Connect with us

MARKETING

Writing a Quality Chatbot Script: Detailed Guide

Published

on

Writing a Quality Chatbot Script: Detailed Guide

To automate communication with website visitors, you need to create a script for the chatbot that accepts appeals. The quality of the dialogs affects the success of the business – positive impressions increase conversion, while negative ones can discourage potential customers. This ultimate guide will tell you how to write a perfect chatbot script.

How to begin work on a script for a chatbot

The first step is to set a goal. It depends on the characteristics of your company and its product. For an online store, the target action will be a completed purchase, for services – an appointment, for a news website – a subscription to a newsletter.

However, not all chatbots are for commercial purposes. Technologies changed commerce and dictated its rules. Today, chatbots can provide reference information on request, assist in navigating the website, tell you about the terms of service, help new employees get accustomed to their jobs, and perform other tasks.

It is crucial to choose a platform for creating the bot at this stage – the chatbot’s capabilities will depend on it. Or you can hire a front-end development team, and they will help you with creating more detailed chatbot software if you’re not interested in platforms. Some platforms have ready-made templates for dialogs that can be assembled according to the constructor principle and adjusted to the needs of your business.

Choosing a tone of voice for a chatbot

1667789106 168 Writing a Quality Chatbot Script Detailed Guide

A chatbot needs a personality corresponding to the company’s field of activity and target audience. In a cosmetics store, the tone of voice should be friendly and recommendatory. In a video game catalog – lively and direct. If you are responding to personal trainers, be energetic and enthusiastic. And in a car dealership – emphatically businesslike and neutral. If the chatbot’s personality is rather friendly, nonverbal means of communication (emojis, stickers, pictures, and even memes) may appear in the responses.

Understanding whether a chatbot can be integrated with your CRM or Zapier is crucial. If this is feasible, the dialogs should be personalized by adding a personal appeal to the user and recommendations based on browsing history.

Careful handling of erroneous messages should be provided. In many ways, this is where the chatbot’s personality comes into play. Not recognizing the other person’s message, may apologize, make a joke, or suggest that the request be phrased more accurately. Consider which response would be more appropriate. And also, localize your chatbot.

5 steps to write a script for chatbots

1667789106 369 Writing a Quality Chatbot Script Detailed Guide

A chatbot responds to a client according to the script. It doesn’t know how to improvise and rearrange communication if something doesn’t go according to plan. That’s why it’s essential to think out a clear, consistent, and logical communication script for the chatbot:

  • Define your tasks and goals. What do you need the chatbot for? For example, this escape room in SF uses a chatbot to help their visitors make a choice, consult on questions, place an order, or handle customer service requests. Write a greeting. Offer help and ask specific questions. For example: “Hello! What kind of coffee do you like?” And add the answer options: “Grain” or “Ground”. This way, the customer will understand that the chatbot understands the parameters of the product and will reduce the search time.
  • Make a structure for the chatbot. To make a structure, detail the user’s journey from the first visit to your website and analyze what information they will need. For example, they can need an assortment of products with prices and descriptions, help and advice on choosing products, or information on payment and delivery. Be sure to include the ability to quickly contact the manager in case the chatbot can not help.
  • Create the tone of voice of the chatbot—for example, friendly format, humor, compliments, and mood emoji. Make communication easy and natural based on the characteristics of the target audience. This builds trust and sympathy and draws people in.
  • Write parting phrases. End any conversation in such a way that the user is left with a pleasant experience with the chatbot. For example, “Congratulations on your purchase,” “Thank you for your choice,” “I was happy to chat,” “Thank you for your time,” and “Have a great day”.

Following these 5 steps, you will quickly write a job aid for a chatbot.

Tips on how to write scripts for a chatbot

1667789107 588 Writing a Quality Chatbot Script Detailed Guide

First, make a list of frequently asked questions. If you have already worked with a call center, you can use its reports as a basis. If not, search for the FAQs of businesses that work in the same field. Run a series of website tests – you can even ask a few people you know to place a test order.

The dialogs for the chatbot should be structured. Combine them by topic. Then enlarge the list again, forming 2 to 5 sections for the main menu. Now you have everything you need to write a script. It should be written as a flowchart, which can be made in your chosen service or even in a text editor.

