# AI-Powered Lead Qualification and Follow-Up Template This template provides a ready-to-use workflow for sales and customer engagement teams who want to automate lead qualification and follow-up using **MCP servers on composio.dev**. --- ## How It Works 1. **Qualifying Questions** The AI agent engages with users by asking a few qualifying questions (e.g., name, email, primary need, budget). 2. **Lead Scoring** Based on the conversation, the agent applies a lead scoring condition: - **Hot Lead** - **Mid Lead** - **Low Lead** 3. **Data Logging in Google Sheets** Using the **Google Sheets MCP server**, the agent populates a CSV file (`LeadsList`) with the extracted details: - Full Name - Email - Primary Need - Budget - Lead Score - Status You can view the data being logged in real-time via the [Leads Spreadsheet](https://docs.google.com/spreadsheets/d/1vh82Qt4ttLepW2w0iZJ6hzxAEHGm3bORimc_9iS1kh0/edit?usp=sharing). This sheet is automatically populated as the AI agent qualifies leads and sends follow-up emails. 4. **Personalized Follow-Up via Gmail** Through the **Gmail MCP server**, the agent sends a personalized HTML-formatted follow-up email: - **Hot Leads:** Acknowledge their use case and invite them to schedule a call via a calendar link. - **Mid Leads:** Acknowledge their use case and request their website address. - **Low Leads:** Thank them for reaching out and inform them that the team will follow up soon. 5. **Workflow Tracking** Finally, the agent updates the **Status column** in the sheet to *“Follow up sent”*, ensuring the workflow is fully tracked. --- ## Plug-and-Play Setup This template is designed to be **plug-and-play**: - Connect your MCP servers for **Google Sheets** and **Gmail** - Embed them into an **AI Prompt** - Let your agent handle the rest It’s ideal for teams looking to **streamline lead management**, reduce manual data entry, and ensure **timely, personalized follow-ups**.

### How It Works & Key Benefits This template creates a learning loop between your human agents and your AI Assistant. Every time a support request is handled by a human and then closed, the flow kicks in: - It collects the conversation transcript (excluding technical/system noise). - It uses an AI model (via Code Action) to evaluate whether a reusable answer exists. - If the conversation contains generic, helpful content: - **Sanitize:** Sensitive or user-specific data is automatically removed. - **Summarize:** A sanitized title and summary are generated. - **Check for duplicates:** The system checks if a similar answer already exists in your Knowledge Base. - **Add to KB:** If the content is new, it is automatically published as a new article. ### Benefits - Continuously improve your AI Agent with real support knowledge - Reduce manual effort to keep your Knowledge Base up to date - Keep learning in the background while your team works normally - Ideal for teams that want to scale their support and capture institutional knowledge ### How to Use It Import this flow into your project, **edit the Knowledge Base name**, and you’ll have a working self-learning agent in minutes — no coding or setup required. To understand how this flow works under the hood and how to build it manually, read the full step-by-step tutorial here: **[Build the Self-Learning AI Agent Flow from Scratch](https://guide.tiledesk.com/knowledge-base/self-learning-ai-agent#self-learning-ai-agent-build-the-flow-from-scratch)**

This advanced template builds upon basic lead qualification by adding intelligent data validation and automatic tracking attributes. Here's how it works: **Welcome Message:** * Start with a personalized reply message that sets professional expectations * Customize the greeting based on your brand voice and requirements * Learn more about [Reply action here](https://guide.tiledesk.com/ai-chatbots-and-automation/actions-explained/reply-action) **Advanced ChatGPT Task Configuration:** * Insert the ChatGPT task into the default fallback block for comprehensive lead qualification * Configure AI settings with enhanced system context for data validation * Learn how to use the [ChatGPT task feature](https://guide.tiledesk.com/ai-chatbots-and-automation/actions-explained/chatgpt-task) **System Context Example:**</br> "Your role is to qualify leads by asking Tiledesk users the following questions: - user full name - user email - user phone number - user company If the user answers incorrectly (e.g., an invalid email format) or refuses to answer, politely ask again and explain that gathering this information helps us provide a tailored solution. Once you have the answers to all questions, respond strictly with just one word: "done" do not add anything before after" **Saving Attributes on Tiledesk** * Add GPT reply attributes block to capture all user responses * Use another ChatGPT task to extract: full_name, email, phone, and company * Enable real-time tracking attributes for immediate lead processing **Data Validation Features:** * Email Verification: Detects common fake email patterns and invalid formats * Phone Validation: Ensures proper phone number structure Import this advanced template into your project for free and customize the validation rules and tracking attributes to match your specific requirements.

