How to Automate Customer Interactions

How we built AI agents that run a LOT of our business using n8n (detailed breakdown) After a few months of refining our automation stack at Kendo ai and my other companies, I want to share exactly how we're using n8n to create AI-powered workflows that operate 24/7 First, what is n8n? It's an open-source workflow automation tool that connects your apps, data, and APIs. Think Zapier but far more powerful and customizable. Here's our exact setup for creating autonomous agents: The foundation: Customer data flow Every customer interaction feeds into our CRM n8n monitors for trigger events (new signup, support request, etc.) Custom nodes extract relevant context from these events Real example: When someone books a demo, our n8n workflow instantly creates a personalized onboarding sequence based on their company size, industry, and the specific features they showed interest in. The intelligence layer: AI integration n8n connects to Claude API and GPT-4 for different reasoning tasks We've built custom prompts for each business function Webhooks allow the AI to trigger specific responses Real example: Our support system has n8n workflows that analyze incoming tickets, categorize the issue, retrieve relevant documentation, and draft personalized responses for our team to review before sending. The action layer: Automated responses Sentiment analysis determines appropriate response paths n8n routes information to the right team member Custom logic handles exceptions and escalations The continuous improvement cycle: Every interaction gets logged and analyzed n8n pulls data weekly to identify bottlenecks Successful patterns get reinforced in updated workflows The game-changer has been creating specialized agents for different functions: Content Agent: Monitors our post performance, suggests topics based on search trends, drafts outlines, and schedules publication Sales Agent: Uses customer info to help create the ai prospects inside of Kendo Ai. Basically creating randomized life stories for the Ai Data Agent: Pulls insights from customer behavior, generates reports, and flags opportunities we're missing Advanced techniques we're using: Chaining multiple n8n workflows together for complex decision trees Using temporary data storage to maintain context between workflow runs Creating feedback loops where one agent can trigger another Start with a single, high-value process and perfect it before expanding. Our first workflow just handled meeting scheduling, but it was the foundation for everything else. (Pro tip: Start with the cloud version to learn, then migrate to self-hosted for more control and to avoid workflow execution limits) N8N is like zapier on steroids and while it has a bit of a learning curve, it is well worth the time investment and automating things inside of your business Comment "n8n" below and i'll try my best to send you all some of the templates we use 🤝🏽 #n8n #ai

Still sending manual emails to your customers? Here’s how we automated the entire email marketing funnel for our client. Most large enterprises have already embraced AI to track SKUs, forecast hiring, and optimise financial decisions. But when it comes to marketing? They’re still stuck with batch-and-blast emails… generic content, poor timing, zero personalisation. AI is improving how companies work but not yet how they connect with customers. Recently, we helped a retail client move from batch emails to AI-driven journeys using Salesforce Marketing Cloud. 📍We mapped customer data across touchpoints to build unified audience profiles 📍We set up automated, trigger-based journeys tailored to user behavior and purchase history Within 3 months: ↪️ Customer engagement increased by 38% ↪️ Repeat purchases rose by 22% especially among previously inactive users By connecting customer data and automating responses, their marketing became timely, relevant, and proactive. Remember, when AI powers the backend and the customer experience, that’s when real growth happens. Which part of your marketing funnel do you think AI should automate next?

For PMs who want to use AI agents to be more productive but feel stuck coming up with ideas, I've been experimenting with a prompt: (this works best in a project that already has context on you/your team/product) ❝❝❝ Based on what you know about me and my organization, please brainstorm five ideas for an AI automation I can build using platforms such as Zapier Agents/Lindy AI/Relay app/Cassidy AI/Gumloop/ etc. These should help me as a product manager save time on draining-yet-essential tasks that take me away from more valuable, strategic, and creative use of my attention and energy. Ask yourself: What ongoing repetitive work requires some judgment and writing abilities, but not my full expertise and intuition? # IMPORTANT: these should be event-driven AI automations, not batch tasks Only suggest event-driven automations that process items one-at-a-time as they arrive. Do NOT suggest batch tasks that process multiple items on a schedule (e.g., "every morning scan all..." or "weekly compile..."). Why: AI automations shine in one-at-a-time, repetitive tasks. They do best when designed for immediate responses to individual triggers. ❌ WRONG (Batch Task): "Every morning, scan all new support tickets and summarize them" ✅ RIGHT (Event-Driven): "When a new support ticket arrives, analyze it and alert me if it's urgent" # Examples Below are examples of use cases where product managers have gotten a lot of value from AI agents. 1. Compile fragmented information that would require a lot of clicks “When a new message is posted in the #feature-requests Slack channel, distill the customer request into 2-5 keywords. Search those keywords in recent Slack threads, HubSpot conversations, and Gong snippets, and reply to the thread with what you find.” “Every morning scan my calendar for customer calls, and instead of searching the web, DM me with recent interactions from this customer in Salesforce, Gong, and Zendesk.” “Every Monday morning, prepare a competitor activity digest by scanning recent blog posts, App Store updates, and X announcements.” “When a customer churns, post a message in the #churn-lessons channel with recent support interactions, NPS rating and date, and churn survey response.” 2. Boring, Sisyphean tasks with high upside “Monitor the pricing pages of 5 competitors for changes.” “DM me a weekly report with bugs that are nearing their SLA deadline for the associated customer, and cc each respective CS representative.” 3. Scanning exhausting amounts of data “DM me with support cases where the resolution was around product confusion rather than tech.” “Monitor NPS responses being posted as messages in a Slack channel. If something is clearly a technical issue, create a support ticket in Zendesk.” 4. Drafting updates “Every Friday at 10 a.m., write a summary of progress made across all teams in our project board, across epics, changes made to scope, and highlight any timeline changes.” ❞❞❞

Four years ago, I worked on a technical automation project for a client via Fiverr. This week, he reached out again, same client, new challenge. He needed a system where AI-powered agents could make personalized inbound & outbound calls to leads and then automatically handle all the follow-up tasks without human intervention. So, I built a connected automation using Retell AI, GoHighLevel (GHL), Make.com, and Chatdash that: ➡️ For inbound calls: Looks up the lead in GHL in real-time, sends the details back to the agent, and allows live appointment booking while on the call. ➡️ For outbound calls: Triggers from actions in GHL, sends lead info to the agent for a personalised approach, waits for the call to finish, gathers transcript + sentiment, and stores it in GHL. ➡️ Across both: Retell AI checks calendar availability, and Make.com books meetings based on the lead’s preferred time, no manual follow-up needed. Impact: ✅ Personalized conversations every time ✅ Automated note-taking and sentiment logging ✅ Faster appointment scheduling with zero back-and-forth Automation isn’t just about replacing task; it’s about enhancing human interactions so agents can focus on building relationships, not juggling tabs and CRMs. If your sales or support team still spends time searching for client info during calls or manually scheduling follow-ups, this is the type of automation that changes the game. PS: What’s one repetitive client interaction in your business you’d love to automate?

The AI Revolution in Call Centers: From Chatbots to Voice Synthesis In 2024, artificial intelligence is dramatically reshaping customer service, particularly in call centers, where 90% now utilize AI technology. This transformation is redefining how businesses engage with customers, offering enhanced efficiency and personalization. 🌍 Key Features and Benefits - Enhanced Efficiency: AI automates routine tasks, allowing human agents to focus on complex issues. - Improved Customer Experience: Faster, personalized service through data analysis and predictive capabilities. - Boosted Agent Productivity: Real-time assistance and automated post-call tasks streamline operations. - Cost Reduction: Automation and smart routing lead to significant savings. 🌍 Cutting-Edge Voice AI Technologies Recent advancements in voice tokenization and AI voice synthesis are pushing the boundaries of customer interactions: 1. dMel: A novel speech tokenization method that outperforms existing techniques in recognition and synthesis. 2. SpeechTokenizer: Combines semantic and acoustic tokens for a comprehensive speech representation. 3. Vec-Tok Speech Framework: A system for speech vectorization showing strong performance across various speech tasks. 🌍 Applications of Voice AI - Voice Cloning: Companies like ElevenLabs are creating high-fidelity voice cloning for customized AI agents. - Multilingual Support: AI-generated speech enables seamless multilingual service. - Emotional Intelligence: AI can modulate tone and emotion for empathetic interactions. - Personalization: Unique voice identities tailored to different customer segments. 🌍 Implementation Strategies 1. Assess Needs: Identify areas for AI implementation. 2. Start Small: Begin with select AI applications like chatbots. 3. Invest in Training: Prepare your team to work with AI technologies. 4. Choose Compatible Tech: Ensure seamless integration with existing systems. 5. Monitor and Iterate: Continuously evaluate and adjust AI performance. 🌍 Ethical Considerations Address ethical concerns regarding disclosure and potential misuse, prioritizing transparency in AI voice technologies. 🌍 Future Outlook The integration of advanced voice AI with existing solutions will redefine call center operations. With predictions of a 50% productivity increase and enhanced customer experiences, AI is set to deliver unprecedented efficiency and personalization in customer service. By leveraging these cutting-edge technologies, businesses can create more responsive and efficient customer service experiences, positioning themselves for success in an increasingly digital world. 1. Wang, L., et al. (2023). Voice‐based AI in call center customer service: A natural field experiment. Production and Operations Management. 2. Cornell University. (n.d.). AI in Contact Centers: Artificial Intelligence and Algorithmic Management in Frontline Service Workplaces. 4Enlight, AI Innovation Lab, AI Research Lab

