{"resourceId":"eagle-mountain-ut-emmie-citibot-ai-assistant-20261102","versions":[{"version":"external-05abbedc72b97b9b87a753d43c6cf0d7536e90ec32c381b0ae74faf367ee33da","resource":{"id":"eagle-mountain-ut-emmie-citibot-ai-assistant-20261102","title":"Eagle Mountain, Utah launches Emmie, a Citibot AI assistant for web chat and text that takes requests in 70+ languages with handoff to staff","organization":"Eagle Mountain City, Utah (vendor: Citibot)","sector":"City constituent services and 311-style requests","geography":"Eagle Mountain, Utah, United States","publishedAt":"2026-11-02","publicationDate":"2026-11-02","eventDate":"2026-11-02","sourceName":"Eagle Mountain City","sourceLabel":"Eagle Mountain City: Meet Emmie, Your 24/7 City Helper","sourceUrl":"https://eaglemountain.gov/eagle-gone-digital-meet-emmie-24-7-city-helper/","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["developers-agents","accessibility-workforce","operating-model"],"finding":"On Nov. 2 the city of more than 80,000 residents announced Emmie, an AI assistant built with Citibot, available by web chat and by text message. The city says residents can ask questions, report issues and submit requests in more than 70 languages, and that Emmie can pass requests to City staff when it cannot help. The post says Emmie is not for emergencies. No usage, accuracy, cost or translation-quality data is given.","sledRelevance":"A fresh example of a small, fast-growing city buying an off-the-shelf AI front door that combines information, request intake, SMS and multilingual access. Citibot is the same vendor whose Denver deployment was rejected by council, so buyers have comparable cases to ask about.","evidence":"City announcement only; operator claims; no metrics, evaluation or contract terms.","architectureImplications":"Web chat and SMS channels feed request intake; the integration with the city's work-order or request system is not described.","governanceImplications":"A human handoff is stated; there is no published AI use policy, accuracy testing or disclosure of translation method in the post.","securityPrivacyImplications":"Text-message intake collects phone numbers and request details; retention and vendor data use are not stated.","caveats":"Launch announcement; no outcomes; translation accuracy across 70 languages unverified.","streamIds":["citizen-engagement"],"roles":{"sales":"Small and mid-size cities are buying packaged AI front doors that take requests by chat and text in many languages. Eagle Mountain's launch is a claim, not a result. Discovery should cover request volume, which languages residents actually use, and how handoffs to staff are tracked. A bounded engagement is a 90-day evaluation plan with baseline call and request data. The source cannot support claims of fewer calls or accurate translation.","engineering":"Engineering fit is a hosted assistant on the city website and an SMS number, feeding request intake with a handoff to staff. Teams should confirm how requests reach the city's work-order system, how the assistant is grounded in city content, and how translation is done. Proof of value should test answers and translated replies in the top resident languages, and check web chat against WCAG with a screen reader.","delivery":"Delivery work is content upkeep, handoff monitoring and a measurement plan. Someone must own the knowledge base and review conversations the assistant could not resolve. Acceptance criteria below are proposals, not observed results. Native-speaker review of translated answers in the most used languages should come before promoting the 70-language claim."},"roleDetails":{"sales":{"customerProblem":"Residents want after-hours answers and request intake without calling City Hall.","stakeholders":["City manager or communications director","Public works and request owners","City IT","Language access or community outreach staff"],"discoveryQuestions":["Which request types should the assistant take, and where do they land?","Which languages do residents use most?","How will handoffs and unresolved questions be measured?"],"valueHypothesis":"An AI front door may handle routine questions after hours; no results are reported yet.","potentialEngagement":"A 90-day evaluation plan with baseline call and request data and translation spot checks.","unsupportedClaims":["Fewer calls or staff hours","Accurate translation in 70 languages","Resident satisfaction gains"]},"engineering":{"fit":"Fits small and mid-size cities without a 311 center.","architectureIntegration":"Hosted chat and SMS assistant grounded in city web content, passing requests and handoffs to staff.","prerequisites":["Current city web content","Request routing rules","Staff handoff queue"],"constraints":["Translation quality unverified","SMS carrier and consent rules","Not for emergencies"],"security":"Set retention limits for chat and text logs and limit vendor reuse of resident data.","proofOfValue":["Test top questions for accuracy","Native-speaker check of translated answers","Screen-reader test of web chat"]},"delivery":{"work":"Run and measure the assistant after launch.","dependencies":["Vendor configuration","Department content owners","Request system integration"],"ownership":"City communications office, with departments owning their answers.","skillsAdoption":"Staff need training on handling handoffs and updating content.","governanceCheckpoints":["30-day review of unresolved questions","Translation spot check","Annual contract and data-use review"],"acceptanceCriteria":["Proposed: every handoff answered by staff within a set time","Proposed: monthly accuracy sample above an agreed threshold"],"risks":["Wrong answers presented as official","Poor translations","Requests lost between assistant and staff"]}},"retrievedAt":"2026-11-03T04:10:00Z","enrichedAt":"2026-11-03T04:10:56Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Multilingual and SMS access may widen reach, but machine translation quality and accessibility for screen-reader users are not addressed.","procurementImplications":"Buyers should ask the vendor for reference results from comparable cities, including ones that ended contracts.","operatingModelImplications":"Staff must monitor handoffs and keep the knowledge base current.","sourceVerification":{"openedUrl":"https://eaglemountain.gov/eagle-gone-digital-meet-emmie-24-7-city-helper/","referenceExcerpt":"She supports more than 70 languages, so more of our neighbors can get help from the City in the language they’re most comfortable using.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}