NARA · NARA - 0010 · record R3206

EOP 42 Search PoC using AI Based Semantic Search

National Archives and Records Administration · National Archives & Records Administration (NARA)

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: Not reported
Start date: 2026-12-01 (day precision)Source: 2026-12-01T00:00:00
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Other
Operational functions: Search and knowledge retrieval Derived by keyword rules; see methodology

Problem the AI is intended to solve

The AI is intended to solve the problem of inefficient information retrieval within Presidential email archives by testing whether AI-driven semantic search can understand context and intent more effectively than traditional keyword matching to improve record accessibility.

Expected benefits

The purpose of this Proof of Concept (POC) is to evaluate whether AI-driven semantic search provides a demonstrable improvement over the current keyword-based search experience for accessing EOP 42 digital records, including email archives.

System outputs

The AI system's output will be significantly improved search results that are contextually relevant (semantic), effectively bypassing the limitations of simple keyword matching within EOP 42 digital records, thereby offering a demonstrable improvement in the search experience for users accessing materials, including complex email archives.

Technology

AI classification: Natural language processingSource: Natural Language Processing: AI that processes, interprets, and shares information in human language.
System name(s): EOP 42
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): Skylight
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: Yes
Privacy Impact Assessment: Not reported
Authorization to Operate: Yes
Demographic features: k) None of the above
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