{"resourceId":"salta-muni-bot-whatsapp-assistant-20261001","versions":[{"version":"external-c7b42c527da897b03763c4113abc65d775963c1c87612deeed4dea1060aac99f","resource":{"id":"salta-muni-bot-whatsapp-assistant-20261001","title":"Salta, Argentina replaces its municipal app with in-house AI 'Muni Bot' on WhatsApp that starts and tracks resident requests","organization":"Municipalidad de la Ciudad de Salta","sector":"Resident services / municipal service requests","geography":"Salta, Argentina","publishedAt":"October 1, 2026 (Todo el Día)","publicationDate":"2026-10-01","eventDate":"2026-10-01","sourceName":"Todo el Día","sourceLabel":"Local news report","sourceUrl":"https://www.todoeldia.com/index.php/2026/10/01/muni-bot-salta-lanza-un-asistente-virtual-con-inteligencia-artificial-para-agilizar-los-tramites-municipales/","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["accessibility-workforce","developers-agents","operating-model","data-security"],"finding":"Salta launched Muni Bot, an in-house AI assistant on WhatsApp that replaced the Muni Salta app, which stopped working Sept. 30. Residents describe needs in their own words; the assistant asks follow-up questions, explains requirements, documents, hours and locations, starts requests and checks status. It accepts location, photos and voice notes, shows a summary for confirmation before submission and issues a tracking number. When another body is responsible it points residents there.","sledRelevance":"Example of a city retiring a standalone app in favour of a conversational intake agent on a messaging channel residents already use, built in-house—relevant to 311 and service-request design in smaller governments.","evidence":"News account of features and channel; no usage, accuracy, cost or data-handling information.","architectureImplications":"Conversational intake connected to the city's case system: intent capture, slot-filling questions, media attachments, confirmation summary and case-number lookup.","governanceImplications":"Interpretation: the confirmation summary before submission is a resident-side control; data retention of photos, voice notes and location via WhatsApp needs explicit policy.","securityPrivacyImplications":"Location, images and audio pass through a third-party messaging platform; the article does not describe retention or consent.","caveats":"Single local report; no performance data; dependence on WhatsApp.","streamIds":["local-government"],"roles":{"sales":"Sales framing: Salta replaced a failing municipal app with an in-house WhatsApp agent that starts and tracks requests, showing cities will move intake to channels residents already use. Conversations should focus on case-system integration, routing accuracy and data handling for photos, voice and location. Because the city built it, partnership or support offers fit better than replacement. The report has no usage or accuracy data, so avoid claiming faster resolution or higher satisfaction.","engineering":"Engineering framing: Fit is a messaging-channel intake agent connected to the case management system, collecting structured fields through follow-up questions and confirming a summary before creating a ticket. Key integration points are the case system, media storage for photos and audio, and status lookup by tracking number. Constraints are WhatsApp platform terms, Argentine data-protection law and voice-note transcription quality. Validate routing accuracy and field completeness on a sample of real requests.","delivery":"Delivery framing: Running an intake agent in production means owning knowledge content, routing rules and the hand-off to departments. Assign a service owner, publish an alternative channel for residents without WhatsApp, and set retention rules for photos, audio and location. Review a weekly sample of conversations for misrouted or incomplete requests, and track tracking-number lookups and repeat contacts. Report those measures before adding new request types."},"roleDetails":{"sales":{"customerProblem":"Residents struggled to know which department handles a request, and the previous municipal app stopped working.","stakeholders":["Municipal modernization/IT team","Department service managers","Resident-services leadership","Legal and data-protection staff"],"discoveryQuestions":["Which request types can the bot create directly?","How are requests routed to departments?","How long are photos, audio and location kept?","What channels exist for residents without WhatsApp?"],"valueHypothesis":"Conversational intake on a familiar channel may raise request completeness and reduce misdirected contacts; no data reported.","potentialEngagement":"A routing-quality and data-handling review of a sample of bot-created requests.","unsupportedClaims":["Muni Bot reduces resolution times","Residents prefer the bot to the old app","The bot handles all municipal procedures"]},"engineering":{"fit":"Fits structured service-request intake through messaging with confirmation and tracking.","architectureIntegration":"WhatsApp Business channel → AI conversation layer (intent and follow-up questions) → case system API → tracking number → status queries.","prerequisites":["Case system API","Curated procedure knowledge","Media storage","Routing rules per department"],"constraints":["WhatsApp platform terms","Argentine data-protection law","Voice transcription accuracy","Single-channel dependence"],"security":"Minimize retained media, restrict access to case attachments, log conversation-to-case linkage, and publish a privacy notice in the chat.","proofOfValue":["Measure misrouting on 100 sampled requests","Check field completeness versus web forms","Test voice-note understanding across accents"]},"delivery":{"work":"Operate Muni Bot as a service with content upkeep, routing review and data rules.","dependencies":["Department participation","Messaging platform availability","Developer capacity in-house","Legal review of data handling"],"ownership":"Municipal modernization/IT office, with departments owning their request types.","skillsAdoption":"Department staff trained to handle bot-created cases and update procedure content.","governanceCheckpoints":["Privacy notice and retention rule approved","Monthly routing-quality review","Approval before adding new request types"],"acceptanceCriteria":["Routing error rate tracked monthly","Alternative non-WhatsApp channel published","Retention rule applied to all media"],"risks":["Misrouted requests","Exclusion of residents without WhatsApp","Platform dependency","Unstated data retention"]}},"retrievedAt":"2026-10-05T22:14:32-05:00","enrichedAt":"2026-10-05T22:19:45.646-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Voice notes and natural language may help residents with low literacy; residents without WhatsApp need alternative channels.","procurementImplications":"Built in-house, so internal capacity and messaging-platform costs replace a vendor contract.","operatingModelImplications":"Removes the need to know which department handles a request; back-office routing quality becomes critical.","sourceVerification":{"openedUrl":"https://www.todoeldia.com/index.php/2026/10/01/muni-bot-salta-lanza-un-asistente-virtual-con-inteligencia-artificial-para-agilizar-los-tramites-municipales/","referenceExcerpt":"Muni Bot es un desarrollo propio de la Municipalidad de Salta y reemplaza a la aplicación Muni Salta","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}