Utilizing AI in Customer Support

AI in Customer Support isn’t new. I’ve been rethinking how we actually use it. Customer Support is moving past basic "faster replies" and learning to implement Claude as a core part of our workflow. The goal? Shifting from reactive firefighting to structured, scalable systems. It’s a work in progress, but here is the blueprint we’re using to turn Claude into a true CX reasoning engine: 1️⃣ It’s not about speed. It’s about structure. Yes, you can draft replies faster. But the real value comes from setting it up properly: → align it with your tone and guidelines → connect it to your knowledge base → define clear boundaries (what it can and can’t say) → train it to understand context, not just keywords That’s how you get consistent, reliable output across the team. 2️⃣ It helps move Support from reactive → proactive Used well, it’s not just answering tickets. It’s helping you: → detect sentiment and urgency → identify recurring friction points → surface gaps in self-service → spot early churn signals That’s where Support starts influencing the whole customer experience. 3️⃣ It fits into your existing workflows (not replaces them) The most effective setups I’ve seen are simple: → Claude + Zendesk → ticket analysis → Claude + Zapier → automate workflows → Claude + Gong→ review calls → Claude + Intercom → inbox support → Claude + n8n → workflow automation → Claude + Notion → knowledge management No complex rebuilds. Just better use of what you already have. 4️⃣ The quality of output = quality of input Small things make a big difference: → assign a role (support agent, CX lead, analyst) → provide context (customer, goal, constraints) → iterate with examples (good vs bad responses) Without this, you get generic answers. With it, you get something your team can actually use. From a leadership perspective, this isn’t about “adding AI.” It’s about designing how your Support team operates at scale. Because the goal isn’t to answer more tickets. It’s to build a system where fewer things break, and when they do, the experience still feels consistent. If you’re already using AI in Support, what’s actually working for you? 👇

A Tale of Two Companies... Salesforce: Replaced 4,000 with chatbots. Now rehiring. Ikea: Reskilled people, $1.4B in new revenue. Many companies are using AI to eliminate roles. The companies getting bigger returns are doing the opposite. Salesforce: Deployed AI agents to handle customer support. Fired 4,000 - tribal knowledge and relationships gone. Turns out bots are no good at things customers get most frustrated at ❌ Billing disputes ❌ Complex product returns ❌ Cases requiring account history ❌ Good judgment outside of a script Now CEO Marc Benioff says maybe we were too quick. Rehiring at 1.5 the cost. Same technology created a $1.4B business at IKEA. IKEA said AI was 47% better at simple questions like "Does screw A go into hole B?" But their support reps had skills AI couldn't replicate: → Understanding the lifestyle customers wanted → Creating the customers' dream spaces → Good taste built over time IKEA reskilled 8,500 call-center workers into interior design advisers. ✅ AI handled routine questions ✅ People worked with customers ✅ Result: $1.4B in new consulting revenue If you care about your people, take 5 minutes now 1. What decisions have the biggest impact. 2. What data or information does someone need to accelerate their judgment. 3. What tradeoffs do we show to make the case. 4. What is the business outcome of a great decision. 5. What does this mean for our team's capabilities. A pure-efficiency leader implements AI and cuts jobs.  A strategic thinker uses AI to make things possible. ♻️ Repost if you're reskilling, not resizing 🔔 Follow Betsy Tong for AI strategies that grow revenue

Customer-facing AI agents keep failing in production...🤯 Because existing agent frameworks lack some fundamental features. I've spent months building with every major AI agent framework and discovered why most customer-facing deployments crash and burn: → Flowchart builders (Botpress, LangFlow) create rigid paths that customers often break → System prompt frameworks (LangGraph, AutoGPT) excel in demos but fail due to AI's unpredictability Parlant's opensource Conversation Modeling Engine solves this. Here's how and why it matters: 1. Contextual Guidelines vs. Rigid Paths ↳ Instead of mapping every possible conversation flow, define what your agent should do in specific situations. ↳ Each guideline has a condition and an action - when X happens, do Y. ↳ The engine matches only relevant guidelines to each customer message. 2. Guided Tool Use That Stays Reliable ↳ Tools are tied directly to specific guidelines. ↳ No more random API calls or hallucinated data. ↳ Your travel agent won't suddenly search flights when someone asks about baggage fees. 3. Priority Relationships for Natural Conversation ↳ Guidelines have relationships with each other. ↳ When multiple guidelines match, the engine selects based on priority. ↳ Creates step-by-step information gathering without rigid flowcharts. 4. The "Utterances" Feature for Regulated Industries ↳ Pre-approve specific responses for sensitive situations. ↳ Agent checks if an appropriate Utterance exists before generating. ↳ Completely eliminates hallucinations in critical interactions. It works with any major LLM provider - OpenAI, Anthropic, Google, Meta. This approach handles what flowcharts and system prompts can't: The messy reality of actual customer conversations. Your IP isn't the LLM. It's the conversation model you create. The explicit encoding of how your AI agent should interact with customers. For anyone building agents that need to stay reliable in production, this might be the framework you've been waiting for. Check it out: https://lnkd.in/dNPSDJ7P P.S. I create AI Agent tutorials and opensource them for free. Your 👍 like and ♻️ repost helps keep me going. Don't forget to follow me Shubham Saboo for daily tips and tutorials on LLMs, RAG and AI Agents.

