{"resourceId":"workforce-wave-flood-night-eoc-ai-voice-agent-20261103","versions":[{"version":"external-4c8e0ae5effbeb14653850c7aaf6ddd44adef7c1d2d6c0e1dfa839444825f466","resource":{"id":"workforce-wave-flood-night-eoc-ai-voice-agent-20261103","title":"South Florida flood night: city AI voice agent routed 227 of 298 resident calls to the EOC in a median 26 seconds","organization":"Unnamed South Florida city / Workforce Wave","sector":"Emergency management / municipal EOC public line","geography":"South Florida, United States","publishedAt":"2026-11-03","publicationDate":"2026-11-03","eventDate":"2026-11-02","sourceName":"Workforce Wave","sourceLabel":"Vendor research case study with call-volume tables from a partner city's flood activation","sourceUrl":"https://www.workforcewave.com/case-studies/flood-night-ai-voice-agent-emergency-front-door","evidenceClass":"vendor-claim","outcomeClass":"effective","topics":["operating-model","infrastructure","accessibility-workforce"],"finding":"Workforce Wave's Nov. 3, 2026 case study reports that during a South Florida local emergency after Nov. 1 flooding, an existing municipal AI voice agent on the city's public line was reconfigured the same afternoon to route flood/EOC intents. From Nov. 2 ~noon to Nov. 3 10:42 PM ET (~35 hours), the agent answered 298 resident calls and connected 227 to the EOC phone bank (median 26 seconds greeting-to-handoff; ~22 seconds for yes-to-greeting callers). Ten EOC connections occurred midnight–7 AM. Other outcomes: 21 answered/redirected without transfer, 31 hung up under 20 seconds, plus small transfers to city/water/admin lines. Life-threatening callers were told to hang up and dial 911; the agent never transfers those. City, partner, and residents are unnamed. Platform reliability claims (99.69% of 36,080 agency calls YTD) are vendor-reported.","sledRelevance":"Direct U.S. emergency-management signal: shows how a non-emergency municipal voice agent can be pressed into EOC surge routing without changing the city's PBX, with measured handoff latency—useful for coastal and flood-prone SLED agencies, with strong vendor-claim caveats.","evidence":"Case study dated November 3, 2026 by Colin P. Highland; disposition table for 298 calls; states 'Connected' means network handoff to the EOC line; reliability figures cover Jan 1–Oct 13, 2026.","architectureImplications":"Keep emergency pathways as configurable routes on an existing public voice agent (greeting question + flood lexicon → EOC) rather than publishing a new number mid-disaster; preserve hard 911 hang-up guidance with no AI transfer of life-threat calls.","governanceImplications":"EOC surge configs need pre-approved playbooks, logged change control, and post-incident review of misroutes—especially when the public line is branded as the EOC number in local news.","securityPrivacyImplications":"Automatic capture of caller phone numbers without name intake speeds handoff but still creates PII/call-detail records that must follow municipal retention and disclosure rules; cloud hosting outside the disaster zone is claimed as resilience.","caveats":"Vendor-authored case study; city unnamed; no independent audit; no clinical or property-loss outcomes; 'connected' is telephony handoff, not confirmed human answer or resolved need; bilingual example is anecdotal.","streamIds":["emergency-services"],"roles":{"sales":"Sales framing: during a South Florida flood emergency, a city's existing AI public-line agent was pointed at the EOC and, per the vendor case study, connected 227 of 298 resident calls in about 35 hours with a median 26-second handoff while keeping life-threat callers on a hang-up-and-dial-911 path. For U.S. emergency managers and 911 boards, the bounded value is proving whether a pre-built municipal voice agent can absorb EOC surge without a new published number. This is a vendor claim from an unnamed city—do not sell guaranteed 26-second EOCs, flood outcomes, or 911 replacement.","engineering":"Engineering framing: implement flood/EOC as a same-day route change—greeting yes-path and flood/standing-water lexicon to the EOC trunk, skip name intake on emergency routes, auto-log ANI, and hard-block transfer of declared life threats to anything but 911 instructions. Preserve ordinary department routing in parallel. Validate barge-in, Spanish/English switch, and overnight staffing of the EOC queue the agent feeds. Limits: unnamed city telephony and no independent packet captures.","delivery":"Delivery framing: before storm season, tabletop an 'emergency pathway' switch with EOC supervisors, communications, and the voice-agent operator; define which intents go to EOC vs utilities; rehearse 911 diversion language; and set a post-event audit of the 298-call-style disposition table (EOC connect, self-serve, abandon). Acceptance is measured handoff latency and zero AI transfers of life-threat calls—not flood-damage reduction, which this source does not show."