Preparation of Brownfields Success Stories

Overview

Development stage

PilotSource: b) Pilot – The use case has been deployed in a limited test or pilot capacity.

High-impact designation

Not high-impactSource: c) Not high-impact

Impact justification

The output of this AI use case does not serve as a principal basis for decisions or actions that have a legal, material, binding, or significant effect on rights or safety.

Start date

2025-08-15 (day precision)Source: 08/15/2025 00:00:00

Withheld from public reporting

NoSource: a) No

Mission

Topic area

Administrative Functions

Operational functions

Summarization Derived by keyword rules; see methodology

Problem the AI is intended to solve

Preparing draft Brownfields success stories involves compiling and summarizing extensive data from technical reports about site history and environmental assessment/cleanup ads well as financial information about cleanup costs, grant funds, leveraged public/private investment, and jobs leveraged. this information comes from many different sources and can be much more quickly collected and compiled by using AI.

Expected benefits

By leveraging AI to do the heavy lifting of collecting and compiling the data, we can focus our efforts more on the narrative aspect of the success stories and shorten the overall amount of time it takes to prepare stories and publish them on our website, where they can provide inspiration and ideas to other communities who may be struggling with brownfield-related challenges of their own.

System outputs

First draft of text for a Brownfields success story ultimately intended for public viewing on our regional Brownfields program web page. Prompt engineering includes specified format, word count, reading level, writing style, and other parameters to ensure consistency and quality.

Technology

AI classification

Generative AISource: Generative AI: AI that generates new or synthetic content (e.g., images, videos, audio, text, code).

System name(s)

AI-Work

Custom-developed code

No

Public source code

Not reported

Sourcing

How it was built

Developed in-houseSource: b) Developed in-house

Vendor (as reported)

Azure OpenAI

Vendors (standardized)

MMicrosoftOOpenAI

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII

No

Privacy Impact Assessment

Not reported

Authorization to Operate

Yes

Demographic features

k) None of the above

Training and evaluation data

public data from EPA's Assessment Cleanup and Redevelopment Exchange System (ACRES)

Federal Data Catalog

catalog.data.gov ↗

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Potential impacts and how they were identified

Not reported