{"resourceId":"barnsley-b-bot-genai-upgrade-94pct-answered-satisfaction-20261109","versions":[{"version":"external-7b8d835df5d9f3e935f1bfd6b6a3fa2d2bfc9446075c0076c9e1a3f635809057","resource":{"id":"barnsley-b-bot-genai-upgrade-94pct-answered-satisfaction-20261109","title":"Barnsley Council reports first-30-day results of its generative AI B-Bot upgrade: 3,700+ conversations, satisfaction up from 3.3 to 4.4 of 5, 94% of enquiries answered without an advisor","organization":"Barnsley Metropolitan Borough Council (Customer Services and Innovation Service)","sector":"Local government website chatbot and customer services","geography":"Barnsley, South Yorkshire, England, United Kingdom","publishedAt":"2026-11-09","publicationDate":"2026-11-09","eventDate":null,"sourceName":"Barnsley Council (news release)","sourceLabel":"AI-powered B-Bot helping more Barnsley residents get answers first time","sourceUrl":"https://www.barnsley.gov.uk/news/ai-powered-b-bot-helping-more-barnsley-residents-get-answers-first-time/","evidenceClass":"government-evaluation","outcomeClass":"effective","topics":["operating-model","knowledge-work","accessibility-workforce"],"finding":"Barnsley Council's Nov. 9, 2026 release reports that its website chatbot B-Bot was upgraded in June 2026 to generate answers from information published on the council website rather than relying only on pre-written responses. Before launch the Digital Team reviewed, restructured and rewrote more than 1,500 webpages, updated over 800 tables of information and tested the bot with more than 2,000 questions. In the first 30 days after the upgrade the council reports more than 3,700 conversations (versus fewer than 2,000 the previous month), customer satisfaction rising from 3.3 to 4.4 out of 5, an average of 94% of enquiries answered by the chatbot, and only two to three enquiries a day escalated to an advisor.","sledRelevance":"A rare published before/after measurement of a generative website assistant in local government, and it attributes the result to a large content clean-up and question-bank test, which is directly transferable to U.S. 311 and city website chat projects. Published Nov. 9, after the last completed CE run.","evidence":"Council self-reported operational metrics for a single 30-day post-upgrade window against the prior month; no independent evaluation, answer-accuracy audit, method for computing 'answered' or satisfaction sample size.","architectureImplications":"Retrieval-style generation over the council's own website content, with escalation to customer service advisors via webchat; content structure (rewritten pages and tables) is treated as part of the system.","governanceImplications":"Accuracy assurance relied on pre-launch testing with 2,000+ questions; the release does not describe ongoing monitoring, error handling or who signs off content changes.","securityPrivacyImplications":"Release does not describe conversation logging, retention or personal-data handling in chats.","caveats":"Self-reported by the council; 30-day window after a June upgrade reported in November; '94% answered' may mean not escalated rather than correctly resolved; satisfaction is likely from opt-in ratings; UK context (council tax, bins) limits direct transfer.","streamIds":["citizen-engagement"],"roles":{"sales":"Sales framing: Barnsley shows that the selling point is the content clean-up, not the bot. The council rewrote 1,500+ pages, updated 800+ tables and tested 2,000+ questions before reporting 94% of enquiries answered and satisfaction rising from 3.3 to 4.4 of 5. Discovery should ask how current a city's web content is, what escalation volume looks like, and how answers are tested. A bounded engagement is a content-readiness and test-bank sprint before any assistant goes live. Do not promise these numbers; they are one council's 30-day self-report.","engineering":"Engineering framing: the upgrade grounds generated answers in the council's published website content, so retrieval quality depends on page structure, tables and freshness. Prerequisites are a content inventory, removal of stale pages and a representative question bank with expected answers. Constraints include unclear handling of logging, model choice and escalation routing. Proof of value should replicate Barnsley's 2,000-question test, measure answer correctness rather than only non-escalation, and track escalation reasons by service area.","delivery":"Delivery framing: the hard work sits with the digital and content teams, before and after launch. Barnsley's Innovation Service rewrote pages and tested questions; customer services absorbed the remaining escalations. Acceptance criteria below are proposals: a correctness rate on a fixed question bank, a content-freshness check cadence, and escalation-rate tracking by topic. Keep webchat advisors available, review a sample of conversations each month, and publish results beyond the first 30 days before declaring success."},"roleDetails":{"sales":{"customerProblem":"Residents searching many web pages or phoning for routine council information, with webchat advisors handling repetitive questions.","stakeholders":["Head of customer services","Digital/content team","Service area web owners","Council leadership"],"discoveryQuestions":["How current and structured is the website content the assistant would draw on?","How will answer correctness, not just escalation, be measured?","Who owns content updates after launch?"],"valueHypothesis":"Content clean-up plus a grounded assistant may raise self-service resolution and satisfaction; magnitude unproven outside Barnsley's 30-day self-report.","potentialEngagement":"A content-readiness assessment and 2,000-question test bank before assistant launch or upgrade.","unsupportedClaims":["Guaranteed 94% containment","Staff cost savings","Answer accuracy (not independently measured)"]},"engineering":{"fit":"Fits councils and cities with large public websites and an existing chat or webchat channel.","architectureIntegration":"Generative answers grounded in the council's own website pages and tables, with handoff to human advisors.","prerequisites":["Content inventory and rewrite","Question bank with expected answers","Escalation routing to advisors"],"constraints":["Vendor and model unnamed","Single 30-day measurement window","UK service mix differs from U.S. 311"],"security":"Define conversation logging, retention and how personal data typed into chat is handled.","proofOfValue":["Correctness on a fixed question bank","Escalation reasons by service area","Satisfaction sample size and method"]},"delivery":{"work":"Clean up and restructure web content, test the assistant, and run it alongside advisor webchat.","dependencies":["Website CMS","Service area content owners","Customer services advisors"],"ownership":"Council customer services with the digital/innovation team as content owner.","skillsAdoption":"Train content editors to write for retrieval and advisors to review escalations and flag bad answers.","governanceCheckpoints":["Pre-launch question-bank sign-off","Monthly conversation sample review","Content freshness review cadence"],"acceptanceCriteria":["Correctness above an agreed threshold on the question bank","Escalation reasons logged and reviewed monthly","Results reported beyond 30 days"],"risks":["Content decay erodes accuracy","Non-escalation mistaken for resolution","Over-reliance on a short measurement window"]}},"retrievedAt":"2026-11-09T22:09:05-06:00","enrichedAt":"2026-11-09T22:15:04-06:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Council says customer service advisors were freed from webchat to handle residents needing more support on complex issues; no staffing reductions are claimed.","procurementImplications":"Vendor and model are not named; the main investment described is internal content work by the Digital Team.","operatingModelImplications":"Escalation volume fell to two to three enquiries a day, shifting advisor time to complex cases; maintaining 1,500+ rewritten pages becomes an ongoing content-operations responsibility.","sourceVerification":{"openedUrl":"https://www.barnsley.gov.uk/news/ai-powered-b-bot-helping-more-barnsley-residents-get-answers-first-time/","referenceExcerpt":"Customer satisfaction increased by a third, going from 3.3 out of 5 to 4.4 out of 5.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}