OpenAI published an exploratory field report showing how AI coding agents are modernizing scientific software for genomics and other data-intensive fields, with case studies from eight projects primarily in the life sciences.
The report, released July 28, documents how teams used OpenAI’s Codex and Anthropic’s Claude Code to tackle work ranging from routine maintenance and targeted optimization to large-scale language migrations and GPU-native redesigns. Contributors consistently described a shift in the researcher’s role from implementation to verification and orchestration.
One highlighted case involved a widely used genomic data parsing library called cyvcf2. A team used GPT-5.5 to replace the library’s legacy build and packaging system with a modern, unified process, making it easier to install, test and release across platforms.
The researchers noted that coding agents significantly accelerated software development and maintenance, in some cases enabling small teams to take on projects that would otherwise have required far more specialized engineering support. However, they also flagged the ongoing challenge of establishing clear, long-term responsibility and stewardship for agent-generated tools.
“With coding agents, it’s quite easy to go fast; for now, to go far in science, there’s still a need for expert guidance, understanding, taste, and care,” said Brent Pedersen, one of the contributors, in the report.
