
Have you ever received a promotional text encouraging you to buy more products from a company after having issues with your order? As a customer, the tone mismatch can be off-putting, and as a company, it’s a missed opportunity to get feedback from your customer.
In this post, you will learn how to use IBM’s Sentiment API and Segment to personalize the message sent to a customer. First you will set up an IVR using a Twilio Studio Flow that will capture the user’s sentiment using IBM’s Sentiment API and send that sentiment to Segment as a Segment Event. If the user’s sentiment is negative, they will receive a text asking for feedback on how their experience can be improved. If the user’s sentiment is positive or neutral, they will receive an SMS with a coupon for the next purchase.
Prerequisites
To get started you will need:

In this post, you will learn how to set up a Discord bot connected to Flex so agents can chat directly with customers on that platform, while pulling in sentiment analysis of previous messages. You will learn how to use IBM’s Tone Analyzer API and Segment to calculate a user’s sentiment from their texts in a Discord channel.
Originally this project was created as a part of the 2021 Solutions Engineering Hackathon. We pared our original project down to the following for simplicity’s sake and to distill the project’s essence, which is to help contact center teams interact with customers directly in Discord. To see the original contents of the project, see this Github repo.
To see a demo of the original project and background on why we chose Discord, check out this quick video below.
Prerequisites
For this project, you will need:
- A Twilio account. Sign up for …

Do you want to automatically discover and communicate with your users on their preferred channels? In this post, learn how to measure and personalize your user’s preferred channel using Sendgrid, Programmable SMS, Programmable Voice, Segment Functions, and Segment Personas.
Why would you want to measure and customize your users’ preferred communications channel?
In this blog post you will learn how to send events to Segment with data on whether someone opened a Sendgrid email, answered a call sent from Twilio, or responded to a text message sent from Twilio.
With those events captured in Segment using Segment Functions, a Computed Trait will be calculated to show what channel someone engaged with the most and set that as that user’s preferred channel. When sending out future notifications, the app will check the user’s preferred channel to select how they should receive their notification – text, email, …

Optimizing IVR flows can be difficult, but with A/B testing tools such as Optimizely, you can optimize Twilio IVR flows through experimentation.
In this article we will show you how to test a longer, more descriptive voice message versus a shorter, more direct one for customers picking up curbside at a store. To measure the effectiveness of the long versus short message, we will also discuss how to capture survey results and send them to Optimizely.
Follow along to learn how to configure a Twilio Studio flow that splits users based on how Optimizely’s SDK buckets them for an experiment. You will also learn how to send Optimizely tracking metrics such as ‘Completed IVR’ to see what score a user would give your service.
Tutorial Requirements
- A Twilio account. If you don’t yet have a free account, you can sign up here.
- An Optimizely Full Stack project -- …