Skip to main content
Start for freeTalk to salesRequest a demo
Developer Portal
Streamlining Lead Qualification: Integrating Zendesk Sell with Chatbot API for Enhanced Efficiency
Chat SDK v4 2x

Swift, Kotlin, and TypeScript SDKs

Build in-app chat, calls, and live streaming

On This Page

Streamlining Lead Qualification: Integrating Zendesk Sell with Chatbot API for Enhanced Efficiency

Jason Allshorn 1
Jason Allshorn
Solutions Engineer
Sendbird Docs
Sendbird Community
Chat SDK v4 2x

Swift, Kotlin, and TypeScript SDKs

Build in-app chat, calls, and live streaming

Chat SDK v4 2x

Swift, Kotlin, and TypeScript SDKs

Build in-app chat, calls, and live streaming

On This Page

Streamlining Lead Qualification: Integrating Zendesk Sell with Chatbot API for Enhanced Efficiency

In the competitive landscape of sales and customer relationship management, efficient lead qualification is paramount for driving business growth and maximizing revenue potential. One powerful solution lies in integrating Zendesk Sell with chatbot API technology. In this comprehensive tutorial, we explore the process of integrating Zendesk Sell with chatbot API to streamline lead qualification processes, optimize sales workflows, and empower sales teams to make informed decisions.

In this module, we will delve into the innovative integration of Sendbird's AI Chatbot with Zendesk Sell to automate lead qualification and creation. This integration aims to enhance customer engagement, streamline lead management, and improve sales efficiency.

This is a tutorial for developers keen on optimizing customer interactions through the strategic integration of Zendesk Sell with the power trio of Chatbot API, Chatbot UI, and chat widgets. In this guide, we'll navigate the intricate process of seamlessly merging Zendesk Sell with cutting-edge chatbot technologies, ensuring a harmonious blend of efficiency and user engagement. We'll explore the strategic integration of chat widgets, turning your Zendesk Sell platform into a hub for visually appealing and interactive conversations. Embed these widgets effortlessly, creating a cohesive and engaging environment for your users.

Use Cases

  • Businesses seeking to improve lead qualification and management through the use of Sendbird’s AI Assistant bots.
  • Companies aiming to enhance customer engagement through AI chat technology.
  • Organizations looking to integrate chatbot interactions with CRM systems for better customer data management.

Key Components of the Integration

Lead Qualification Automation

By integrating Zendesk Sell with chatbot API, businesses can automate lead qualification processes, allowing chatbots to engage with leads, gather relevant information, and assess their readiness for conversion.

Real-time Lead Alerts

Enable real-time notifications and lead alerts within Zendesk Sell by integrating chatbot API, ensuring that sales teams are promptly notified of new leads and can take immediate action to follow up and engage with prospects.

Data Enrichment and Insights

Leverage chatbot API to enrich lead data with additional insights and information, such as social media profiles, company details, and behavioral data, providing sales teams with valuable context to tailor their outreach efforts effectively.

Lead Nurturing Workflows

Implement lead nurturing workflows within Zendesk Sell by integrating chatbot API, enabling chatbots to engage with leads at various stages of the sales funnel, deliver personalized content, and guide them through the buying journey.

Step 1. Gather Zendesk Token and Use POST in Postman to generate sample lead

There is a walkthrough video here for Zendesk Sell.

  1. Login and create a Zendesk Sell Token.

    1. Guide to generating a token

  2. Make a POST call using PostMan to check that everything is working as expected.

  3. Example request.


{
"data": {
"first_name": "John",
"last_name": "Doe",
"email": "john.doe@example.com",
"description": "The user looks like a typical lead for these reasons."
}
}


Notice how the lead details are nested under data. Because of the data field there is a need to convert the schema via a proxy server since Sendbird’s bot currently has no way to match the nesting required by Zendesk.

Note: The need for a proxy server may be gone in the future as Sendbird’s bot service is rapidly improving.

Step 2. Create a Sendbird Function Trigger

A Sendbird bot Function call is an AI service that is closely related to a bot. The Functional call has a Trigger Prompt writing in plain language that can listen for a particular scenario to happen within a conversation, between the bot and a user, then take an action based and make an API call out from Sendbird (generate a lead).

In this project the trigger prompt looks like this, and the chatGPT service running in Sendbird is powerful enough to recognize this scenario with zero training.

Listen for when a comprehensive discussion about the user's requirements is complete and you have the user's first name, last name, and email.


Create a Sendbird Function Trigger Video here, and for the proxy server here.