1667789107 567 Writing a Quality Chatbot Script Detailed Guide

Creating a structure for chatbots is a complicated and responsible job that requires knowledge of psychology, basic programming principles, and sales techniques. It is desirable to involve a professional who knows how to build the right algorithms. But if your business is gaining momentum, you can start independently. The following tips will help you:

  • Choose a discreet and friendly way to start a dialogue. You usually see a help button when you open the website. A separate chat window opens if the user browses many web pages or takes a long time to take targeted action.
  • Use quick action buttons where possible. Make it easier for the user to type responses. But don’t forbid typing the request in the text – some people find it easier to communicate this way.
  • Put closed questions, which imply a limited number of answers. For example, in the store – “What kind of case do you want: black, white, gray, or a bright shade?” In a beauty salon – “What service are you interested in: a haircut, manicure, or depilation?”
  • Try not to build flowcharts deeper than five levels. If a person has to perform more actions, he or she begins to get tired of the endless clicks and distracted from the dialogue.
  • Be sure to think about the possibility of returning to one level and instantly returning to the main menu. Make sure that any parts of the flowchart coordinate with each other in both directions.
  • Make an algorithm for closing the session. In addition to performing the targeted action, the client can close the window, leave the message unattended, or confirm that the chatbot has answered all his questions.

As for the text content of the dialog, it should be composed using simple words. Do not try to sugarcoat the terms, trying to emphasize your professionalism – such a tone of communication may seem contrived and arrogant. After writing the script, you should reread it several times. Consider whether you can simplify things for the client. Check the length of each message. Ideally, it ranges from 50 to 150 characters without spaces.

How to debug a chatbot on your website

1667789107 708 Writing a Quality Chatbot Script Detailed Guide

Even a perfectly scripted dialog can leave a negative impression because of annoying mistakes. Therefore, it is essential to think through “escape routes” for the chatbot. Alternative scripts are needed in the following cases:

  • Suppose the user’s requests go beyond the authority of the chatbot. You can offer him or her to contact an operator or leave a phone number for customer feedback.
  • Suppose the selected action does not work. For example, the data from the CRM won’t load. It is better to see a neutral reference than %USERNAME%.
  • Suppose the operator is unavailable. Instead of keeping the customer in suspense, offer him or her to leave contacts. He or she will be contacted as soon as the service starts working.
  • Suppose the user can’t decide which option is right for him for a long time. After a certain amount of time, the chatbot may provide help or recommendations.
  • Suppose the customer does not respond in a structured manner, e.g., writing every word in a separate message. You can automatically return it to the previous level of dialogue or ask it to clarify the request.

To improve the chatbot, look for successful examples of chatbot dialogs, set up analytics on your website, and test regularly. Once you discover typical errors, don’t leave them in your reports, but adjust the script, keeping the visitor’s attention and improving conversion rates. But if you need a full-scale chatbot, it is better to use an AI chatbot.

Takeaways

Writing scripts for chatbots is complicated and responsible work at the intersection of several professions. If you are just starting in this industry, you should

  • Define your tasks and goals
  • Write a greeting
  • Make a structure for the chatbot
  • Create the tone of voice of the chatbot
  • Write parting phrases

Adhering to our tips, you will write a powerful chatbot script.

Source link

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address

MARKETING

YouTube Ad Specs, Sizes, and Examples [2024 Update]

Published

on

YouTube Ad Specs, Sizes, and Examples

Introduction

With billions of users each month, YouTube is the world’s second largest search engine and top website for video content. This makes it a great place for advertising. To succeed, advertisers need to follow the correct YouTube ad specifications. These rules help your ad reach more viewers, increasing the chance of gaining new customers and boosting brand awareness.

Types of YouTube Ads

Video Ads

  • Description: These play before, during, or after a YouTube video on computers or mobile devices.
  • Types:
    • In-stream ads: Can be skippable or non-skippable.
    • Bumper ads: Non-skippable, short ads that play before, during, or after a video.

Display Ads

  • Description: These appear in different spots on YouTube and usually use text or static images.
  • Note: YouTube does not support display image ads directly on its app, but these can be targeted to YouTube.com through Google Display Network (GDN).