At Rackspace, we reduced IT ticket volume by 70% without adding headcount. By integrating an AI coworker directly into Microsoft Teams, it now automates 500+ tickets end-to-end each month. AI works best when employees don’t have to change how they work. So our team built an AI coworker for IT (RITA) that doesn’t need a new portal or separate interface. By running inside Microsoft Teams, an app Rackers use every day, RITA fits naturally into existing workflows. Employees don’t need to switch tools or change how they work, which drives widespread adoption. Beyond answering questions, RITA executes workflows in real time and handles device provisioning, account lockouts, and everyday software issues. It completes the work, not just the request, which lets IT teams spend less time on triage and more time on higher-value work. As a result, we see a widening gap in the market. Teams that treat AI as a tool stay stuck in pilots, while teams that design AI as a participant in operations scale faster. After running RITA inside Rackspace and refining it in production, we deploy it for other IT teams that want to scale without adding headcount. Happy to start a conversation via LinkedIn DMs if this is something you’re actively working on. And if helpful, we’ve written up how this approach played out alongside three other agentic AI solutions we deployed at Rackspace Technology. The link is here: https://bit.ly/4q177Ii.

60% of support tickets are repetitive. And, customers expect immediate responses. That creates pressure on teams and frustration for customers. This is why support is one of the most practical and now proven places to apply AI. AI can handle common, repeat questions instantly, in your tone, using your knowledge base and CRM data. That frees up humans to focus on situations that require judgment, empathy, and creativity. One of our customers, The Knowledge Society (TKS) Society, did exactly that. Every enrollment season, they saw a surge of messages across email, Facebook Messenger, and WhatsApp. The busiest time of year was also the most overwhelming for their team. They implemented the Customer agent to answer common enrollment questions around the clock. Today, close to 80% of inquiries are handled automatically. Their team now spends more time on complex conversations and less time copying and pasting the same answers. The (ISSA) International Sports Sciences Association also scaled with Customer Agent. They were managing multiple support channels across different tools. The experience was fragmented for their team and inconsistent for customers. By introducing an AI agent to handle repetitive questions across channels, they cut response times in half and created a more consistent experience. Over 8,000 companies are already using HubSpot’s Customer Agent, with resolution rates above 67%. This is the real opportunity with AI in support.

In customer experience (CX), the closed-loop feedback (CLF) model has been a cornerstone for over two decades, originally designed to ensure responsiveness and adaptation. It's time for a change. With the advent of artificial intelligence, it's clear that merely adapting this model isn't enough. It's old tapes. It needs to evolve. Here's what's next: Real-time Interaction Management: Traditional CLF reacts to feedback after the fact. And, traditionally, closing the "inner loop" requires a human to follow up. AI turns this on its head. Imagine a system that adjusts the customer journey in real-time based on predictive analytics, reducing friction points before they affect the customer experience. Large Action Models: We all know that AI can dive deep into data lakes to instantly identify patterns and root causes of customer dissatisfaction. This rapid analysis allows companies to not only close the feedback loop faster, but also implement more effective solutions. This will come in the evolution of Large Language Models, or LLMs, to LAMs, or Large Action Models. Continuous Learning Systems: AI transforms CLF from a loop that ends into continuous cycle of improvement. These systems learn from each interaction, constantly updating and refining strategies to enhance the customer experience. This means that the feedback loop is ever-evolving, driven by AI's ability to adapt to new information and complex variables, seamlessly. CX leaders have to embrace AI's potential to redefine our foundational practices. It's time to innovate beyond the traditional CLF and leverage AI to deliver personalized experiences, and at scale. How are you thinking about adaptive, predictive, and personalized CX strategies? Your answer can't be to hire more people to close more loops. #customerexperience #ai #journeymanagement #survey #CLF

