{"resourceId":"bac-ninh-peoples-assistant-ai-paperwork-pilot-scale-up-20261016","versions":[{"version":"external-18a9e435ab5fb5ceeedd41172b7273da874544c3b02263cf805fb67179919250","resource":{"id":"bac-ninh-peoples-assistant-ai-paperwork-pilot-scale-up-20261016","title":"Bac Ninh, Vietnam scales its AI \"People's Assistant\" paperwork app after a six-ward pilot reported 98.32% extraction success and over 90% satisfaction","organization":"Bac Ninh municipal People's Committee, Vietnam","sector":"Local administrative services and one-stop service centers","geography":"Bac Ninh, Vietnam","publishedAt":"October 17, 2026 02:31 ICT (October 16, 2026 19:31 UTC)","publicationDate":"2026-10-16","eventDate":null,"sourceName":"VietnamPlus (Vietnam News Agency)","sourceLabel":"State news agency report of municipal pilot results","sourceUrl":"https://en.vietnamplus.vn/bac-ninh-to-expand-ai-app-for-paperwork-after-positive-pilot-results-post353808.vnp","evidenceClass":"government-evaluation","outcomeClass":"emerging","topics":["infrastructure","data-security","operating-model"],"finding":"Bac Ninh tested its AI \"People's Assistant\" app, which scans and recognizes documents, auto-fills information and checks that applications are complete, in six wards. Uptake reached 83.2% in Hiep Hoa and topped 60% in Bac Giang; resident satisfaction exceeded 90%. Testing showed support for about 300 concurrent users on lightweight tasks and document extraction averaging 18.6 seconds per request with a 98.32% success rate. The People's Committee ordered a controlled large-scale pilot in seven-day phases covering 20-30 communes and wards over three months, with a training plan and rollout conference before Oct 20. Science and Technology and city police advise on cybersecurity and personal data protection; ward committees must ensure staff, equipment and connectivity; monthly reports and a final assessment at least 30 days before the pilot ends will decide on official deployment.","sledRelevance":"International example of measured AI document intake at local service counters with explicit scale-up gates; transferable lessons for U.S. permitting and clerk offices on intake completeness checks, with limits given different governance, data-protection and media context.","evidence":"VietnamPlus English article opened in full via curl (gzip-decoded) and text extraction. Metrics are government-reported via the state news agency; no methodology, baseline processing times or error definitions were given.","architectureImplications":"Document OCR/extraction service sized for ~300 concurrent users must scale across 20-30 wards per phase; network connectivity at ward counters is an explicit dependency.","governanceImplications":"Phased pilot with monthly reporting and a final assessment that gates official deployment; chairman decides.","securityPrivacyImplications":"City police and Department of Science and Technology advise on cybersecurity and personal data protection; specifics not given.","caveats":"State media; no independent verification; \"success rate\" and \"satisfaction\" undefined; no baseline for time saved; concurrency limit may constrain scale; governance context differs greatly from U.S. localities.","streamIds":["local-government"],"roles":{"sales":"Sales framing: Bac Ninh reports high extraction success for AI-assisted paperwork intake and is scaling with explicit gates. For U.S. buyers, discovery should focus on intake completeness pain in clerk, licensing and permit counters. A bounded engagement is an intake pre-check pilot with defined accuracy metrics. The evidence cannot support claims of time savings, accuracy in U.S. document types or independent verification. Interpretation: useful as a pattern, not a benchmark.","engineering":"Engineering framing: Fit is document OCR and completeness checking at service counters. Integration requires connecting extraction to case or permit systems and handling roughly 300 concurrent users per deployment. Prerequisites include document templates and required-component rules. Constraints include connectivity at local offices and data-protection review. Proof of value should define extraction success, measure field-level accuracy and compare processing time to baseline. Interpretation: concurrency and connectivity are the scaling risks.","delivery":"Delivery framing: Run phased rollouts across wards, train counter staff, ensure equipment and connectivity, and report monthly. Ownership sits with the Public Administration Service Centre and the People's Committee office. Acceptance criteria should include field-level accuracy, processing time against baseline and incident reporting. Risks include uneven uptake, capacity limits and undefined metrics. Interpretation: define metrics before scaling, not after."},"roleDetails":{"sales":{"customerProblem":"Residents submit incomplete paperwork, slowing local administrative services.","stakeholders":["People's Committee leadership","Public Administration Service Centre","Department of Science and Technology","Ward one-stop units","City police (data protection)"],"discoveryQuestions":["How is extraction success defined?","What is the baseline processing time?","Which document types fail most?","How will capacity scale?"],"valueHypothesis":"Automated completeness checks may reduce rework at counters; time savings not reported.","potentialEngagement":"For U.S. analogs: intake pre-check pilot on one permit or license type with defined accuracy metrics.","unsupportedClaims":["Time saved per application","Independent verification","Transferability to U.S. documents"]},"engineering":{"fit":"Local service counters handling standardized paperwork.","architectureIntegration":"OCR/extraction and completeness rules connected to administrative case systems.","prerequisites":["Document templates","Required-component rules","Counter connectivity"],"constraints":["~300 concurrent users tested","Personal data protection review","Network at ward level"],"security":"Cybersecurity and data protection advised by police and S&T department; details absent.","proofOfValue":["Field-level extraction accuracy","Processing time vs baseline","Load test beyond 300 users"]},"delivery":{"work":"Phased three-month rollout to 20-30 wards per phase with training and monthly reports.","dependencies":["Ward staffing and equipment","Connectivity","Training plan","S&T and police advice"],"ownership":"Public Administration Service Centre with the People's Committee office.","skillsAdoption":"Formal training plan and rollout conference before Oct 20.","governanceCheckpoints":["Monthly reports","Final assessment 30 days before end","Chairman deployment decision"],"acceptanceCriteria":["Proposed: defined extraction accuracy threshold met per ward","Proposed: processing time reduction measured vs baseline","Proposed: incident and data-protection log reviewed monthly"],"risks":["Uneven uptake","Capacity limits","Undefined success metrics"]}},"retrievedAt":"2026-10-16T22:20:55-05:00","enrichedAt":"2026-10-16T22:40:00-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Ward one-stop units must staff and train personnel; uptake varied widely between wards (83.2% vs over 60%).","procurementImplications":"Not reported; vendor or in-house origin unstated.","operatingModelImplications":"AI pre-checks application completeness before submission, shifting staff toward exception handling at one-stop counters.","sourceVerification":{"openedUrl":"https://en.vietnamplus.vn/bac-ninh-to-expand-ai-app-for-paperwork-after-positive-pilot-results-post353808.vnp","referenceExcerpt":"AI-powered document extraction takes an average of 18.6 seconds per request, with a 98.32% success rate.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}