AI-Enhanced ULS Reverse Engineering

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

Not reported

Start date

2025-01-03 (day precision)Source: 01/03/2025 00:00:00

Withheld from public reporting

NoSource: a) No

Mission

Topic area

Information Technology

Operational functions

No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

Accelerates legacy code analysis and documentation that would otherwise require extensive manual review.

Expected benefits

Accelerates the analysis and documentation of legacy code in the Universal Licensing System (ULS), reducing manual workload and enabling timely reverse engineering. This supports long-term modernization of the ULS application, helping the agency maintain a scalable, reliable licensing system and improving service delivery to the general public.

System outputs

(1) Extracts and documents business logic, data flows, and application architecture from legacy code; (2) Generates visual models such as business process diagrams, integration maps, and data flow diagrams; and (3) Produces structured documentation including source code analysis, performance metrics, and modernization-ready technical artifacts.

Technology

AI classification

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

System name(s)

Not reported

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)

Microsoft Azure Open AI, Securigence

Vendors (standardized)

MicrosoftOpenAI

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

No

Demographic features

k) None of the above

Training and evaluation data

The AI system uses legacy ULS source code including scripts, stored procedures, and application components as input to extract business logic and architecture. These assets are used to evaluate the model’s ability to automate reverse engineering and documentation.

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.

Potential impacts and how they were identified

Not reported