𝗔𝗜 𝗶𝘀 𝗲𝘃𝗲𝗿𝘆𝘄𝗵𝗲𝗿𝗲 𝗿𝗶𝗴𝗵𝘁 𝗻𝗼𝘄. 𝗦𝗼 𝗮𝗿𝗲 𝗵𝗮𝗹𝗳-𝗯𝗮𝗸𝗲𝗱 𝗽𝗿𝗼𝗺𝗶𝘀𝗲𝘀. My team has experimented A LOT with how to use AI meaningfully. It wasn’t always smooth. We made mistakes, iterated, and eventually landed on a framework that works pretty well—and honestly, I’m blown away by what the team pulled off. Big kudos to my cofounder Francis Brero for running a weekly AI hackathon. 𝗪𝗛𝗔𝗧 𝗪𝗘'𝗩𝗘 𝗟𝗘𝗔𝗥𝗡𝗘𝗗 • 🎯 Focus on automating 𝘁𝗮𝘀𝗸𝘀, not roles • ⚠️ Don’t aim for 100% automation — 𝗮𝗶𝗺 𝗳𝗼𝗿 𝟴𝟬%  (it's 10x easier than the last 20%) • 🛠️ 𝗨𝘀𝗲 𝘁𝗵𝗲 𝘁𝗼𝗼𝗹𝘀 𝘆𝗼𝘂 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝗵𝗮𝘃𝗲 before evaluating new ones The meta takeaway is: “𝗗𝗼𝗻’𝘁 𝗹𝗶𝘀𝘁𝗲𝗻 𝘁𝗼 𝗔𝗜 𝘃𝗲𝗻𝗱𝗼𝗿𝘀.” 😅 𝗢𝗨𝗥 𝗖𝗨𝗥𝗥𝗘𝗡𝗧 𝗣𝗥𝗢𝗖𝗘𝗦𝗦 Let's take the Sales Account Exec role as an example. 𝗦𝗧𝗘𝗣 𝟭: 𝗟𝗶𝘀𝘁 𝘁𝗵𝗲 𝗸𝗲𝘆 𝗮𝗰𝘁𝗶𝘃𝗶𝘁𝗶𝗲𝘀 of the role Be as granular as possible. You can use a ChatGPT prompt like "𝘠𝘰𝘶 𝘢𝘳𝘦 𝘢 𝘉2𝘉 𝘚𝘢𝘭𝘦𝘴 𝘓𝘦𝘢𝘥𝘦𝘳 𝘧𝘰𝘤𝘶𝘴𝘦𝘥 𝘰𝘯 𝘴𝘦𝘭𝘭𝘪𝘯𝘨 𝘵𝘰 𝘮𝘪𝘥-𝘮𝘢𝘳𝘬𝘦𝘵 𝘢𝘯𝘥 𝘦𝘯𝘵𝘦𝘳𝘱𝘳𝘪𝘴𝘦 𝘤𝘶𝘴𝘵𝘰𝘮𝘦𝘳𝘴. 𝘎𝘪𝘷𝘦 𝘮𝘦 𝘢 𝘥𝘦𝘵𝘢𝘪𝘭𝘦𝘥 𝘭𝘪𝘴𝘵 𝘰𝘧 𝘢𝘤𝘵𝘪𝘷𝘪𝘵𝘪𝘦𝘴 𝘢 𝘵𝘺𝘱𝘪𝘤𝘢𝘭 𝘈𝘤𝘤𝘰𝘶𝘯𝘵 𝘌𝘹𝘦𝘤𝘶���𝘪𝘷𝘦 𝘥𝘰𝘦𝘴 𝘰𝘷𝘦𝘳 𝘢 𝘸𝘦𝘦𝘬, 𝘸𝘪𝘵𝘩 𝘢𝘱𝘱𝘳𝘰𝘹𝘪𝘮𝘢𝘵𝘦 𝘩𝘰𝘶𝘳𝘴 𝘧𝘰𝘳 𝘦𝘢𝘤𝘩." 𝗦𝗧𝗘𝗣 𝟮: 𝗦𝗰𝗼𝗿𝗲 𝗲𝗮𝗰𝗵 𝗮𝗰𝘁𝗶𝘃𝗶𝘁𝘆 𝗯𝘆 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻 𝗹𝗲𝘃𝗲𝗹 Use a simple 0%, 20%, 80%, 100% scale. Rate where you are today, and where you should be. 𝗦𝗧𝗘𝗣 𝟯: 𝗣𝗶𝗰𝗸 𝗼𝗻𝗲 𝗮𝗰𝘁𝗶𝘃𝗶𝘁𝘆 𝘁𝗼 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲 Focus on the low-hanging fruit. 𝗦𝗧𝗘𝗣 𝟰: 𝗕𝘂𝗶𝗹𝗱 𝗮 𝗾𝘂𝗶𝗰𝗸 𝗽𝗿𝗼𝘁𝗼𝘁𝘆𝗽𝗲 Or ask someone who "code vibes" to help. Start with tools your team already knows. 𝗦𝗧𝗘𝗣 𝟱: 𝗣𝗼𝗹𝗶𝘀𝗵 𝗮𝗻𝗱 𝗿𝗼𝗹𝗹 𝗶𝘁 𝗼𝘂𝘁 If the first try is not a win, evaluate specialized AI tools or try to automate another activity. 📎 Here's our current 𝗔𝗘 𝗮𝗰𝘁𝗶𝘃𝗶𝘁𝘆 𝗺𝗮𝘁𝗿𝗶𝘅 𝗮𝗻𝗱 𝘁𝗵𝗲 𝘁𝗼𝗼𝗹𝘀 𝘄𝗲 𝘂𝘀𝗲: https://lnkd.in/enuCaBks Feel free to make a copy and adapt it to your company and roles (SDRs, content marketers, solutions engineers, customer success managers, etc.). 𝗥𝗘𝗦𝗨𝗟𝗧𝗦 We didn’t automate everything—but task by task, it adds up. ➡️ In our case, we've freed up ~𝟭𝟴 𝗵𝗼𝘂𝗿𝘀 𝗮 𝘄𝗲𝗲𝗸 𝗽𝗲𝗿 𝗔𝗘 𝘀𝗼 𝗳𝗮𝗿—time they now spend with customers, on deals, and improving their craft (or creating amazing memes -> Hayden Anderson a.k.a the Emily Dickinson of "meme-led sales") 💬 Over to you. What’s been your most useful AI workflow so far? What are your learnings? Or—what’s still a mess? And if you're curious about how we automated a specific activity—like call prep, proposal write-ups, or security questionnaire responses—let me know!

