NRC · NRC-0001 · record R0063

Text Retrieval and Generation for NRC Staff Support

Nuclear Regulatory Commission · NRC

Overview

Development stage: DeployedSource: c) Deployed – The use case is being actively authorized or utilized to support the functions or mission of an agency.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: 2025-08-01 (day precision)Source: 08/01/2025 00:00:00
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Energy and the Environment
Operational functions: No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

NRC staff are required to discover, retrieve, and analyze information from internally-managed and externally-provided documents. These documents can be lengthy as well as dense with content and often require cross-reference against multiple policies, standards, guidelines, and procedures. The process of discovery, retrieval, analysis, and cross-reference is time consuming and often represents the most significant bottleneck in carrying out agency activities and in making agency decisions.

Expected benefits

This use case enhances the NRC’s efficiency and consistency in licensing, oversight, and other regulatory activities. It enables more efficient capture and use of institutional knowledge to mitigate against the risks associated with staff attrition. The NRC expects this use case to improve the timeliness of its risk- and policy-informed decisions, supporting its mission to enable the safe and secure use and deployment of civilian nuclear energy technologies and radioactive materials.

System outputs

The output is semi-structured content (e.g., text and tables) responsive to the NRC staff's queries.

Technology

AI classification: Generative AISource: Generative AI: AI that generates new or synthetic content (e.g., images, videos, audio, text, code).
System name(s): SimplifAI
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): TekSynap
Vendors (standardized): None on the standard list

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: Where appropriate, prior NRC records are used in concert with subject matter expert review to evaluate the performance of the model's outputs.
Federal Data Catalog: Not reported

Governance

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

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported