Automated Customer Support

The way we think about agents today is overly naive. We treat them like they're one thing—"agents"—when they're actually going to be as varied as software itself. A customer support agent needs to be careful, double-check everything, build trust. A commercial agent? Maybe you want it to be a bit pushy. Decision support agents can never be wrong about a number, never leak information, and must explain their reasoning clearly. Each type requires completely different design choices. Your customer support agent needs to understand your specific return policies, your brand voice. Your decision support agent needs to know your risk tolerance, your strategic priorities, how your board thinks. These aren't generic capabilities—they're deeply specific to how your organization operates. The future isn't one super-intelligent agent or one type of agent for all tasks. It's dozens of specialized agents, each designed for its specific role in your specific organization. Those who grasp this will deploy the right agent for each job. Those who don't will wonder why their one-size-fits-all approach keeps falling short. #AI #AIDilemma #AIAgents #EnterpriseAI

Without data structure, intent signals are just noise. After months of refining our account-based program, I've come to a simple realization: without proper data structure, intent signals are drowned and unusable. The team is tackling this challenge using this 3-step process: 1️⃣ Capturing the RIGHT signals With AI, Clay, and countless data providers, intent signals have become more accessible and commoditized (company announcements, reviews, technographics, hiring and more). It's incredibly tempting to buy it all and see what surfaces — I've been there! But I've learned the hard way that collecting signals without strategy creates more noise than insight. Beyond the hype, we took a deep dive into our customer journey (specifically won deals) to identify common patterns in buyer attributes and behaviors. Yes, we scrap and ingest external signals, but we've placed special emphasis on our 1st party data (CRM infos, website/product tracked events, webinar viewers, ad engagement). This gives us an edge that competitors simply can't replicate. 2️⃣ Building a UNIQUE data set Playing around with new intent signals in Clay is fun — and we do it! But the game-changer was figuring out how to structure and process these signals within the CRM. We've customized HubSpot to store them in custom objects. Every signal, regardless of source, follows the same structure: name, desc, source, URL, and timestamp. This standardization has transformed our ability to combine signals, refine scoring models, and surface insights that truly resonate with our team. In the end, better iteration and more educated guesses. 3️⃣ Routing signals for HUMAN engagement The final and hardest part (in my opinion): getting these signals into the hands of our sales team for meaningful action. While we've automated the routing mechanics, we've discovered that enablement and discipline are equally crucial. We’ve set up regular team meetings to go over disqualification reasons, celebrate wins, and come up with new signal ideas. There’s nothing better than seeing our team turn these intent signals into conversations. Technology enables, but the human connection converts. Open questions to the #Growth and #RevOps in my network: what signals are you prioritizing in your growth strategy right now? What sources are delivering the best results? Any tips on improving signal routing and sales enablement? —— Follow me if you found value in this post 🙇♂️ I used to share stuff about growth, marketing and SaaS.

AI Agents have moved from simple scripts to multi-agent systems Understanding the stages helps save time and cost... Multiple reports suggest the issue isn’t AI workflows themselves, but how people design them. Often, you don’t need a complex agentic system for simple tasks like summarizing HR documents. That’s why it’s crucial to pick the right solution instead of chasing the biggest one. 📌 To make it clearer, let’s walk through the 5 stages: 1. Script Chatbots - Human Dependency (~90–80%): Almost fully dependent on humans to script every single response. - Autonomy: No real intelligence — purely rule-based workflows. - Scalability: Scales linearly, but only for repetitive, predictable tasks. - Use Case: Simple automations like email replies, FAQs, or support ticket routing. 2. LLM Chatbots - Human Dependency (~70–60%): Reduced, but still needs supervision. - Autonomy: Contextual understanding with natural conversations — but no planning ability. - Scalability: Expands easily for large customer support operations. - Use Case: Customer-facing chatbots that can hold human-like conversations, but can’t take autonomous action. 3. Modern RPA - Human Dependency (~50–40%): Handles repeated, structured tasks with less manual input. - Autonomy: Contextual but still repetitive — can trigger scripts and execute tools when prompted. Scalability: Great for high-volume, process-driven workflows. - Use Case: Hiring document processing, invoice scanning, compliance checks. 4. Single Agentic AI - Human Dependency (~30–20%): Agents plan, use tools, and incorporate feedback with limited supervision. - Autonomy: Adaptive reasoning within a defined scope — memory + planning + tool use. - Scalability: Dynamic scaling for dedicated enterprise use-cases. - Use Case: Smart document retrieval, enterprise knowledge Q&A, semi-autonomous research. 5. Multi-Agentic AI - Human Dependency (~15–10%): Agents coordinate among themselves, requiring minimal human input. - Autonomy: Dynamic, multi-workflow execution with cross-agent collaboration. - Scalability: Designed for complex, large-scale enterprise automation. - Use Case: Interconnected coding agents, enterprise-wide orchestration, cross-department AI systems. In our latest book, we explored what each of these stages means for enterprises, not just in theory. I’ve linked the detailed breakdown in the comments 👇 📌 The big takeaway: Those reports are right, which state that the problem is not models or workflows - it is people who are implementing them. Not every task needs a complex system — sometimes simpler approaches are more effective. That’s why identifying the right use case is critical for enterprises. And that’s exactly what we cover in our AI Agent Engineering course — helping you design scalable agents with the right enterprise mindset. 🔗 Enroll here: https://lnkd.in/gA3zhcfm Save 💾 ➞ React 👍 ➞ Share ♻️ & follow for everything related to AI Agents

