Organizations: Chalmers University of Technology Gothenburg, Sweden · University College London London, United Kingdom · Volvo Group Gothenburg, Sweden
Multidisciplinary Software Development (MSD) requires domain experts and developers to collaborate across incompatible formalisms and separate artifact sets. Today, even with AI coding assistants like GitHub Copilot, this process remains inefficient; individual coding tasks are semi-automated, but the workflow connecting domain knowledge to implementation is not. Developers and experts still lack a shared view, resulting in repeated coordination, clarification rounds, and error-prone handoffs. We address this gap through a graph-based workflow optimization approach that progressively replaces manual coordination with LLM-powered services, enabling incremental adoption without disrupting established practices. We evaluate our approach on spapi, a production in-vehicle API system at Volvo Group involving 192 endpoints, 420 properties, and 776 CAN signals across six functional domains. The automated workflow achieves 93.7% F1 score while reducing per-API development time from approximately 5 hours to under 7 minutes, saving an estimated 979 engineering hours. In production, the system received high satisfaction from both domain experts and developers, with all participants reporting full satisfaction with communication efficiency.
Figures & tables
Figure 1. Comparison of workflows in the Multidisciplinary Software Development (MSD) process: (a) a typical MSD workflow and (b) optimized workflow through automated translation via our graph-based approach.
Figure 2. Iterative workflow optimization framework for vehicle API generation. The upper part illustrates graph-level optimization, depicting how the initial manual workflow undergoes three iterative refinements to achieve a highly automated workflow. The lower-right part illustrates the final deployed workflow, which comprises three server nodes. The lower-left part illustrates the detailed structure of each node.
Dimension
Score
Description
Complexity
-1
Task or exchange removed or combined
0
No change
+1
Task or exchange added
Automation
-1
Task becomes more manual
0
No change
+1
Task becomes more automatic
Table 1. Scoring scheme for transformation impact across three dimensions
Figure 3. A simplified DSPy signature for Signal R/W Synthesis. The LLM generates Python functions to read or write CAN signals based on signal metadata.
Figure 4. Representative prompt used in the Signal-Property matching task (simplified for clarity).
Figure 5. Example of a FastAPI endpoint boilerplate template.
Figure 6. A representative prompt used in the API Endpoint synthesis task (simplified for clarity).
Iteration
Comp.
Auto.
Comm.
1: Signal R/W
-1
+1
+2
2: Signal-Property
-2
+1
+2
3: Property-Endpoint
-2
+1
+2
Net change
-5
+3
+6
Table 2. Cumulative transformation impact across three iterations.