Agentic Pipelines in Embedded Software Engineering: Emerging Practices and Challenges
Simin Sun, Miroslaw Staron
TL;DR
The paper addresses the challenge of integrating generative AI into embedded software engineering, where determinism and safety are non-negotiable. It employs a qualitative study with ten senior engineers across four companies to map emerging practices and challenges, revealing eleven practices and fourteen challenges clustered into Orchestrated AI Workflow, Responsible AI Governance, and Sustainable AI Adoption. Key contributions include the Architecture of Agentic Pipelines, AI-Friendly Artifacts, Compiler-in-the-Loop Feedback, and governance-oriented protocols like MCP and AICP, providing concrete guidance for auditable, safe AI adoption in embedded contexts. The findings offer practical implications for standardizing tool interactions, preserving traceability, and aligning organizational strategy with regulatory and certification demands, thereby enabling scalable, responsible AI-augmented embedded software development.
Abstract
A new transformation is underway in software engineering, driven by the rapid adoption of generative AI in development workflows. Similar to how version control systems once automated manual coordination, AI tools are now beginning to automate many aspects of programming. For embedded software engineering organizations, however, this marks their first experience integrating AI into safety-critical and resource-constrained environments. The strict demands for determinism, reliability, and traceability pose unique challenges for adopting generative technologies. In this paper, we present findings from a qualitative study with ten senior experts from four companies who are evaluating generative AI-augmented development for embedded software. Through semi-structured focus group interviews and structured brainstorming sessions, we identified eleven emerging practices and fourteen challenges related to the orchestration, responsible governance, and sustainable adoption of generative AI tools. Our results show how embedded software engineering teams are rethinking workflows, roles, and toolchains to enable a sustainable transition toward agentic pipelines and generative AI-augmented development.