You don't need a 2 trillion parameter model to tell you the capital of France is Paris. Be smart and route between a panel of models according to query difficulty and model specialty! New paper proposes a framework to train a router that routes queries to the appropriate LLM to optimize the trade-off b/w cost vs. performance. Overview: Model inference cost varies significantly: Per one million output tokens: Llama-3-70b ($1) vs. GPT-4-0613 ($60), Haiku ($1.25) vs. Opus ($75) The RouteLLM paper propose a router training framework based on human preference data and augmentation techniques, demonstrating over 2x cost saving on widely used benchmarks. They define the problem as having to choose between two classes of models: (1) strong models - produce high quality responses but at a high cost (GPT-4o, Claude3.5) (2) weak models - relatively lower quality and lower cost (Mixtral8x7B, Llama3-8b) A good router requires a deep understanding of the question’s complexity as well as the strengths and weaknesses of the available LLMs. Explore different routing approaches: - Similarity-weighted (SW) ranking - Matrix factorization - BERT query classifier - Causal LLM query classifier Neat Ideas to Build From: - Users can collect a small amount of in-domain data to improve performance for their specific use cases via dataset augmentation. - Can expand this problem from routing between a strong and weak LLM to a multiclass model routing approach where we have specialist models(language vision model, function calling model etc.) - Larger framework controlled by a router - imagine a system of 15-20 tuned small models and the router as the n+1'th model responsible for picking the LLM that will handle a particular query at inference time. - MoA architectures: Routing to different architectures of a Mixture of Agents would be a cool idea as well. Depending on the query you decide how many proposers there should be, how many layers in the mixture, what the aggregate models should be etc. - Route based caching: If you get redundant queries that are slightly different then route the query+previous answer to a small model to light rewriting instead of regenerating the answer

Two weeks ago I said AI Agents are handling 95% of our sales and support and I replaced $300k of salaries with a $99/mo Delphi clone. 25+ founders DM’d me… “HOW?” Here’s the 6 things you MUST do if you want to run your entire customer-facing business with AI: 1. Create a truly excellent knowledge base. Your AI is only as good as the content you feed it. If you’re starting from zero, aim for one post per day. Answer a support question by writing a post, reply with the post. After 6mo you have 180 posts. 2. Have Robb’s CustomGPT edit the posts to be consumed by AI. Robb created a GPT (link below) that tweaks posts according to Intercom’s guidance for creating content for Fin. The content is still legible to humans, but optimized for AI. 3. Eliminate recursive loops - because pissed off customers won’t buy If your AI can’t answer a question but sends the customer to an email address which is answered by the same AI, you are in trouble. Fin’s guidance feature can set up rules to escalate appropriately, eliminate loops, and keep customers happy. 4. Look at every single question every single day (yes, EVERY DAY). Every morning Robb looks at every Fin response and I look at every Delphi response. If they aren’t as good as they could possibly be, we either revise the response, or Robb creates a support doc to properly handle the question. 5. Make sure you have FAQs, Troubleshooting, and Changelogs. FAQs are an AI’s dream. Bonus points if you create FAQ’s written exactly how your customers ask the question. We have a main FAQ, and FAQs for each sub section of our support docs. Detailed troubleshooting gives the AI the ability to handle technical questions. Fin can solve 95% of script install issues because of our Troubleshooting section. Changelogs allow the AI to stay on top of what’s changed in the app to give context to questins about features and UI as it changes. 6. Measure your AI’s performance and keep it improving. When we started using Fin over 1y ago, we were at 25% positive resolutions. Now we’re above 70%. You can actively monitor positive resolutions, sentiment, and CSAT to make sure your AI keeps improving and delivering your customers an increasingly positive experience. TAKEAWAY: Every Founder wants to replace entire teams with AI. But nobody wants to do the actual work to make it happen. Everybody expects to flip a switch and have perfect customer service. The reality? You need to treat your AI like your best employee. Train it daily. Give it the resources it needs. Hold it accountable for results. Here’s the truth that the LinkedIn clickbait won't tell you… The KEY to successfully running entire business units with AI? Your AI is only as good as the content you feed it. P.S. Want Robb's CustomGPT? We just launched 6-part video series on how RB2B trained its agents well enough to disappear for a week and let AI run the entire business. Access it + get all our AI tools: https://www.rb2b.com/ai