We built a Zendesk email assist AI agent and it's handling a full quarter’s work for one human support rep. Here's the step-by-step flow: 1. User sends a complex or nuanced product question to support@voiceflow.com 2. Tico (our AI agent) reviews the question and passes the content and intent. 3. The most fitting knowledge base is tapped via confidence level. 4. A personalized, accurate & highly-specific response is drafted. 5. The draft is slotted into Zendesk as a private comment. 6. Our team reviews, tweaks if necessary, and sends it to the user. This has slashed the onboarding and training time for support staff that's typically slowed down by the complexity of the product. The impact? ✅ Our support team is no longer just keeping up; they’re ahead, delivering faster, sharper responses. ✅ Customers feel understood, their issues addressed with pinpoint accuracy, boosting our CSAT scores. ✅ Tico’s continuous learning means every interaction makes it smarter, ready for even the most nuanced queries. So far, Tico Assist is tackling over 2000 tickets - a full quarter’s work for one human support rep, for less than the price of lunch. If you’re navigating high support volumes with a lean team, this type of Zendesk AI Assist Agent can help blend automation with quality for your customers. P.S. Tico doesn’t just fetch any answer. It pulls from the most relevant knowledge base (e.g. a technical code response for a developer question). From my post last week, this multi-knowledge base strategy is something that I think we will see much more of in CX this year.

