TREAS · TREAS-129 · record R2809

Ask-CFO Research Aide

Department of the Treasury · Internal Revenue Service (IRS)

Overview

Development stage: In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: The output is not presumed to be high-impact and is not used as the principal basis for significant decisions/actions
Start date: Not reported
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Administrative Functions
Operational functions: Document processing and extraction, Search and knowledge retrieval Derived by keyword rules; see methodology

Problem the AI is intended to solve

Ask-CFO is an extension of the Research Aide developed using a COTS platform originally designed for the Joint Committee on Taxation Research Aide (JCR) and Internal Revenue Manual Research Aid (IRMA) use cases. It is a Retrieval Augmented Generation (RAG) search on a number of Chief Financial Officer (CFO) specific documents. In addition to the existing research aide capability and user interface (UI), extensions will be developed to incorporate AI Agents that can perform actions such as document summary comparison over fiscal year, or extract information from tables.

Expected benefits

This will help CFO users search and obtain information from their repository of relevant documents.

System outputs

This system uses an embedding model to produce a vector representation of texts for contextual searching, and Large Language Model to generate a response to user inquiries. Outputs of the tool include the model generated response to a user's inquiry, as well as the text from relevant documents identified in the retrieval stage and used by the model in generating said response.

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: Not reported
Public source code: Not reported

Sourcing

How it was built: Not reported
Vendor (as reported): Not reported
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: Not reported
Privacy Impact Assessment: Not reported
Authorization to Operate: Not reported
Demographic features: Not reported
Training and evaluation data: Not reported
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