At UKSAC, we go above and beyond to get our clients what they’re looking for. Iheomachi tried us and concludes that... #uksac# #uksaconsult# #studentsaccommodation# #customerservice# #customersatisfaction# #housingservice# #internationalstudents# #middlesbrough# #teesside# #teessideuni#

BREAKING: Starlink has debuted on the American Customer Satisfaction Index for the first time — ranking 3rd among 12 major internet providers. 🛰️📈 Starlink ranked ahead of Cox, AT&T Internet, Xfinity and Spectrum, while every cable and DSL provider finished behind it. Only two fixed 5G services ranked higher. Starlink is already delivering one of the highest customer satisfaction levels in the U.S. Source: American Customer Satisfaction Index (ACSI)

$6M projected annual savings. 7x return. Customer satisfaction up 900%. That’s @SouthwestAir with Agentforce Justin Bundick, VP of AI, joins us at @Dreamforce to share how they got there

Starlink is taking over Aer Lingus long-haul Wi-Fi ✈️ In less than six months, Aer Lingus has already equipped 50% of its long-haul fleet with Starlink And passengers are clearly using it: • 85% connect on an average flight • Customer satisfaction is 27 points higher on Starlink-equipped aircraft • Some transatlantic flights have used up to 950 GB in a single crossing That is enough data for more than 300 hours of HD streaming on one flight Aer Lingus is now pushing toward Starlink across its entire long-haul fleet by the end of 2026

Practices for embedding AI agents into enterprise systems [Confidence-Gated Abstention & Escalation] 💡 The most dangerous AI is one that answers when it doesn't know. Designing "I don't know" as a first-class output is the first step toward enterprise-grade quality. 🔥 Problems Solved - Agent cannot say "I don't know" and provides misinformation via hallucination - Overconfident responses with no factual basis mislead users - Inappropriate auto-replies to questions requiring specialized expertise - Cases that need human handling get resolved poorly by the agent, tanking customer satisfaction 🏗️ Proposed Pattern Combine self-assessment, search hit quality, verifier pass/fail, and uncertainty signals into a composite confidence score. Below the threshold, the agent responds with "I'm not sure" and performs a warm handoff to a human, carrying over the full conversation context so the human doesn't start from scratch. Measure the tradeoff curve between containment rate (agent self-resolution) and error rate, and set the threshold more conservatively for high-cost-of-error domains. ✅ Selection Criteria - Fit: customer support, specialized domains, high-stakes advisory where wrong answers are costly - Not Fit: harmless brainstorming or exploratory conversations where errors are inconsequential ⚠️ Pitfalls - Threshold too high turns the agent into a pass-through to humans, negating its value - Threshold too low increases wrong answers and destroys trust - Failing to carry conversation context on escalation forces customers to repeat themselves 🛠️ Implementation Approach 1. Implement a composite scoring function that combines self-assessment, search hit relevance, and verifier pass/fail into a single confidence score 2. On warm handoff below threshold, auto-transfer conversation history, extracted entities, and attempted answers to a Zendesk ticket or Slack thread 3. Design escalation paths in three tiers: Zendesk (customer-facing), Slack (internal), and PagerDuty (urgent) 4. Visualize the containment rate vs. error rate tradeoff curve weekly and adjust thresholds per domain 5. Log abstention reasons in structured logs and identify knowledge base improvement areas from recurring abstention patterns #AIAgents# #EnterpriseArchitecture#