{"resourceId":"brown-county-in-ai-meeting-minutes-pilot-20261008","versions":[{"version":"external-84e3355969d2f83928f3338e44d198931f7d7ac6cb7bf100464bab95c97d2ec1","resource":{"id":"brown-county-in-ai-meeting-minutes-pilot-20261008","title":"Brown County, Indiana IT director presents local-model AI pilot drafting summary meeting minutes from auto-transcripts, claiming hours cut to under an hour","organization":"Brown County, Indiana","sector":"County clerk/records workflow","geography":"Brown County, Indiana, United States","publishedAt":"Oct 8, 2026","publicationDate":"2026-10-08","eventDate":null,"sourceName":"Citizen Portal","sourceLabel":"Meeting summary report","sourceUrl":"https://citizenportal.ai/articles/10652453/indiana/brown-county/brown-county-it-presents-ai-pilot-to-speed-production-of-written-meeting-minutes","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["knowledge-work","infrastructure","operating-model"],"finding":"Citizen Portal reported Brown County's IT director presented a pilot that feeds YouTube auto-generated captions and the meeting agenda into a local AI model to produce a five-page draft summary that staff review and correct. He said it cut staff time from several hours to roughly 45 minutes to an hour (the page renders this as '45—1 minutes') and yields about 95% accuracy when combined with the agenda.","sledRelevance":"A small county using a locally hosted model for minutes is a concrete, low-cost clerk workflow with a self-reported time and accuracy claim.","evidence":"Meeting summary of a staff presentation; time and accuracy figures are self-reported with no stated method, baseline or sample; full story behind newsletter sign-up.","architectureImplications":"Local model avoids sending meeting content to a cloud service; depends on YouTube captions as first layer.","governanceImplications":"Staff review and correction retained; minutes are official records.","securityPrivacyImplications":"Meeting content is public; local hosting limits third-party exposure.","caveats":"Only the page summary was accessible without sign-up; figures are an IT director's claims; the time figure is garbled on the page.","streamIds":["local-government"],"roles":{"sales":"Sales framing: Brown County shows small counties will build minutes automation themselves with local models when cloud tools feel risky or costly. The bounded engagement is helping validate accuracy and records handling, not selling a platform. Discovery should ask how the 95% figure was measured and who signs off minutes. The time and accuracy claims are self-reported and cannot be cited as proven savings.","engineering":"Engineering framing: The pipeline chains auto-captions, agenda context and a local model, so caption quality and speaker attribution set the ceiling. A fit design versions prompts, keeps the transcript and draft for audit, and runs on hardware the county controls. Proof of value should compare drafts with clerk-approved minutes across several meetings and track the error types corrected.","delivery":"Delivery framing: Move the pilot into a defined clerk workflow: who reviews drafts, how corrections are logged and how the final record is retained. Acceptance should include measured review time and correction counts across meetings. Risks include over-trusting drafts, caption errors on names and motions, and support depending on one IT person."},"roleDetails":{"sales":{"customerProblem":"Producing written minutes takes clerks several hours per meeting.","stakeholders":["County IT director","Auditor/clerk","County commissioners"],"discoveryQuestions":["How was 95% accuracy measured?","Who approves AI-drafted minutes?","What hardware runs the local model and who supports it?"],"valueHypothesis":"Drafting time may fall substantially if review remains efficient; unverified.","potentialEngagement":"Accuracy validation of AI-drafted minutes against approved minutes over several meetings.","unsupportedClaims":["95% accuracy as a validated figure","Guaranteed time savings","Readiness for verbatim legal records"]},"engineering":{"fit":"Fits small governments that livestream meetings and publish summary minutes.","architectureIntegration":"Captions plus agenda into a locally hosted model; draft stored with transcript.","prerequisites":["Reliable captions","Agenda in machine-readable form","Local compute"],"constraints":["Indiana records retention","Caption quality","Single-person IT support"],"security":"Local hosting keeps data in county control.","proofOfValue":["Compare drafts with approved minutes for 5+ meetings","Count corrected motions and names","Time the review step"]},"delivery":{"work":"Formalize review, correction logging and retention.","dependencies":["IT support","Clerk participation"],"ownership":"County auditor/clerk with IT.","skillsAdoption":"Train reviewers on common AI errors in motions and votes.","governanceCheckpoints":["Commissioner approval of workflow","Retention schedule mapped"],"acceptanceCriteria":["Review time recorded per meeting","Motion and vote errors tracked to zero in approved minutes","Documented fallback when the model fails"],"risks":["Over-reliance on drafts","Caption errors","Key-person dependency"]}},"retrievedAt":"2026-10-11T22:13:11-05:00","enrichedAt":"2026-10-11T22:20:00-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Shifts clerk work from drafting to review.","procurementImplications":"No procurement or costs reported.","operatingModelImplications":"IT-led pilot; clerk ownership unclear.","sourceVerification":{"openedUrl":"https://citizenportal.ai/articles/10652453/indiana/brown-county/brown-county-it-presents-ai-pilot-to-speed-production-of-written-meeting-minutes","referenceExcerpt":"produces a five-page draft summary that county staff then review and correct","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}