I just built an FAQ using the new Copilot powered FAQ Webpart, And a Copilot agent from the same 140-page compliance manual. Here's when to use each one because you're probably wondering which tool to pick for your next project. When you see shiny new Copilot integrations in SharePoint you tend to think you need to choose one. Nope. In this case, they solve different problems for your users. The FAQ web part is for your quick-answer people. We all know the ones, they scan, find their question, get the answer, and move on. When I tested "How is staff measured on compliance performance?" the FAQ gave me a clean, condensed response. Perfect for someone who just needs the policy details without the conversation. The Copilot agent is for your detail-seekers, your conversationalist. Same question, but the agent gave me way more context and background. It's conversational. Your users can ask follow-ups, dig deeper, get explanations. Better when someone's trying to understand how policies actually work in their day-to-day. Here's what I learned building both, so you don't have to. The FAQ took one document and created clean categories with collapsible questions. Great for your policies, procedures, anything where people need quick reference. Think employee handbook, IT support, compliance guidelines. The agent lets your people have actual conversations about that same content. Someone can ask "What happens if we miss a compliance deadline?" and get a detailed response they can build on. You might want both. People work differently. Some scan FAQs, others prefer to ask questions and get explanations. Don't make this an either-or decision for your organization. Build what matches how your users actually work.

Metacognition is central to our ability to use AI well. The paper "Exploring the Potential of Metacognitive Support Agents for Human-AI Co-Creation" demonstrates how "metacognitive agents" can help human mechancial designers, also surfacing valuable lessons on effective agent design. The Carnegie Mellon University researchers created three agents, SocratAIs, HephAIstos and Expert FreeForm. Some of the key findings: 🧠 Metacognitive agents boost design feasibility. Designers supported by metacognitive agents produced significantly more feasible mechanical parts than those without support. The average design quality score was 3.5 out of 5 for supported users, compared to just 1.0 for unsupported users. 🗣️ Voice-based agents effectively prompt reflection. Using a voice interface, agents like SocratAIs and HephAIstus prompted designers to reflect on their design decisions and simulate real-world conditions. For instance, SocratAIs’ questions led users to reconsider incorrect force directions, improving load case setup and part feasibility. 🛠️ Sketching + planning enhances design reasoning. HephAIstus prompted users to sketch free-body diagrams and fill out planning sheets, leading to deeper engagement and improved problem setup. All users followed through with these activities, and in several cases, these tools anchored productive discussions that corrected prior design flaws. 📉 Over-questioning can backfire. While SocratAIs helped many, repeated questioning sometimes increased doubt and led users to override correct assumptions. In one session, this caused a participant to regress from a correct load setup to an incorrect one, illustrating how reflective support needs careful timing and calibration. 👥 Experts adaptively modulate support. Expert designers acting as support agents intuitively timed their interventions, sometimes delaying advice until users showed readiness. They blended reflective questioning with direct support, effectively guiding users without overstepping or causing dependency. 🧭 Metacognitive agents enhance self-regulation. Participants reported that agents helped them plan better and reflect more thoroughly. Some described feeling more organized and aware of their design logic, aligning with principles of self-regulated learning. One user noted the agent “walked me through my own thought process.” There is a lot more work to do in this vein, but this offers an important framing and valuable insights.