This AI agent automates customer interactions and acts as both a shopping assistant and a customer support agent — all in Spanish, English, and Italian. It has been trained using official website content, FAQs, and external sources to provide fast, accurate answers about: - **Tailored product suggestions** through guided conversations - **Upcoming matches**, ticket pricing by sector, and direct purchase links - **Company policies** including shipping, refunds, and general inquiries You can easily import this template into your Tiledesk project, upload your content with just a few clicks, and customize the responses to fit your needs. Your AI agent will be live and supporting users in multiple languages within minutes.

# AI Agent Template Tutorial This AI agent template is designed to provide a truly humanized experience for users through several actions. Here’s a summary of how it works and how to implement it: ## Step-by-Step Process ### 1. Welcome Message - The AI agent welcomes users with a friendly message and offers two options: 1. Reserving a room 2. Talking with an operator ### 2. Booking Information - If the user selects the first option, the conversation moves to the next [block](https://gethelp.tiledesk.com/articles/how-to-create-blocks/), which includes a [ChatGPT Task](https://gethelp.tiledesk.com/articles/learn-how-to-use-the-chatgpt-task-feature/). This task's role is to ask for necessary information in a natural way, such as: - Email address - User’s full name - Check-in and check-out dates - Confirmation at the end ### 3. Gathering Details - The AI agent continues the conversation until it gathers all the required information from the user. It then shares a summary with the user. ### 4. Room Availability - Finally, the bot shares the available rooms with a short description of each and some images to help the user make their decision. ### 5. Operator Assistance - During the conversation, if the user asks to talk with an operator, the AI agent will transfer the conversation to the available operator for further support. ## Implementation - **Insert Prompt**: In the AI setting section of the ChatGPT Task action, insert the following prompt to ensure the AI asks for booking details in a natural way: "You are a friendly support AI assistant at ROYAL HOLIDAY HOTEL. Your task is to ask users four questions: 1. Name and Surname 2. Check-in and Check-out Date 3. Email Address 4. Number of Guests If the user refuses to answer or provides incorrect information, try to ask again and convince them to share the correct information. Once the user answers all four questions, you must respond strictly in this format: **Summary:** - **User Name** - **Check-in** - **Check-out** - **Email** - **Number of Guests** If the user explicitly informs they need to talk with an operator or an agent, reply with only one word: "operator""

This template is highly effective yet simple, asking important questions like customer needs, email addresses, and more. Here's how it works: **Welcome users**: Start with a simple reply message, which you can customize based on your preferences. [Ream more about Reply action here](https://gethelp.tiledesk.com/articles/reply-action/) **ChatGPT Task**: Insert the ChatGPT task into the default fallback block, then define the system context under AI settings. [Learn how to use the ChatGPT task feature](https://gethelp.tiledesk.com/articles/learn-how-to-use-the-chatgpt-task-feature/). For this template, I used the following system context, but you can modify it as needed: "Your role is to qualify leads by asking Tiledesk users the following questions: - Their email address - Primary needs - Deadline - Budget - Whether they would like to integrate with instant messaging channels Once you have all the answers, thank them and let them know we will get back to them soon. If the user answers incorrectly (e.g., an invalid email format) or refuses to answer, politely ask again and explain that gathering this information helps us provide a tailored solution." **Add a new block**: Incorporate GPT reply attributes. Simple yet highly effective. Import this template into your project for free and easily customize it to fit your needs.

The combination of Tiledesk’s AI features with Zendesk’s robust [ticketing system](https://tiledesk.com/blog/chatbot-ticketing-system/) will elevate your customer support efficiency. Tiledesk AI agents can independently address up to 75% of customer inquiries. When they fall short, they can issue a ticket and send it to your Zendesk agent dashboard instantly. This saves your human agents time and keeps your support team organized and efficient. To configure this template, after importing it, follow the tutorial below: [Integrate Tiledesk AI Agent with Zendesk Ticketing](https://gethelp.tiledesk.com/articles/integrate-tiledesk-ai-agent-with-zendesk-ticketing/)

