{"resourceId":"orland-park-humphrey-phone-pause-transfer-fix-govtech-20261106","versions":[{"version":"external-2552f12a261502c19a7ba85d16785513ed91b56ff1decdbe3942060e46f07bf6","resource":{"id":"orland-park-humphrey-phone-pause-transfer-fix-govtech-20261106","title":"Orland Park pauses Humphrey AI phone agent after transfer failures; September metrics show 2,687 calls, 71% transferred, 6% negative, while board funds Gemini staff archive support","organization":"Village of Orland Park, Illinois","sector":"Municipal resident phone and chatbot services","geography":"Orland Park, Illinois, United States","publishedAt":"2026-11-06","publicationDate":"2026-11-06","eventDate":"2026-11-03","sourceName":"GovTech (Daily Southtown / Tribune Content Agency)","sourceLabel":"GovTech: Orland Park, Ill., Works to Fix AI-Powered Phone System","sourceUrl":"https://www.govtech.com/artificial-intelligence/orland-park-ill-works-to-fix-ai-powered-phone-system","evidenceClass":"independent-reporting","outcomeClass":"cautionary","topics":["operating-model","accessibility-workforce","governance-procurement"],"finding":"On Nov. 6, 2026 GovTech republished Daily Southtown reporting that Orland Park paused its Humphrey AI phone agent after October resident complaints that callers could not reach a person. IT Director Tad Spencer said pre-launch tests missed the failure: the system could not transfer callers to the operator or Parks and Recreation because of associated phone numbers, and the village is working with a vendor to add numbers before resume. Of 2,687 September calls, 71% transferred to a department; 91% were perceived neutral and 6% negative. The board also approved a $43,200 Zion Cloud Solutions contract for Google Gemini staff data-archive support (40 hours/month from January), with Spencer citing 97% of staff questions answered and ~$85,000 prior archive cost avoided. Mayor Dodge said the fault was in the phone system, not the AI technology.","sledRelevance":"A Chicago-suburb 311-style AI phone front door that already appeared in the archive as a resident transfer failure now has measured call volume, sentiment, an explicit pause, and a vendor fix plan—exactly the human-transfer control CE tracks for resident voice agents.","evidence":"Syndicated local reporting with named IT director, September operational metrics, pause confirmation, and board contract details; village self-reported sentiment labels.","architectureImplications":"AI phone agent must successfully transfer to live operator and department numbers; vendor work to add numbers before resume; separate Gemini staff knowledge agent on archived ERP data.","governanceImplications":"Board approved Gemini monitoring contract; voice AI paused after public complaints until transfer routing is fixed.","securityPrivacyImplications":"Gemini staff use for archived data storage/query described at high level; resident call-recording and retention not detailed in the article.","caveats":"Sentiment percentages are village-perceived labels; no independent accuracy audit of Humphrey answers; Gemini savings are staff-side, not resident phone outcomes.","streamIds":["citizen-engagement"],"roles":{"sales":"Resident AI phone agents fail when they cannot hand off to a human. Orland Park's Nov. 6 update shows a pause after transfer failures, with September volume and sentiment numbers but no independent answer-accuracy audit. Discovery should ask which queues must always be reachable, what metrics trigger a pause, and who owns the telephony integration. A bounded engagement is a transfer-success baseline before any voice AI go-live. Do not sell Humphrey's pause as proof Gemini will fix resident call routing.","engineering":"Engineering fit is a voice AI front door that must transfer reliably into existing auto-attendants and department DIDs. Confirm number inventory, test matrices that include operator and Parks queues, logging of failed transfers, and a kill switch. Proof of value is transfer success rate, time-to-human, and negative-sentiment share versus the published September baseline—not staff Gemini Q&A alone.","delivery":"Delivery work is telephony remediation plus clear public communication that human reachability is restored before Humphrey resumes. Village IT owns the vendor number fix, while department owners must verify operator and Parks queues in live tests. Acceptance criteria below are proposals. Publish transfer-success and time-to-human before claiming service recovery, and keep an immediate path to a person on every call path."},"roleDetails":{"sales":{"customerProblem":"Residents cannot complete routine village business when an AI phone agent fails to transfer them to staff.","stakeholders":["Village IT","Mayor / Village Board","Parks and Recreation","Resident callers"],"discoveryQuestions":["Which queues must always transfer successfully?","What metric triggers a pause?","Who tests operator and department DIDs before resume?"],"valueHypothesis":"Fixing transfer numbers may restore reachability; unproven until post-fix resume metrics are published.","potentialEngagement":"A transfer-success and time-to-human baseline with a documented pause/resume gate.","unsupportedClaims":["That Gemini staff savings prove Humphrey resident outcomes","Independent accuracy of Humphrey answers","That phone-system blame ends AI product risk"]},"engineering":{"fit":"Fits municipalities putting AI on the main resident phone line with existing auto-attendants.","architectureIntegration":"Voice AI in front of operator and department numbers; separate Gemini agent on archived ERP data for staff.","prerequisites":["Complete DID/auto-attendant inventory","Failed-transfer logging","Documented pause switch"],"constraints":["Pre-launch tests missed the failure mode","Sentiment labels are village-perceived","Resume timing depends on vendor"],"security":"Confirm call recording, retention, and that staff Gemini access to archives respects record controls.","proofOfValue":["Transfer success to operator and Parks","Negative-sentiment share vs September 6%","Time-to-human after resume"]},"delivery":{"work":"Remediate transfer numbers with the vendor and retest before public resume.","dependencies":["Voice AI vendor","Telecom/auto-attendant owners","Department queue owners"],"ownership":"Village IT with board visibility.","skillsAdoption":"Staff need scripts for when AI is paused and how to escalate failed transfers.","governanceCheckpoints":["Vendor fix complete","Board/public notice before resume","30-day post-resume metric review"],"acceptanceCriteria":["Proposed: transfer success above an agreed threshold for operator and Parks","Proposed: published time-to-human after resume"],"risks":["Resume without fixing Parks/operator paths","Residents lose trust after repeated failures","Confusing Gemini staff project with resident phone recovery"]}},"retrievedAt":"2026-11-06T22:06:50-06:00","enrichedAt":"2026-11-06T22:11:17-06:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Residents who could not transfer spent hours or visited Village Hall; restoring human reachability is the immediate accessibility/service requirement.","procurementImplications":"$43,200 one-year Zion Cloud Solutions contract for Gemini platform monitoring starting January; voice-agent vendor remediation underway.","operatingModelImplications":"IT owns troubleshooting with vendor; Parks and Recreation and operator queues must be reachable; public board reporting created the fix trigger.","sourceVerification":{"openedUrl":"https://www.govtech.com/artificial-intelligence/orland-park-ill-works-to-fix-ai-powered-phone-system","referenceExcerpt":"before the village paused using the AI agent due to the complaints","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}