This is why AI agents are exploding in adoption—they deliver real business value by turning LLM intelligence into automated action. They are becoming the backbone of automation in customer support, operations, sales, and internal workflows, replacing repetitive tasks that humans perform by clicking buttons and following rules. Instead of just generating text, AI agents orchestrate actions, making them far more valuable in real business environments. A perfect example is customer-support order-tracking. Every day, support teams receive hundreds of emails asking, “Where is my order?” A human agent reads the message, extracts the order number, searches in the backend system, checks the shipment status in the carrier portal, decides what’s wrong, and finally replies or creates a follow-up ticket. This manual process takes 2–3 minutes per email—highly repetitive and expensive at scale. An AI agent can now automate this entire workflow end-to-end. It first extracts the order ID from the customer’s message, then calls the lookup_order tool to fetch order details, and the check_tracking_status tool to get carrier updates. Next, it analyzes the status and determines whether delivery is delayed, lost, or on track. Based on the result, it triggers the right action, such as create_internal_ticket, initiate_carrier_trace, or reschedule_delivery. Finally, the agent generates a personalized reply to the customer with the latest status—without any human involvement. With memory, it can even handle future follow-ups intelligently. Read more on the internal architecture of an AI Agent in detail: https://lnkd.in/gEhVX5cY Build Your First AI Agent in 10 Minutes! (No Code Needed): https://lnkd.in/gjNf5yyr

Last month our team of 5 did the work of 50 people. While taking every weekend off. The secret? We replaced the most expensive job with code: Let me show you exactly how this works. Three features transformed our support from "answers questions" to "handles entire workflows": 1. Guidance: When someone requests a feature, our AI: - Thanks them properly - Logs feedback automatically - Directs to feedback portal - Updates them on progress - Maintains perfect brand voice 2. Processes: Take a refund requests. Our AI: - Checks account status - Verifies eligibility - Processes through Stripe - Sends confirmation - Logs everything instantly 3. Actions: This is the real power. AI can: - Pull CRM data - Process payments - Update records - Trigger notifications - Make API calls Real workflow example: Customer: "Can I get a refund?" AI: - Verifies account instantly - Checks eligibility - If eligible: processes immediately - If not: explains why + alternatives - Everything logged in seconds What used to take 30 minutes Now happens automatically. Start with feature requests. It's simple but shows the power. Then you'll want to automate everything. Because your support team should solve problems. Not copy-paste responses at 3AM. What would you automate first? Interested in seeing how Helply can do this for you? Shoot me a DM

Automation is transforming the way we work, but not all automation is the same! Let’s break it down in simple terms with real-world examples. RPA (Robotic Process Automation) Mimics human actions on a screen (clicking, typing, copying). Best for repetitive, rule-based tasks. Example: A bot logs into an email, downloads invoices, and enters data into an ERP system. Intelligent Automation (IA) RPA + AI capabilities (OCR, NLP, Machine Learning). Can handle semi-structured and unstructured data. Example: An AI-powered bot extracts data from scanned invoices (OCR) and classifies them before processing payments.  API Automation Connects software directly without using a UI. Faster and more reliable than RPA. Requires coding knowledge to set up API calls. Example: An API automatically updates customer records in a CRM when a new order is placed—without a bot clicking anything! Why Combine RPA + API? RPA is great for legacy systems that don’t support APIs, while APIs make automation faster and more reliable. Example: A bot logs into an old accounting system, extracts customer data, and then uses an API to update a modern CRM—best of both worlds!    AI Agents Autonomous, learns from interactions, and makes decisions. Works with structured and unstructured data. Example: An AI-powered assistant understands customer queries, learns from past interactions, and automatically books meetings. For more insights on automation, subscribe to my newsletter 👉 https://lnkd.in/dpqw4WtS