LO
DeploymentCognitive automation2026-04-13
Language models generate user stories and summarise workshop outcomes in a deployed system at the US Department of Veterans Affairs, built in-house
Business analystoccupation page →
Event date / reported
2026-04-13 · reported 2026-04-14
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
Writing requirements and user stories
Turning what was learned into requirement documents, specifications and user stories that developers and testers can work from.
Being augmented✓ Evidence-backed
Where this applies
United States, Veterans Health Administration. The agency's inventory entry, marked deployed and developed in-house, says its human-centered design team uses large language models and custom agents, and that the system streamlines tasks such as analysing user feedback, generating user stories, summarising workshop outcomes and refining user personas, with faster insights and less manual labour for staff. It is the agency describing its own system; it does not report effects on staffing or the quality of the stories.
What this means
Drafting user stories and writing up workshops — core analyst output — is being done by language models in at least one large public organisation. The analyst's part shifts towards what goes in and whether what comes out is right.
What it does not yet show
One agency's inventory entry; it does not measure quality, time saved or staffing.
What you can check
Open the 2025 Federal Agency AI Use Case Inventory CSV and find entry VA-24-3164, "generating user stories".
Does it change the assessment?
No. The impact index is never moved by a single event. Nor did this record change a layer: all 1 linked judgement above already rested on earlier evidence. This one adds to them.
Source
Office of Management and Budget — 2025 Federal Agency AI Use Case Inventory, individually reported use cases (Department of Veterans Affairs entry VA-24-3164, Human-Centered Design (HCD) User Feedback Summary, Analysis, and Design) · verified 2026-09-29 · Claude (VOLO agent) · interpreted 2026-09-29 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.