To create the Sendbird bot Function

  1. Sendbird Dashboard → Left menu → AI Chatbot → Function Calls → Click → “Create function +”

  2. Function name = Generate Lead

  3. Function key = generate_lead

  4. Trigger prompt = “Listen for when a comprehensive discussion about the user's requirements is complete and you have the user's first name, last name, and email. “

  5. Header: key = Authorization Value = Bearer YOUR_TOKEN_FROM_ZENDESK_SELL.

  6. Method URL: HTTP method = “POST” URL = “URL_TO_YOUR_PROXY_SERVER”

    1. For testing you can POST to this end point → https://zendesk-sell.glitch.me/lead

  7. Request body:
    1. Parameter 1:

      1. Parameter type = Dynamic

      2. Key = first_name

      3. Prompt describing data… = “User’s first name.”

    2. Parameter 2:

      1. Parameter type = Dynamic

      2. Key = last_name

      3. Prompt describing data… = “User’s last name.”

    3. Parameter 3:

      1. Parameter type = Dynamic

      2. Key = email

      3. Prompt describing data… = “User’s email.”

    4. Parameter 4:

      1. Parameter type = Dynamic

      2. Key = description

    5. Prompt describing data… = “Provide a summary of the conversation and an assessment of why the user may be a good lead for Sendbird’s sales team.”

Step 3: Create a proxy server

As a reminder the proxy server sits between Sendbird’s Function call and Zendesk Sell. Its only purpose is to add the data field to the JSON schema coming from Sendbird before it is passed onto Zendesk Sell.

There is an example of a proxy server here that you can use or Remix if needed. Note that if you remix the server then your end point will change.

server.js code

const express = require("express");
const axios = require("axios");
const app = express();
app.use(express.json());

async function createLead(content) {
const { first_name, last_name, email, description, token } = content;

let data = {
data: {
first_name: first_name || "NOT GIVEN",
last_name: last_name || "NOT GIVEN",
email: email || "a@b.com",
description: description || "SOME TEXT"
}
};

let config = { headers: { "Content-Type": "application/json", Authorization: token } };

try {
const response = await axios.post("https://api.getbase.com/v2/lea...", data, config);
const result = JSON.stringify(response.data);
return result;
} catch (error) {
return JSON.stringify(error);
}
}

// Define POST endpoint for creating a lead
app.post("/lead", async (req, res) => {
const token = req.headers.authorization || null;
const lead = await createLead({ ...req.body, token });
console.log(lead); // Log the result for debugging purposes
res.status(200).send(lead); // Send the result back to the client
});

// Start the server on port 3000
app.listen(3000, () => console.log("Server started on port 3000"));

Step 4: Test the Sendbird function creates a Zendesk lead

Video of testing from Sendbird Dashboard here.

  1. From the Function view, once you have filled in all of the items above then click → “Send Request”

  2. Observe the request body in the Sendbird Dashboard.

  3. Note in the Proxy server that the request succeeded.

  4. Finally visit Zendesk Sell → Leads, to see the created example lead.

Note: This test is only to check the API calls are working. In the next step we will build a bot and check the service works as a whole.

Step 5: Introduction to creating a lead generator bot in Sendbird

The core to the lead generator is to tell it what to do and what information it needs to gather from the user. With Sendbird AI bots it is completely possible to mix FAQ bots about your product together with a service that converses with your users to assess if they are likely to become a lead and gather details needed for the lead.

With this bot we focus on a bot that converses with a user to find out their use case, suitability and then gathers personal details enough to generate a lead.

At the core of bots created using Sendbird are their system prompts. Below is an example system prompt that you can test for generating leads:


Sendbird Advisor's primary role is to engage users in discussions about their communication needs, with a focus on understanding their unique challenges and objectives.

It should ask insightful questions to clarify user requirements and assess if Sendbird chat is a suitable solution. When additional information is needed, Sendbird Advisor will directly ask for clarification, maintaining a friendly and approachable tone.

It will avoid technical jargon and refrain from making commitments about Sendbird's services. The goal is to provide a consultative, informative experience. Sendbird Advisor will personalize interactions by referencing previous parts of the conversation, building a tailored dialogue.

It will also incorporate unique phrases and expressions that align with Sendbird's brand tone, making each interaction distinctive and engaging.

When the time is right it should request from the user their first name and email address.

Strictly do not make up any name or email address.


Note how the prompt is structured.

  1. A paragraph about the bot’s primary role.

  2. A paragraph about how to fulfill the primary role.

  3. Some guidance on what to avoid and also some information about the bot’s persona.

  4. Some guidance on setting the tone of the bot.

  5. The last two paragraphs are guardrails relating to collecting requirements for lead generation.

  6. In addition do not forget our Function prompt seen earlier.

    1. Listen for when a comprehensive discussion about the user's requirements is complete and you have the user's first name, last name, and email.

