{"resourceId":"ksl-salt-lake-valley-ecc-ai-agent-nonemergency-line-dec-4-20261029","versions":[{"version":"external-aaf72d37d0ec6cbbf02462cd108fbf361daaa032fb3d2eed3e7015cef84f4b12","resource":{"id":"ksl-salt-lake-valley-ecc-ai-agent-nonemergency-line-dec-4-20261029","title":"Salt Lake Valley Emergency Communications Center will put an AI agent on non-emergency lines Dec. 4, covering 600,000 of its 850,000 annual calls","organization":"Salt Lake Valley Emergency Communications Center (Utah)","sector":"911 emergency communications and dispatch","geography":"Salt Lake County, Utah, United States","publishedAt":"2026-10-29","publicationDate":"2026-10-29","eventDate":"2026-12-04","sourceName":"KSL.com","sourceLabel":"KSL: AI agent coming to Salt Lake County non-emergency line","sourceUrl":"https://www.ksl.com/article/51642078/ai-agent-coming-to-salt-lake-county-non-emergency-line","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["operating-model","accessibility-workforce","knowledge-work"],"finding":"KSL reports that the Salt Lake Valley Emergency Communications Center, which dispatches police, fire and EMS countywide, receives about 850,000 calls a year, about 600,000 of them non-emergency. Officials say about 70% of non-emergency calls are routine questions. An AI agent will answer those questions on non-emergency lines only, send information by text or email, and support 30 languages. Executive director Ivan Whitaker says 911 callers will reach a live dispatcher and the AI is set 'very sensitive' to transfer any emergency. Launch is scheduled for Dec. 4, with a public session on Nov. 19 to test the agent and choose its voice.","sledRelevance":"A large multi-agency U.S. communications center is adopting the same non-emergency AI model as smaller counties, with multilingual follow-up and a public preview before launch.","evidence":"Pre-launch announcement quoting the executive director; no performance data exists yet. The 70% routine share is the center's estimate. Vendor not named.","architectureImplications":"Non-emergency lines only, with text and email follow-up and language detection; emergency escalation to a live dispatcher.","governanceImplications":"A public test session before launch is an unusual transparency step other centers can copy; the center should publish how 'very sensitive' escalation is tested.","securityPrivacyImplications":"Sending information by text or email means storing caller phone numbers and addresses; terms are not described.","caveats":"Announcement only; no results; the 'very sensitive' escalation setting is undefined; vendor and cost not given.","streamIds":["emergency-services"],"roles":{"sales":"For sales, the framing point is scale: a countywide center with about 600,000 non-emergency calls a year is adopting an AI agent, with 30 languages and a public test day before its Dec. 4 launch. That makes multilingual service and transparency selling points. A bounded engagement is a pre-launch test plan and post-launch measurement design. The announcement cannot support any claim about containment, accuracy or savings.","engineering":"For pre-sales engineering, the design is an AI agent on non-emergency lines with language detection, text and email follow-up, and sensitive escalation to live dispatchers. Prerequisites are telephony separation, messaging integration and content for routine answers. Constraints include translation accuracy and an undefined escalation threshold. Proof of value should test escalation with scripted emergency phrasings in several languages before launch.","delivery":"For delivery, the work is preparing routine-answer content, configuring escalation and messaging, and running the Nov. 19 public test. Ownership sits with the center's executive director and operations staff. Acceptance should include escalation tests in multiple languages and post-launch containment and transfer reporting. Risks include missed emergencies phrased indirectly, mistranslated information and privacy of messaging data."},"roleDetails":{"sales":{"customerProblem":"About 600,000 non-emergency calls a year compete with 911 for dispatcher attention.","stakeholders":["Center executive director","Member police, fire and EMS agencies","Dispatchers","Residents and language communities","AI vendor"],"discoveryQuestions":["How will you measure escalation sensitivity before launch?","Which languages see the most non-emergency calls?","What will you publish after launch?"],"valueHypothesis":"Answering routine questions with AI and digital follow-up could reduce non-emergency load at scale (interpretation; no data yet).","potentialEngagement":"A pre-launch multilingual escalation test plan and a 90-day post-launch metrics report.","unsupportedClaims":["Any containment or time-saved figure","Translation accuracy","Safety of escalation"]},"engineering":{"fit":"Fits large consolidated centers with heavy routine non-emergency volume.","architectureIntegration":"AI on non-emergency lines with language detection, text and email delivery, and live-dispatcher escalation.","prerequisites":["Separate non-emergency telephony","SMS and email integration","Curated routine-answer content"],"constraints":["Escalation threshold undefined","Translation quality across 30 languages","Vendor not named"],"security":"Protect caller numbers and email addresses used for follow-up; define retention.","proofOfValue":["Scripted emergency phrasings in several languages all escalate","Containment and transfer rates reported after launch","Spot checks of translated messages"]},"delivery":{"work":"Build answer content, configure escalation and messaging, and run public testing before Dec. 4.","dependencies":["Vendor configuration","Member-agency content","Telephony and messaging setup"],"ownership":"Center executive director and operations staff.","skillsAdoption":"Dispatchers learn to receive AI escalations; staff maintain answer content.","governanceCheckpoints":["Pre-launch escalation test sign-off","Public notice of AI use","Post-launch review at 30 and 90 days"],"acceptanceCriteria":["Proposed: all scripted emergency test calls escalate","Proposed: monthly containment and transfer report published"],"risks":["Indirectly described emergencies not escalated","Mistranslated information","Privacy of messaging data"]}},"retrievedAt":"2026-10-29T22:06:52-05:00","enrichedAt":"2026-10-29T22:10:40-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Thirty-language support and native-language follow-up could help limited-English callers if translations are accurate; no workforce impact is stated.","procurementImplications":"A launch date and public preview suggest a contract is in place; terms, cost and vendor are not reported.","operatingModelImplications":"Shifts routine non-emergency information requests to AI with digital follow-up while 911 stays human.","sourceVerification":{"responseId":"curl-ksl-2026-10-29","openedUrl":"https://www.ksl.com/article/51642078/ai-agent-coming-to-salt-lake-county-non-emergency-line","referenceExcerpt":"The new AI agent is designed to answer those questions and send callers information by text or email.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}