Recently the engineers released a 20K-word document outlining changes to the Salesforce platform since 2020 … and we talked about the first 2 big things: (1) #Hyperforce and (2) Data Cloud. There’s also (3) #Agentforce – which deserves attention. Hidden in section 6.2 is this: “Centralizing customer data into a single source of truth is crucial but challenging due to data fragmentation and the complexity of system management.” Thus Data Cloud, but: Why is this “crucial”? Because #AI, #GenAI and agentic AI like #Agentforce doesn’t work without data management. The #CDP like Data Cloud is item number 1. Built on #Hyperforce, Data Cloud is basically an integrated infrastructure and no-code platform to consolidate data. Data beautifully aligned has no purpose unless it is put to work. The first – and still the primary – use for CDPs in my opinion is analytics: pulling insights out of data, building predictive models and recommendations. Mere better segmentation can rescue a stalling business; direct marketers have known this for decades. Predictive models often use machine learning, which is a subset of AI. But I would say they are still just a genre of data organization. Really putting data to work requires something more – and this is why #Agentforce matters. Putting data to work requires decisions: What data and what work? Decisions can be made by a rule or a trigger: If a person abandons their cart, wait a day and send them a note. Such a rule can easily be set by a person. #Agentforce happens when the decisions around (a) what data, and (b) what action aren’t so obvious. Salesforce’s existing AI Platform already includes a layer for managing, training, and tuning models, incl. a no-code Model Builder and Prompt Builder. But there have to be ways to integrate AI into business applications like Marketing, Sales and Service Clouds. #Agentforce is like a co-pilot but more helpful. We use #RAG and outside LLMs of course to ground prompts in your own data and a Trust Layer to ensure usability, but there is more to agentic AI. So the #Agentforce Platform incorporates: 💥 Planner Service, which: (a) Interprets the user’s request (their intent & sentiment) using NLP methods and aligns this to a framework of topics (b) Structures a plan to respond to the request, using instructions (guardrails) (c) Initiates actions directly via other services, incl. actions to locate more data #Agentforce itself is the platform for building agents, but we can see how it requires a bigger platform around it to get work done. It needs Data Cloud to access unstructured data (like call center FAQs or contracts) and use it to do (b) above – make a plan, within boundaries. It also needs something like the Salesforce Platform w/ metadata for cross-department cooperation and – most important – built-in automations like Flow Builder and Process Automation to do (c) above, i.e., trigger actions and workflows.

AI customer service will fail if brands treat it as a cost-cutting project. Gladys and I see agentic AI as a major shift from basic chatbots. These systems can interpret requests, make decisions and complete actions across connected workflows. Gartner predicts that agentic AI could resolve 80% of common customer service issues without human intervention by 2029. That figure will attract attention in boardrooms. The harder question is whether those resolutions will strengthen or weaken the customer relationship. An AI agent needs more than a polished interface. It needs: * Accurate product and customer data * Access to the right systems and workflows * Clear limits on the decisions it can make * A direct route to a person when judgement or empathy is required * A handover that includes the customer’s full context Without these foundations, AI becomes another layer customers must fight through. From a marketing perspective, every service interaction shapes the brand. A fast response has little value when it is incorrect, impersonal or difficult to resolve. The role of AI should be clear: handle routine, information-heavy work and give service teams more capacity for cases requiring judgement, care and accountability. Human handover should never feel like starting again. Customers should not have to repeat their issue, resend information or explain why the matter is urgent. The human agent should receive the history, relevant data and actions already taken. The strongest service model will assign each task to the resource best placed to handle it. AI for speed and scale. People for judgement and trust. For leaders investing in agentic AI, the real measure is not how many conversations are automated. It is how many customer problems are resolved without damaging the relationship. Are we using AI to remove customer effort, or simply moving that effort somewhere else? Sources: Azumo, Gartner and Zendesk ⭐ Co-created with Gladys Ng, Top 20 Creator in Marketing and Sales on LinkedIn Singapore.

650. That’s the staggering number of companies offering conversational AI solutions for sales and service. The flood isn’t slowing: each week brings new entrants or announcements. A year ago, the market was already crowded; today, the latest wave of AI technologies has further lowered barriers to entry, fueling an unsustainable proliferation. Beyond the three hyperscalers, only a handful of providers have surpassed $100M in ARR. I spent the summer making sense of the mayhem. The result: nine categories mapped to the core jobs-to-be-done. Customer service and support solutions fall into four categories: • Virtual Agents. IVAs and their AI evolution operate across digital channels, handling transactional interactions and escalating to humans when necessary. • AI Answer Engines. These retrieve and format answers from knowledge bases. Generative AI has dramatically improved precision for informational inquiries. • Conversational IVR and Voice Agents. Voice remains complex; these agents primarily handle transactional interactions. • Conversational Engagement and Outreach Agents. These manage outbound communications across voice, SMS, and messaging channels, complying with regulations. Historically transactional, they increasingly enable dynamic engagement. Sales solutions are grouped into three categories: • Conversational Commerce & Concierge Agents. Mature agents replacing traditional chat with conversational experiences across pre- and post-sales. "Concierge" reflects their versatility in guiding customers seamlessly. • Autonomous SDRs (Sales Development Reps). Focused on complex B2B scenarios, they enrich and qualify leads, route them to sellers, and schedule appointments. Among the most mature AI applications for B2B sales. • Autonomous BDRs (Business Development Reps). These drive outbound sales motions where relevance is critical. Complex to implement and scale, they work best in highly targeted scenarios where personalization is flawless. Some providers span the full spectrum of service use cases and Conversational Commerce & Concierge Agents. Rather than duplicating them across categories, I group them under Conversational AI Platforms, relying on robust capabilities to design, deploy, and continuously improve applications and agents. Customer Support Automation is an emerging platform category, tailored for handling support requests and a natural fit for GenAI. These platforms deliver full resolutions when possible, automate workflows, and assist agents with context and guidance. It’s a mature use case for Agentic AI, with many providers publicly demonstrating transformative results. The visual landscape below captures this segmentation. A few vendors will emerge as true platforms, while others will focus on niches or become embedded in broader applications. The market remains in motion, and I welcome perspectives on what I may have overlooked. #conversationalai #agenticai #cx #salestech