Step 6: Creating the lead generator bot in Sendbird

Video walkthrough can be found here.

  1. Sendbird Dashboard → Left menu → AI Chatbot → Manage bots → Click → “Create bot + “

  2. Fill in bot details.

    1. Bot name = lead generator

    2. Bot ID = lead_generator

    3. System prompt = See Step 5 above for and example.

    4. Function Calls → Select function → Select Generate Lead (created in Step 2 above) → Click → “Confirm”.

    5. Click “Save”


Step 7: Test the Lead Generator bot

For the testing approach there is also a video here.


  1. In the Sendbird Dashboard open the Lead Generator bot → Left menu → AI Chatbot → Manage Bots → Click → lead generator.

  2. In the testing tool converse with the bot to test until a lead is generated in Zendesk Sell.

  3. The below example should only be used to see if it is possible to trigger the Function Call.

Can you create a lead for me?

Of course! I'd be happy to help you create a lead. To get started, could you please provide me with your first name, last name, and email address?

Jason Smith - jason@smith.com

Thank you for providing your information, Jason Allshorn. Before we proceed, can you please provide me with a brief summary of what led you to consider creating a lead? This will help me better understand your needs and ensure that our solution aligns with your requirements.

“I’m ready to buy Sendbird. It is for 100k MAU, on iOS, Android and Javascript. We need realtime chat in our Fintech app along with transactional messaging via Platform API where each payment sends a message to the end user. We require SOC2 security. Also we would like Reactions and file uploads for our chat. I have no other requirement other than that. That is the only information I’m willing to provide at the moment.”

Thank you for the information, Jason. It's great to hear that you're ready to purchase Sendbird! Based on your requirements, it seems like Sendbird Chat can be a suitable solution for your Fintech app.

To summarize, you need Sendbird Chat for a user base of 100,000 monthly active users (MAU) on iOS, Android, and JavaScript platforms. You require real-time chat functionality, along with transactional messaging via our Platform API, which will enable you to send messages to end users for each payment. It's worth mentioning that Sendbird is SOC2 compliant, ensuring the security of your data. Additionally, you're interested in features like Reactions and file uploads for your chat.

Is there anything specific you would like to know or discuss further about these features or Sendbird's capabilities?

Nope that's it.

Thank you for providing the information, Jason. I have created a lead for you based on the details you provided. Our sales team will review your requirements and reach out to you shortly to discuss the next steps.

If you have any further questions or need assistance in the meantime, please feel free to let me know.


  4. Consider that the above items are technical in nature and in this step we looked at the technical aspects of testing this service. However, consider that for your own bot comprehensive prompt testing is required before going to production (further guidance here).

Conclusion

In conclusion, integrating Zendesk Sell with chatbot API technology offers a powerful solution for streamlining lead qualification processes, optimizing sales workflows, and empowering sales teams to achieve better results. By leveraging the capabilities of chatbot API, businesses can automate lead qualification, gain valuable insights, and drive efficiency in their sales operations.

This module has equipped participants with the knowledge and tools needed to implement this powerful integration effectively. As Sendbird's AI capabilities continue to evolve, the potential for further innovation in customer engagement and CRM integration is vast.

How to build AI chatbot for your business

If you’ve found yourself asking: Can I create my own ChatGPT chatbot on mobile or website? You can, easily, with Sendbird’s ChatGPT capabilities.

With the introduction of ChatGPT-powered chatbots by Sendbird, businesses can now engage state-of-the-art technology to build custom ChatGPT chatbots that revolutionize the customer experience.

GPT AI takes chatbot interactions to a new level with human-like and personalized interactions. The experience improves user engagement and satisfaction, which drive applications' top-line revenue growth. In addition, cloud-based automation boosts operational efficiency with 24/7, scalable, and global availability.

With Sendbird's new ChatGPT integration and chatbot API and chatbot UI, you can now build your own ChatGPT chatbot in minutes.

Anyone can do so with zero coding experience in the dashboard, and developers with just a few lines of code using the Chatbot API of Sendbird's platform. If you need to embed ChatGPT chat in your app, build a quick proof of concept to get used to our simple chat APIs.

Once ready to turn on the ChatGPT chatter in your app, start a 30-day free trial. Now go have fun building a chatbot with ChatGPT! 🤖 💬

Related Tutorials

Tutorial
How to master prompt engineering, function calling, and the use of GPT
Tutorial
What is low latency? Definition, FAQs, and 10 tips to minimize latency
Tutorial
A Guide to Building AI Conversational Forms
Item 1 of 2
01/02
Tutorial
How to master prompt engineering, function calling, and the use of GPT
Item 1 of 5
01/05

Need more resources?