},"roleDetails":{"sales":{"customerProblem":"EOCs need a public phone front door that stays up and routes flood callers quickly when city hall lines and staff are disrupted.","stakeholders":["Emergency management director","EOC phone-bank lead","City communications","911/PSAP coordinator","Municipal IT/telephony","Elected officials"],"discoveryQuestions":["Is there already an AI or IVR on the main city line that can gain an EOC route without a new number?","Who authorizes same-day greeting and intent changes during a declared emergency?","How are life-threat callers forced to 911 rather than EOC transfer?","Will post-event call dispositions be publishable?"],"valueHypothesis":"If a city already runs a public voice agent, a pre-approved EOC pathway may cut median handoff toward the tens of seconds under flood surge—operational access value only, as claimed here.","potentialEngagement":"Bounded readiness workshop: design and tabletop an emergency voice-agent pathway with metrics matching this disposition table.","unsupportedClaims":["Guaranteed 26-second EOC connect in any city","Property or life-safety outcomes from the flood","That the unnamed city's results generalize","Replacement of 911 by the voice agent"]},"engineering":{"fit":"Fits municipal voice agents / contact-center AI that already route non-emergency calls and can add disaster intent trees.","architectureIntegration":"Public DID → cloud voice agent → conditional transfer to EOC ACD; ANI capture; no life-threat transfer; parallel normal department routes.","prerequisites":["Existing public-line agent with changeable prompts","EOC trunk/ACD capacity for overnight surge","Intent lexicon for flood/evac/shelter","Logged configuration versions"],"constraints":["Unnamed city and partner stack","Vendor self-report of connect rates","Resident cellular outages still limit reachability"],"security":"Treat ANI, recordings, and transcripts as sensitive municipal emergency records; restrict vendor access and define retention.","proofOfValue":["Reproduce disposition table in a flood drill","Measure median greeting-to-EOC connect with EOC answer confirmation","Verify life-threat utterances never transfer"]},"delivery":{"work":"Build and exercise a flip-switch emergency pathway with EOC staffing plan and after-action metrics.","dependencies":["Voice-agent operator","EOC supervisors","City PIO for published number messaging","PSAP liaison for 911 boundary"],"ownership":"Emergency management owns pathway activation; telephony/IT owns config; EOC floor owns answering capacity.","skillsAdoption":"EOC call-takers need scripts for AI-handed callers; PIO needs clear public wording that the AI is a router not a 911 substitute.","governanceCheckpoints":["Pre-season pathway approval","Activation logged under emergency declaration","Post-event disposition and misroute review"],"acceptanceCriteria":["Median handoff at or below agreed SLA in drill","Zero life-threat transfers in test set","Published after-action with disposition counts"],"risks":["Public confusion if news lists AI number as 'EOC'","EOC queue overload from easy connects","Vendor narrative outrunning independent verification"]}},"retrievedAt":"2026-11-07T04:05:20Z","enrichedAt":"2026-11-07T04:12:46Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Spanish-then-English example suggests language switching helps some callers, but equity for disability, low-literacy, and cell-outage populations is not measured; overnight EOC staffing remains the bottleneck the agent feeds.","procurementImplications":"Prefer contracts that already include emergency-pathway change rights, audit logs, and post-incident data exports rather than buying a new flood chatbot mid-event.","operatingModelImplications":"Treat the public voice agent as dual-use: day-to-day 311-like routing plus a declared-emergency EOC front door with human answer capacity sized for the connect rate.","peerReview":"unknown","sourceVerification":{"openedUrl":"https://www.workforcewave.com/case-studies/flood-night-ai-voice-agent-emergency-front-door","referenceExcerpt":"connected 227 of them to the Emergency Operations Center, with a median of 26 seconds","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}