Here's another way we're using AI at Reformed IT to improve our client experience without replacing the human touch 👇🏻 Every time a client emails us about an issue, we use AI to analyse the tone of their email and the likely level of satisfaction. 📩 Their tone could be: 🤬 Angry 😠 Frustrated 🤔 Confused 😟 Concerned 😐 Neutral 😊 Polite 😁 Happy Which would in turn lead to a likely satisfaction score between 1 - 10. If we detect that a client is Angry or frustrated with us based on their emails, we'll flag this ticket automatically with our head of service, Dan, to review. ✅ As you'll have seen recently, we track a lot of stats/data around customer service and satisfaction. 📊 However, we will only get feedback after we've completed a task. But we're picking up sentiment from the client during the entire interaction. By looking at the signs of frustration early on, we're more likely to be able to deal with the root cause of these frustrations and ensure that we turn it around to have a happy client by the time we've done the work. 😁 I've talked a lot about AI recently and the fact it will have an impact on jobs, but I also think, when used in the best way, it can really empower your business and people to do the best they can. 🤖 + 👨🏻💼 Are you using AI and Automation to improve your client experience? If so, how?

It was a pleasure to talk to Paul Morrison at WNS about the impact of AI on retail. We discussed a wide range of topics, from the impact of GenAI on retailers operations, to how it could impact the customer journey. It's such a fascinating area which is changing at pace. Here are a few areas that I think will see the largest impact. ➡ Personalisation at Every Stage GenAI crafts individual experiences, from targeted product recommendations based on past purchases to custom promotions that hit right when a customer is most receptive. It builds customer loyalty by making each interaction feel tailor-made. ➡ Intelligent CX Support (WISMO) Solving the most common customer concern, “Where’s my order?” GenAI-powered chatbots handle this and other frequent queries instantly, freeing up staff and providing seamless, reliable support—no human intervention needed. ➡ Predictive Inventory Management By analysing sales patterns and seasonal demand (and thousands of other inputs such as weather, supply chain disruptions, social media buzz), GenAI forecasts precisely what stock to have on hand, minimising costly overstocking or disappointing stockouts. This ensures products are ready when customers want them. ➡ Dynamic Pricing, Rewards, and Promotions for Real-Time Relevance GenAI empowers retailers to adjust prices, rewards, and promotions in real-time based on demand, competitor trends, and customer profiles. This approach ensures every deal feels personalised, offering customers relevant discounts or loyalty rewards right when they’re most likely to engage. It’s a seamless way to stay competitive, maximise margins, and increase customer satisfaction—all while driving repeat business through tailored offers that adapt to each shopper's unique journey. ➡ Enhanced Loyalty Through Personalised Rewards GenAI helps personalise loyalty programme rewards, delivering offers that resonate based on individual behaviour, increasing retention and turning one-time buyers into repeat customers. Please do have a listen, I really enjoyed the conversation. Apple: https://bit.ly/AP3-L Spotify: https://bit.ly/SO3_L Amazon Music: https://bit.ly/AZ3_L

Customer loyalty platforms decide whether a brand keeps customers for life or loses them to the competition. What used to be static batch-driven systems is now powered by #DataStreaming with #ApacheKafka. Enterprises across industries rely on real-time #Loyalty and #Rewards platforms to increase retention and boost revenue. Kafka ensures #DataConsistency across all applications and databases while enabling context-specific decisions in the moment. Case studies prove the value: - #Albertsons revamped its loyalty platform to deliver real-time offers across 2200+ stores - #VirginAustralia synchronizes frequent flyer rewards across airline, CRM, and booking systems - #GlobeTelecom moved from batch to event-driven processing for personalized customer rewards - #Disney+ #Hotstar gamifies live events at massive scale with real-time engagement - #Porsche built Streamzilla as its central platform for omnichannel customer experience Kafka provides the backbone for real-time points accumulation, event-driven offers, cross-channel integration, engagement tracking, fault-tolerant transactions, and compliance-ready audit trails. It acts as the integration hub, not only for retail or telco, but also for automotive, aviation, public sector, and media. #StreamingData is no longer a technical nice-to-have. It is a business-critical capability to create meaningful loyalty and rewards experiences at scale. More details: https://lnkd.in/eedeu8SE How is your organization rethinking customer loyalty in the era of real-time engagement and streaming data?