs face competing demands at once: expanded test coverage, accelerated timelines, and reduced cost. For Emposo and their customers, test-case creation was a significant organizational constraint:
- Test engineers manually produce test cases from intricate specifications
- HMI, infotainment, and vehicle-bus systems demand highly specialized, granular testing
- Manual processes are time-intensive, costly, and susceptible to error
Cost Baseline
The economics made the bottleneck concrete:
- ~1,000 test cases required ~100 engineering days (~€49,600)
- ~5,000 test cases per project, across ~6 projects annually
- ~€1.5M in annual spend on test creation
Solution: TestForge
Context64AI and Emposo developed TestForge, an AI-powered platform that generates test cases from sophisticated engineering specifications.
Implementation Strategy
- Constructed a knowledge graph incorporating customer specifications, functional requirements, existing test cases, and CAN bus / protocol documentation
- Deployed AI agents that replicate the actual workflow of a test engineer
- Fed generated test cases back into the graph, enabling iterative learning and continuous improvement
The approach centered on reasoning through structured engineering knowledge rather than scraping unstructured information.
Context64AI built a knowledge graph from our specifications, requirements, and CAN bus documentation. Their agents follow our engineers’ actual workflow.
Impact
How test-case creation changed, before and after TestForge:
- ~100 engineering days per batch → ~16 days (7× faster)
- Baseline cost → 84% reduction end-to-end
- Manual, linear effort → 700% productivity increase, with continuous improvement
Because every generated case flows back into the graph, the system keeps getting better at matching the engineering team's intent — turning a one-time automation into a compounding capability.
Key Takeaway
Test automation alone addresses execution, not the creation bottleneck. By anchoring AI in structured engineering knowledge and genuine engineer workflows, TestForge converted test creation from a manual expense center into a scalable, self-improving system.
German OEM Builds a Linked Data Layer for Engineering Systems
A large German automotive OEM unified PLM, CAD, requirements, test and supplier data into a single governed knowledge graph — cutting engineering search and rework by 60–70% and laying an AI-ready foundation.
Context-Aware Engineering Intelligence for 3D Models
Threedy’s instant3Dhub combined with Context64AI lets engineers select a part in a 3D model and instantly retrieve the linked engineering knowledge behind it — turning visual discovery into knowledge retrieval.
Engineering data your AI can actually reason over.
Talk to the team behind this work. We will walk you through the architecture, the deployment shape, and the path to your first production agent.