Agentic Pipelines in Embedded Software Engineering: Emerging Practices and Challenges

2026-01-15

AI Summary

This study addresses the open challenge of effectively integrating generative AI into safety-critical, resource-constrained embedded software engineering while meeting stringent requirements for determinism, reliability, and traceability. Through semi-structured focus group interviews and structured brainstorming sessions with ten senior experts from four industry partners, the research systematically identifies eleven emerging practices and fourteen key challenges centered on the orchestration, governance, and integration of generative AI tools. The findings reveal how embedded development teams are strategically reconfiguring their workflows, roles, and toolchains to accommodate AI augmentation. This work provides the first empirical foundation and a sustainable, agent-oriented pipeline transformation pathway for deploying generative AI in safety-critical development contexts.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Embodied AI

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• embedded software engineering
• generative AI
• safety-critical systems
• resource-constrained environments
• AI adoption challenges

Innovation

• agentic pipelines
• generative AI
• embedded software engineering
• AI governance
• sustainable adoption