Inventory of NARA Artificial Intelligence (AI) Use Cases
National Archives and Records Administration (NARA) has prepared an inventory of AI use cases including current and planned uses, consistent with the agency's mission. The links below the following table summarize updates to the inventory of AI use cases by year.
| AI Use Case Name | AI Use Case Description | Current Status | What specific AI techniques are used? |
|---|---|---|---|
| Generative AI Solutions for Workplace Productivity | This AI initiative is intended to boost employee productivity by providing intelligent tools to summarize, draft, and navigate operational records more efficiently. | Deployed in production | NARA is integrating Google Gemini into Google Workspace to boost productivity across Gmail, Docs, Sheets, Drive, Meet, and other collaborative tools |
| A1 Museum AI Project |
This AI initiative is intended to solve limited document discoverability by using automated tagging to personalize the visitor experience and make millions of digital records instantly accessible. |
Deployed in production | NARA is leveraging Azure OpenAI to automatically generate tags and topics for approximately 2 million digital records. This AI-driven recommendation system enhances the personalized experience for A1 museum visitors while freeing up staff to focus on other priorities. |
| NARA@WORK Kendra Search | This AI initiative is intended to solve inefficient information discovery by replacing keyword search with a natural language system that provides instant, context-aware answers from disparate agency resources. | Deployed in Production | NARA implemented Amazon Kendra to modernize search on the NARA@Work internal site. Using Natural Language Processing, staff can query agency information—such as benefits and policies—to receive immediate "Suggested Answers." |
| Amelia Earhart AI Search | This AI initiative is intended to efficiently retrieve and prepare all government records related to Amelia Earhart’s final flight for release, in compliance with the Presidential directive of September 26, 2025. | Deployed in Production | NARA is utilizing NLP-based search to modernize information retrieval across its vast holdings. By overcoming the limitations of traditional keyword search, this technology ensures the accurate and timely release of historical records to the public in fulfillment of NARA's legal mandate. |
|
AI Pilot Project to Screen and Flag for Personally Identifiable Information (PII) in Digitized Archival Records |
This AI initiative is intended to solve manual processing bottlenecks and privacy risks by automating the identification and redaction of sensitive information, ensuring rapid and secure public access to digitized collections. |
Pilot (in-progress) | NARA is developing an AI-driven PII detection and redaction solution, currently comparing a custom AWS model against GCP’s native service. The final implementation will be determined by a comparative analysis of testing results from both platforms. |
| AI based Semantic Search for National Archives Catalog (aka ArchiAI) |
This AI initiative is intended to solve the problem of "unsophisticated" keyword-based search limitations by implementing semantic search that understands user intent and historical context, enabling researchers to find relevant records without requiring exact term matches. |
Pilot (in-progress) | NARA is utilizing the Vertex AI platform to develop a semantic search engine for its online catalog. By identifying contextual meanings and hidden connections between documents beyond simple keywords, this tool provides researchers with faster, more comprehensive, and insightful results. |
| Auto-fill of Descriptive Metadata for Archival Descriptions | This AI initiative is intended to solve the "descriptive gap" of labor-intensive cataloging by automatically generating metadata and summaries from document content, allowing NARA to process massive backlogs and make millions of records instantly searchable. | Pilot (in-progress) | NARA is utilizing AI to automatically generate metadata for its digital archives. By streamlining the description process, this tool increases staff efficiency and improves searchability and clarity for the public within the National Archives Catalog. |
|
Topic Summarizer and Entity Extraction Using AI |
This AI initiative is intended to solve the problem of unsearchable digital collections by automating metadata creation for billions of objects, ensuring immediate public discoverability without the need for years of manual archival processing. |
Pilot (in-progress) | NARA is utilizing AI to automatically generate descriptions for its digital objects. This initiative increases staff efficiency and enhances the discoverability and accessibility of materials within NARA’s systems for all users. |
| Create an AI based knowledge articles user interface for working with CGR documents |
This AI pilot is intended to improve the case processing by providing staff with an automated retrieval tool that navigates the complex Case Reference Guide (CRG) to deliver instant, accurate answers for veteran and personnel record requests. |
Pilot (in-progress) | NARA is developing an AI-powered tool to assist National Personnel Records Center (NPRC) staff in navigating the Case Reference Guide (CRG). This solution improves search speed and accuracy, enhancing customer service and reducing training time for new employees. |
|
EOP 42 Search PoC using AI Based Semantic Search |
This AI initiative is intended to solve inefficient retrieval within Presidential email archives by testing whether AI-driven semantic search can understand context and intent more effectively than keyword matching to improve record accessibility. | Pilot (in-progress) | NARA is utilizing the Vertex AI platform to develop a semantic search solution for EOP 42 digital records. By moving beyond traditional keyword matching, this tool provides contextually relevant results, significantly improving navigation through complex email archives and digital materials. |
| Freedom of Information Act (FOIA) Discovery AI Pilot | The AI pilot is intended to solve the problem of larger FOIA backlogs and manual review bottlenecks by automating the discovery of relevant records and the redaction of sensitive data, ensuring responses are both rapid and compliant with privacy laws. | Planned for future pilot (TBD) | NARA will pilot AI to streamline FOIA request processing. By utilizing AI for automated record discovery and PII redaction, this initiative will increase processing speed and accuracy while ensuring full compliance with privacy regulations. |
| Archives.gov AI search | This AI initiative is intended to solve unstructured data challenges by replacing literal-match search with semantic technology that understands researcher intent, connects disparate records, and surfaces results hidden by inconsistent terminology. | Planned for future pilot (TBD) | NARA will develop a semantic search engine for Archives.gov to enhance the public’s research experience. By utilizing AI to identify contextual meanings and connections beyond simple keywords, this tool will provide faster, more accurate, and more insightful search results. |
| Develop a Natural Language Based Chat Interface (like ChatGPT) to Interact With the Archival Documents | This AI initiative is intended to solve high barriers to historical research by replacing complex queries with a natural language interface, allowing users of all skill levels to discover records through simple conversation. | Planned for future pilot (TBD) | NARA will develop an AI-powered chat interface to enable natural language exploration of its digital archives. By allowing users to query records in everyday language, this tool will increase the accessibility of historical documents and provide a more engaging, efficient research experience. |
| Automated Data Discovery and Classification Pilot | This AI initiative is intended to solve inefficient manual data governance by testing automated classification to organize unstructured datasets, accelerate discovery, and accurately identify security or privacy vulnerabilities. | Planned for future pilot (TBD) | NARA will pilot AI-driven data classification to automatically organize and categorize its digital assets. This initiative aims to enhance data visibility and retrieval speed, improving operational efficiency and risk management across the agency. |
2025 NARA AI Use Case Inventory (updated January 2026)
2024 NARA AI Use Case Inventory_Bulk_Upload (updated December 2024)
Any questions regarding the AI inventory can be directed to NARA Responsible AI Officials (RAIO) raio@nara.gov.