|
Organizes large volumes of text, such as public comments from Regulations.gov
|
- Groups contents by similar themes
- Prioritizes reviews based on relevant hierarchical topics
|
Late-stage prototype |
- Natural language processing
- Topic modeling
- Sentiment analysis
- Semantic matching
|
| Summarizes draft GAO legislative mandates |
- Increases efficiency and reduces manual processes
- Highlights potentially fragmented and duplicative mandates
|
Late-stage prototype |
- Natural language processing
- Large language model
- Semantic matching
- Regular expressions
|
| Assists with copyediting according to GAO’s style guide |
- Automates select copyediting tasks
- Enables staff to focus on narrative structure and clarity
|
Late-stage prototype |
- Natural language processing
- Neural network modeling
- Sentiment analysis
|
| Provides automated responses to chat questions on published GAO work |
- Summarizes published GAO content to enhance knowledge management and increase efficiency
- Enhances specificity and accuracy of results
|
Early-stage prototype |
- Large language model configuration
- Prompt engineering
- Retrieval-augmented generation
- User telemetry measurement
|
| Summarizes qualitative responses from annual GAO Employee Experience Survey |
- Identifies trends, patterns, and sentiments quickly
- Improves survey interpretation with less manual intervention
- Assists with root-cause analyses
|
Early-stage prototype |
- Natural language processing
- Large language model
|
| Monitors information about congressional committee calendars, press releases, and web contents |
- Matches congressional interests with relevant GAO work
- Enhances timeliness of outreach and technical assistance
|
Early-stage prototype |
- Natural language processing
- Large language model
- Semantic matching
|
| Enhances GAO auditing through use of extended reality glasses |
- Improves data collection and collaboration across locations
- Reduces costs and risks
- Enables new data capturing and analysis opportunities
|
Concept exploration |
- Computer vision and object recognition
- Real-time image, video, and sensor data processing
|
| Triages IT help desk requests and answers internal GAO policy questions |
- Provides 24/7 self-service assistance to GAO employees
- Allows support staff to focus on more complex requests
|
Concept exploration |
- Natural language processing
- Large language model
- Sentiment analysis
- Integrated workflow and escalation
|