## Tutorial: Come utilizzare il bot di Tiledesk per prenotazioni di tour Benvenuti al tutorial su come utilizzare il nostro bot di Tiledesk per effettuare prenotazioni per tour culturali. Questo bot è progettato per facilitare la prenotazione e fornire informazioni pertinenti ai visitatori. ### Introduzione Il nostro bot di Tiledesk è stato creato per assistere i visitatori nel processo di prenotazione di tour, offrendo un'interfaccia semplice ed efficace. Come esempio è stato scelto l'Anfiteatro e Teatro Romano di Lecce, ma può essere facilmente adattato anche ad altre Organizzazioni Culturali e Creative. ### Come iniziare Per iniziare a interagire con il bot, seguite questi semplici passaggi: #### 1. Saluto Iniziale - Quando avviate la chat, il bot vi darà il benvenuto con un messaggio di saluto e presenterà alcune opzioni iniziali come `Orari di apertura`, `Prenotazioni` e `Informazioni sul Museo`. Si può personalizzare il messaggio iniziale o cambiare le opzioni presenti all'interno dei bottoni. #### 2. Fare una Prenotazione - Cliccate su `Prenotazioni` per iniziare il processo di prenotazione. - Il bot vi chiederà il numero di visitatori. Rispondete inserendo il numero appropriato. Questi parametri possono essere poi inviati al gestionale che raccoglie tutte le prenotazioni. #### 3. Scegliere la Data e l'Ora - Dopo aver confermato il numero dei visitatori, il bot richiederà la data della visita. Inserite la data nel formato giorno/mese/anno. - Successivamente, vi sarà chiesto di scegliere l'orario preferito per la visita (mattina o pomeriggio). #### 4. Conferma della Prenotazione - Una volta inseriti tutti i dettagli, il bot riepilogherà la vostra prenotazione e vi invierà una conferma via email con tutti i dettagli del tour, grazie ai parametri che sono stati raccolti dal bot. ### Chiusura della Chat - Dopo aver completato la prenotazione, potete chiudere la chat cliccando su `Chiudi Chat` o continuare a interagire con il bot per altre informazioni. ### Supporto In caso di necessità, il bot può mettervi in contatto con un operatore umano per assistenza diretta, garantendo un'esperienza utente completa e soddisfacente. --- Utilizzate questo tutorial per navigare facilmente attraverso il processo di prenotazione e sfruttare al meglio le funzionalità del nostro bot. Buona visita!

In the world of customer service, chatbots have become an integral part. They provide quick and efficient responses, enhancing the user experience. This chatbot template will ask the user which product they are interested in and then share the price of that product. I will walk you through the process of creating this chatbot below. This chatbot utilizes Global variables, which are constants throughout the conversation flow, and can be recalled and reused at any point during the conversation. ## What are Global Variables? Global variables are key-value pairs that remain constant throughout the conversation flow. The 'Key' is the name of the variable, and the 'Value' is the data you input. For this template, I will use a Global variable named 'Pricetable', where we will store the names of the products and their respective prices. ## The Power of GPT Tasks This chatbot template is powered by GPT Tasks. This means we write prompts to find the price of the product that the user asks for, and then generate human-like responses with the price of the item. If the bot cannot find the item in the list, it will generate a response saying, "Oh sorry, the item is not available right now." ## Step-by-Step Tutorial Now, let's dive into the step-by-step process of creating this chatbot: 1. **Setting up the Global Variable**: First, select "Globals" from the left sidebar menu. Then, add a new global variable. 2. **Choosing a Key and Inputting Values**: Next, choose a Key for your variables and input your price list in the Value section. 3. **Capturing User Reply**: Now, return to the Blocks section to design the bot. You'll need an action called "Capture User Reply" to capture the customer's response. You can assign an attribute to it. In this case, we used 'UserReply' as the attribute. 4. **Using the ChatGPT Task Action**: For the next block, use the 'ChatGPT Task' action. You can see the prompt I wrote and the way we recall the price list. Prompt: "Given the user’s reply, {{UserReply}}, which is asking for the price of a product, try to identify the product from the {{pricetable}}. The {{pricetable}} contains product names in the first column and their corresponding prices in the second column. Your task is to find the product that the user asked for in their reply, {{UserReply}}, and then find that product in the {{pricetable}}. Please share only the price of the product that the user has inquired about. If there is a minor spelling error in the product name provided by the user, try to understand what product they’re referring to and provide the price for that product. Your responses should mimic a human agent supporting users. If you can’t find the product that the user is asking for in the {{pricetable}}, respond by saying that the product is not currently available." 5. **Adding a New Reply Block**: Finally, add a new reply block and simply choose the {{gpt_reply}}. And that's it! You have successfully created a chatbot that can share product prices with customers. In the video below, you can see how the bot finds the price in the table and shares it with the user. I hope this tutorial was helpful in guiding you through the process of creating a chatbot for Tiledesk. Happy bot building!

A chatbot that advertises your special offers. It collects the customer’s name, email and phone number to share the promo code and for marketing purposes.

The Tiledesk Feedback GPT Bot is a transformative tool designed to enhance your customer engagement strategy. It leverages the power of ChatGPT AI to analyze real-time customer feedback and generate personalized responses. Whether a customer rates their experience as excellent or less than satisfactory, the bot responds appropriately, expressing gratitude or empathy as needed. This bot is not just a feedback tool; it’s an essential part of your customer engagement strategy, helping you understand and respond to your customers’ needs more effectively.

A proactive chatbot that helps increase the number of demo requests, provides info about pricing, plans, product features, and connects website visitors to a sales team member if the user requests.