PermitAI Public-Private Partnership Speeds Environmental Review Drafting Tasks

RICHLAND, Wash.—An innovative public-private partnership has yielded powerful new tools to help federal agencies rapidly synthesize complex data, historical documents and more into draft environmental impact statements.

The benchmark project, called DraftNEPABench, paired the Department of Energy’s Pacific Northwest National Laboratory with corporate partner OpenAI. PNNL’s PermitAI^TM research team worked together with OpenAI over the past year to evaluate whether AI agents originally designed for coding tasks could help draft complex sections of environmental impact statements. These major reports are often required under the National Environmental Policy Act (NEPA) when agencies consider major federal projects such as siting of new data centers or electricity infrastructure.  

“Our evaluation showed that AI coding agents can generate structured and domain-specific draft sections for environmental impact statements with promising results,” said PNNL data scientist and DraftNEPABench research lead Anurag Acharya. “While the systems still require human oversight, the benchmark highlights both the potential and current limitations of these approaches.”

The research team presented the peer-reviewed research at the first annual Association of Computing Machinery Conference on AI and Agentic Systems, held May 27–29, 2026, in San Jose, Calif.

PermitAI^TM began as a pilot project sponsored by the DOE’s Office of Policy to centralize NEPA decision data. Driven by the recent federal priority to accelerate and improve environmental reviews, the PermitAI^TM team has been steadily expanding its focus.

What makes DraftNEPABench unique?

Benchmarks are like standardized tests for AI systems. Researchers use them to evaluate coding and scientific algorithms. But rigorous benchmarks for drafting documents in regulatory settings are largely absent. That’s because until the PermitAI^TM team developed data standards and metadata coding, most environmental permitting documentation remained siloed and inaccessible. Once the team released the machine-readable dataset, known as NEPA Text Corpus (NEPATEC), accessing historical NEPA data and decisions made labor-intensive searches much simpler.

Now, DraftNEPABench can push beyond summarization. It can evaluate systems that write specific subsections following detailed instructions. It can also pull facts from multiple references and is grounded in technical and authoritative sources that can be cited, with pointers to the original documentation for expert review. Unlike a simple AI chat system, a coding agent can break a task into steps, search and extract information from documents, and iteratively refine its draft in ways that mimic how a human analyst works.

Benchmarking environmental impact statements from the real world

The benchmark includes 102 real-world test cases curated from published environmental impact statements spanning 19 government agencies and a range of action types, from energy development to restoration and waste-related projects. Nineteen subject matter experts with drafting experience created the challenge tasks, bringing expertise across disciplines such as biology, geology, engineering, anthropology and law.

DraftNEPABench has now shown potential for speeding up workflows and freeing up experts to focus on more complex analysis and careful review.

“The combination of data science expertise and private-sector AI prowess has produced a system that empowers the federal professionals responsible for scientifically credible and publicly accountable decision-making,” added Sameera Horawalavithana, a principal investigator of the PermitAI^TM project.

DraftNEPABench adds to the growing suite of tools to speed the federal permitting process. Previous releases include SearchNEPA, an interactive AI-driven toolkit with an interface designed for federal NEPA reviewers. SearchNEPA provides a plain language interface for NEPATEC’s more than 140,000 NEPA documents and decisions spanning 50-plus years of data collection, with more coming online regularly as agencies comply with the federal mandate to adopt uniform standards.

Looking to the future, the PermitAI^TM team is expanding its outreach beyond tools for federal agencies to include search functions that can help the public and corporations more rapidly prepare and submit documents required for federal permitting.