{"resourceId":"uofl-its-aristides-ai-concierge-20261013","versions":[{"version":"external-cf11665a6150bb0b59a5076d8220352c114891457c900946b40e700ec1996780","resource":{"id":"uofl-its-aristides-ai-concierge-20261013","title":"University of Louisville ITS readies Aristides, a locally built AI concierge in the Student Portal, after spring–fall 2026 pilot testing","organization":"University of Louisville Information Technology Services (Innovation unit and Integrative Design & Development team)","sector":"University IT and student-services operations","geography":"Kentucky, United States","publishedAt":"UofL ITS News, 13 October 2026","publicationDate":"2026-10-13","eventDate":null,"sourceName":"University of Louisville Information Technology Services","sourceLabel":"Institutional announcement (self-report)","sourceUrl":"https://louisville.edu/its/news/and-running-aristides-uofls-new-ai-powered-student-concierge","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["operating-model","developers-agents","accessibility-workforce","data-security"],"finding":"UofL ITS is preparing to release Aristides, an always-available conversational assistant in the Student Portal. It answers questions about topics such as financial aid, changing majors, enrollment deadlines, advising and campus services from official university information. ITS's Innovation unit and its Integrative Design & Development (IDD) team built it. IDD has four professional staff plus student designers and programmers, and has focused since July 2024 on locally managed AI engines and frameworks. IDD's portfolio includes the Student Portal, the Louie textbot, the Aristides Student Concierge and a separate Aristides platform for administrative and research units. In spring and fall 2026, students, advisers and administrators tested the tool in everyday situations, noted incomplete or incorrect responses and submitted detailed evaluations. Users can hide the widget through the portal's Edit Layout feature. ITS says Aristides is meant to support, not replace, advisers, financial aid professionals and other staff. Planned phases add personalized responses using Student Portal data and two-way texting through Louie.","sledRelevance":"An example of a university IT unit building and owning its AI service layer instead of licensing a vendor chatbot, with pilot testing by front-line staff before release. It is relevant to campus service-desk and student-services operations. Scope note: this is student-facing service navigation, not teaching or learning, so it is tagged campus-operations. The planned administrative and research-unit platform is the more direct campus-operations signal.","evidence":"Institutional announcement only. There is no release date, usage, accuracy or error-rate data, no pilot sample size, and no model, hosting or data-handling details. Testers' reports of incomplete or incorrect responses are acknowledged but not quantified.","architectureImplications":"Interpretation: a locally managed AI engine with a curated knowledge base, embedded as a portal widget. The planned personalization would connect the assistant to authenticated student-record data, and integration with an existing textbot would add a second channel. That raises integration and identity requirements.","governanceImplications":"ITS cites published AI principles (human-centred design, validation, transparency, accountability, fairness, security, data privacy) and an opt-out widget. Moving to personalized responses will need data-use approval and accuracy oversight by the offices whose information it gives.","securityPrivacyImplications":"The current version answers from official university information. The planned use of Student Portal data for personalization would bring student-record privacy obligations into scope. Hosting and retention are not described.","caveats":"Self-reported launch announcement with no outcome data. Release timing is not stated. Effectiveness, accuracy and staff workload effects are unknown. Applicability depends on having in-house development capacity similar to IDD's.","streamIds":["campus-operations"],"roles":{"sales":"For sales, the point is that some university IT units are choosing to build and own AI service assistants rather than buy them. UofL ITS has a small development team, has worked on locally managed AI engines since 2024, and used staff and student pilot testing before release. Discovery should explore build capacity, knowledge-base ownership and plans to extend into administrative units. Do not claim reduced call volumes, accuracy or staff savings; none are reported.","engineering":"For pre-sales engineering, Aristides is a portal-embedded assistant over curated official content, with planned personalization from authenticated portal data and a texting channel. Evaluate the knowledge-base pipeline, content freshness, identity integration for personalized answers, and escalation to human offices. The pilot recorded incomplete or incorrect responses, so any comparable build needs a measured accuracy baseline and a correction workflow before personalization is turned on.","delivery":"For delivery, the work is moving from pilot feedback to measured service quality. Agree content owners in financial aid, advising and registrar offices. Set accuracy and escalation targets. Instrument conversations for unresolved questions. Plan the data-protection review needed before using Student Portal records. Keep the opt-out and human-contact paths visible, consistent with the support-not-replace commitment, and report accuracy results each term to the participating offices."},"roleDetails":{"sales":{"customerProblem":"Students and staff search several websites, systems and office inboxes for answers, often outside office hours.","stakeholders":["CIO and IT innovation director","Financial aid and registrar directors","Advising leadership","Student-services operations","Privacy officer"],"discoveryQuestions":["Which offices own the content the assistant answers from?","How were pilot errors logged and corrected?","What metrics will define a successful release?","Will the administrative-unit version share the same platform and governance?"],"valueHypothesis":"Interpretation: a curated, always-available assistant may absorb routine navigation questions if content owners keep answers current.","potentialEngagement":"A bounded accuracy and escalation evaluation of a portal assistant across two or three service offices before personalization is enabled.","unsupportedClaims":["Reduced call or email volume","Measured answer accuracy","Staff time savings"]},"engineering":{"fit":"Fits institutions with in-house developers building assistants over curated official content in an existing portal.","architectureIntegration":"Locally managed AI engine and knowledge base embedded as a Student Portal widget, with planned links to portal data and the Louie textbot.","prerequisites":["Curated knowledge base with named content owners","Portal and identity integration","Escalation paths to service offices"],"constraints":["Student-record privacy obligations once personalized","Small development team capacity","Content currency across many offices"],"security":"Not described in the source; confirm hosting, retention, logging and access controls before using authenticated portal data.","proofOfValue":["Accuracy test on sampled real student questions per office","Escalation success rate to the right human office","Content-update lag measurement"]},"delivery":{"work":"Release with defined accuracy targets, content-owner workflows, conversation analytics and a privacy review before personalization.","dependencies":["IDD development team","Service-office content owners","Privacy and data governance","Portal team"],"ownership":"ITS owns the platform; each service office owns the accuracy of its content.","skillsAdoption":"Content owners need a simple update workflow; front-line staff need to know how to route corrections.","governanceCheckpoints":["Pre-release accuracy review","Data-protection approval before personalization","Term-end quality and usage review"],"acceptanceCriteria":["Proposed: sampled answer accuracy at or above an agreed threshold per office","Proposed: unresolved questions routed to a human contact in all cases","Proposed: content corrections applied within an agreed time"],"risks":["Incorrect answers on deadlines or aid","Scope creep into personalized advice","Dependence on a small team"]}},"retrievedAt":"2026-10-14T21:54:09-05:00","enrichedAt":"2026-10-14T22:02:19-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Uses paid student designers and programmers alongside four professional staff, which is a workforce development model. Staff roles are explicitly to be supported, not replaced. Accessibility testing of the widget is not described.","procurementImplications":"A build-and-own approach avoids a vendor chatbot licence but depends on sustained internal funding and staff retention.","operatingModelImplications":"IT acts as product owner for an AI service layer that service offices feed with content. Extending it to administrative and research units makes this a shared enterprise service.","sourceVerification":{"openedUrl":"https://louisville.edu/its/news/and-running-aristides-uofls-new-ai-powered-student-concierge","referenceExcerpt":"Since July 2024, the team has focused on developing locally managed AI engines and frameworks for UofL.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}