AI Software Engineer: Programming with Trust

Columbia University, USA Large Language Models (LLMs) have shown surprising proficie ncy in generating code snippets, promising to automate large parts of software engineering via artifici al intelligence (AI). We argue that successfully deploying AI software engineers requires a level of trust eq ual to or even greater than the trust established by human-driven software engineering practices. The recen t trend toward LLM agents offers a path toward integrating the power of LLMs to create new code with the powe r of analysis tools to increase trust in the code. This opinion piece comments on whether LLM agents could dominate software engineering workflows in the future and whether the focus of programming will shift from programming at scale to programming with trust. Software engineering is undergoing a significant phase of greater au tomation owing to the emergence of Large Language Models (LLMs) for code.