{"resourceId":"spectrum-dane-county-ava-first-month-20260928","versions":[{"version":"external-04decfdfe6d6ed8074a816397cd4f3673d9923fc5598d461a5a804483cdbf70c","resource":{"id":"spectrum-dane-county-ava-first-month-20260928","title":"Spectrum News: Dane County AVA handled 24,000+ non-emergency calls in first month with no major mistakes reported","organization":"Dane County Public Safety Communications (Wisconsin) / Spectrum News 1","sector":"County PSAP / emergency communications","geography":"United States (Wisconsin)","publishedAt":"2026-09-28","publicationDate":"2026-09-28","eventDate":"2026-09-28","sourceName":"Spectrum News 1 Wisconsin","sourceLabel":"Local TV reporting on Dane County's one-month AVA non-emergency line update","sourceUrl":"https://spectrumnews1.com/wi/milwaukee/news/2026/09/28/dane-county-public-safety-ai-non-emergency-calls","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["operating-model","accessibility-workforce","governance-procurement"],"finding":"Spectrum News 1 reports (Sept 28, 2026) that Dane County's AVA voice assistant handled more than 24,000 non-emergency calls in roughly its first month. The deputy director said there were no major mistakes and attributed misses to how the county programmed the system. Staff rotate monitoring AVA so a communicator can call back if an emergency is missed; callers can ask for a human. Eleven months of the trial remain.","sledRelevance":"Direct 911-center evidence that conversational AI on non-emergency lines is being run as a staffed, monitored trial, with emergency detection on the non-emergency line called out as a key function.","evidence":"Local TV reporting quoting a communicator and the deputy director; the 24,000-call count and 'no major mistakes' are agency statements with no published error log, missed-emergency count, or 911 answer-time baseline.","architectureImplications":"Voice agent on the non-emergency trunk with keyword/warning-sign detection that forwards to a human dispatcher, an opt-out-to-human path, and a staffed monitoring seat with call-back capability.","governanceImplications":"A 12-month trial with early public reporting is a reasonable governance model, but 'no major mistakes' needs a defined error taxonomy and published missed-escalation counts to be auditable.","securityPrivacyImplications":"Article does not describe recording retention, vendor data use, or how transcripts are stored; agencies should require these terms before go-live.","caveats":"One month of operation; metrics are agency-reported; no independent evaluation; 'mistakes' defined informally by the agency.","streamIds":["emergency-services"],"roles":{"sales":"Frame Dane County's first month as an operating-discipline story: 24,000+ non-emergency calls handled, a staffed monitoring rotation, and an opt-out-to-human path. The useful conversation with a PSAP is not 'will AI take calls' but 'who watches it and how fast can you call back a missed emergency.' Position any engagement around defining what counts as a mistake and reporting it, since this evidence is an agency statement, not an evaluation.","engineering":"Treat AVA as a voice agent on the non-emergency trunk with keyword-based emergency detection and a human forward path. The deputy director says misses came from programming, so the engineering work is route and trigger configuration, test-call suites, and logging that ties each forwarded or missed emergency to a rule. Validate against recorded calls before expanding scope; nothing here shows performance on ambiguous or multilingual emergency cues.","delivery":"Stand up the trial like Dane County: a named monitoring rotation, call-back procedure for suspected misses, opt-out-to-human, and a clear trial end date. Add what the article lacks: a written error taxonomy, weekly missed-escalation review, and a public summary at the midpoint. Acceptance should hinge on escalation accuracy and dispatcher time recovered, not on call volume alone."},"roleDetails":{"sales":{"customerProblem":"Non-emergency calls tie up call takers who also answer 911.","stakeholders":["PSAP director/deputy director","Communicators/dispatch staff","County board","Callers needing human access"],"discoveryQuestions":["What share of your lines are non-emergency?","Who monitors the AI and how often?","How do you define and count a mistake?","What happens when an emergency is missed?"],"valueHypothesis":"A monitored voice agent may absorb routine non-emergency volume if emergency forwarding and call-back are reliable; value must be shown in recovered dispatcher time.","potentialEngagement":"Trial governance package: error taxonomy, monitoring SOP, and midpoint public report template for a 12-month non-emergency AI trial.","unsupportedClaims":["Faster 911 answer times (not measured)","Zero missed emergencies","Staff reductions"]},"engineering":{"fit":"Non-emergency voice front door with emergency keyword detection and human forwarding.","architectureIntegration":"Non-emergency trunk to AVA; forward to communicator on emergency cues or caller request; monitoring seat with call-back.","prerequisites":["Call-type and keyword rule set","Human forward and opt-out routing","Monitoring console and call logs","Test-call library"],"constraints":["Agency-reported results only","One month of data","Keyword detection may miss indirect emergency cues"],"security":"Confirm recording retention, transcript storage, and vendor data-use terms; not described in the article.","proofOfValue":["Missed-escalation rate on seeded test calls","Share of forwarded calls that were true emergencies","Dispatcher minutes recovered per week"]},"delivery":{"work":"Configure routes and emergency triggers, staff a monitoring rotation, publish caller opt-out, and run a fixed-term trial.","dependencies":["Vendor configuration support","Telephony/trunk changes","Staff scheduling","County board oversight"],"ownership":"Public Safety Communications operations owns monitoring, call-backs, and configuration decisions.","skillsAdoption":"Train communicators to review AI calls, flag misconfigurations, and coach callers to speak naturally.","governanceCheckpoints":["Go-live sign-off on emergency triggers","Weekly miss review","Midpoint public report","Renewal decision at trial end"],"acceptanceCriteria":["Every suspected missed emergency reviewed within one shift","Opt-out to human honored on 100% of requests","Documented error taxonomy in place before go-live"],"risks":["Indirect emergency language not recognized","Monitoring fatigue","Over-reliance on agency-defined success"]}},"retrievedAt":"2026-10-04T22:01:35-05:00","enrichedAt":"2026-10-04T22:01:35-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Staff take turns monitoring AVA, which shifts some dispatcher time to oversight; callers may opt out to a human, which matters for callers who struggle with voice agents.","procurementImplications":"Trial-period structure (11 months remaining) gives the county a decision point; buyers should tie renewal to measured escalation accuracy rather than call counts.","operatingModelImplications":"Human-monitored AI front door on the non-emergency line, with misses treated as configuration problems the center owns.","sourceVerification":{"responseId":"curl-spectrum-dane-2026-10-04T22:01:35-05:00","openedUrl":"https://spectrumnews1.com/wi/milwaukee/news/2026/09/28/dane-county-public-safety-ai-non-emergency-calls","referenceExcerpt":"an artificial intelligence voice assistant has handled more than 24,000 non-emergency calls since the county launched the program about a month ago","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}