Ensuring reliable data-driven decisions is crucial in domains where analytical accuracy directly impacts safety, compliance, or operational outcomes. Decision support in such domains relies on large tabular datasets, where manual analysis is slow, costly, and error-prone. While Large Language Models (LLMs) offer promising automation potential, they face challenges in analytical reasoning, structured data handling, and ambiguity resolution. This paper introduces GateLens, an LLM-based architecture for reliable analysis of complex tabular data. Its key innovation is the use of Relational Algebra (RA) as a formal intermediate representation between natural-language reasoning and executable code, addressing the reasoning-to-code gap that can arise in direct generation approaches. In our automotive instantiation, GateLens translates natural language queries into RA expressions and generates optimized Python code. Unlike traditional multi-agent or planning-based systems that can be slow, opaque, and costly to maintain, GateLens emphasizes speed, transparency, and reliability. We validate the architecture in automotive software release analytics, where experimental results show that GateLens outperforms the existing Chain-of-Thought (CoT) + Self-Consistency (SC) based system on real-world datasets, particularly in handling complex and ambiguous queries. Ablation studies confirm the essential role of the RA layer. Industrial deployment demonstrates over 80% reduction in analysis time while maintaining high accuracy across domain-specific tasks. GateLens operates effectively in zero-shot settings without requiring few-shot examples or agent orchestration. This work advances deployable LLM system design by identifying key architectural features—intermediate formal representations, execution efficiency, and low configuration overhead—crucial for domain-specific analytical applications where accuracy, traceability, and stakeholder trust are paramount.

Vehicle API testing verifies whether the interactions between a vehicle's internal systems and external applications meet expectations, ensuring that users can access and control various vehicle functions and data. However, this task is inherently complex, requiring the alignment and coordination of API systems, communication protocols, and even vehicle simulation systems to develop valid test cases. In practical industrial scenarios, inconsistencies, ambiguities, and interde-pendencies across various documents and system specifications pose significant challenges. This paper presents a system designed for the automated testing of in-vehicle APIs. By clearly defining and segmenting the testing process, we enable Large Language Models (LLMs) to focus on specific tasks, ensuring a stable and controlled testing workflow. Experiments conducted on over 100 APIs demonstrate that our system effectively automates vehicle API testing. The results also confirm that LLMs can efficiently handle mundane tasks requiring human judgment, making them suitable for complete automation in similar industrial contexts.

A practical method for the design of an in-vehicle wireless sensor network operating in a truck is presented. The network has been dimensioned using promising candidate sensor applications that were chosen based on a set of key criteria including safety, security, and timing-criticality and commercial viability. An extensive set of experiments were carried out to determine characteristics, feasibility and ease of integration of such a network into the vehicle electrical system. A network of 10 node positions and 3 possible gateway positions was used as a reference platform. Initial results indicate that for truck variants with up to 5 axles, there is near universal coverage using 2.4 GHz IEEE 802.15.4 radios with link budgets above 100 dB. Links between sensors and all gateway positions have been found to support above 90% packet reception rates at received signal strengths of about -70 dBm, with gateway positions in the central and rear chassis areas performing best. Current estimates are that such a network is robust enough to support sensors of low safety, security and timing criticality.