Companion Banners

  • Description: Appears to the right of the YouTube player on desktop.
  • Requirement: Must be purchased alongside In-stream ads, Bumper ads, or In-feed ads.

In-feed Ads

  • Description: Resemble videos with images, headlines, and text. They link to a public or unlisted YouTube video.

Outstream Ads

  • Description: Mobile-only video ads that play outside of YouTube, on websites and apps within the Google video partner network.

Masthead Ads

  • Description: Premium, high-visibility banner ads displayed at the top of the YouTube homepage for both desktop and mobile users.

YouTube Ad Specs by Type

Skippable In-stream Video Ads

  • Placement: Before, during, or after a YouTube video.
  • Resolution:
    • Horizontal: 1920 x 1080px
    • Vertical: 1080 x 1920px
    • Square: 1080 x 1080px
  • Aspect Ratio:
    • Horizontal: 16:9
    • Vertical: 9:16
    • Square: 1:1
  • Length:
    • Awareness: 15-20 seconds
    • Consideration: 2-3 minutes
    • Action: 15-20 seconds

Non-skippable In-stream Video Ads

  • Description: Must be watched completely before the main video.
  • Length: 15 seconds (or 20 seconds in certain markets).
  • Resolution:
    • Horizontal: 1920 x 1080px
    • Vertical: 1080 x 1920px
    • Square: 1080 x 1080px
  • Aspect Ratio:
    • Horizontal: 16:9
    • Vertical: 9:16
    • Square: 1:1

Bumper Ads

  • Length: Maximum 6 seconds.
  • File Format: MP4, Quicktime, AVI, ASF, Windows Media, or MPEG.
  • Resolution:
    • Horizontal: 640 x 360px
    • Vertical: 480 x 360px

In-feed Ads

  • Description: Show alongside YouTube content, like search results or the Home feed.
  • Resolution:
    • Horizontal: 1920 x 1080px
    • Vertical: 1080 x 1920px
    • Square: 1080 x 1080px
  • Aspect Ratio:
    • Horizontal: 16:9
    • Square: 1:1
  • Length:
    • Awareness: 15-20 seconds
    • Consideration: 2-3 minutes
  • Headline/Description:
    • Headline: Up to 2 lines, 40 characters per line
    • Description: Up to 2 lines, 35 characters per line

Display Ads

  • Description: Static images or animated media that appear on YouTube next to video suggestions, in search results, or on the homepage.
  • Image Size: 300×60 pixels.
  • File Type: GIF, JPG, PNG.
  • File Size: Max 150KB.
  • Max Animation Length: 30 seconds.

Outstream Ads

  • Description: Mobile-only video ads that appear on websites and apps within the Google video partner network, not on YouTube itself.
  • Logo Specs:
    • Square: 1:1 (200 x 200px).
    • File Type: JPG, GIF, PNG.
    • Max Size: 200KB.

Masthead Ads

  • Description: High-visibility ads at the top of the YouTube homepage.
  • Resolution: 1920 x 1080 or higher.
  • File Type: JPG or PNG (without transparency).

Conclusion

YouTube offers a variety of ad formats to reach audiences effectively in 2024. Whether you want to build brand awareness, drive conversions, or target specific demographics, YouTube provides a dynamic platform for your advertising needs. Always follow Google’s advertising policies and the technical ad specs to ensure your ads perform their best. Ready to start using YouTube ads? Contact us today to get started!

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Continue Reading

MARKETING

Why We Are Always ‘Clicking to Buy’, According to Psychologists

Published

on

Why We Are Always 'Clicking to Buy', According to Psychologists

Amazon pillows.

(more…)

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Continue Reading

MARKETING

A deeper dive into data, personalization and Copilots

Published

on

A deeper dive into data, personalization and Copilots

Salesforce launched a collection of new, generative AI-related products at Connections in Chicago this week. They included new Einstein Copilots for marketers and merchants and Einstein Personalization.

To better understand, not only the potential impact of the new products, but the evolving Salesforce architecture, we sat down with Bobby Jania, CMO, Marketing Cloud.

Dig deeper: Salesforce piles on the Einstein Copilots

Salesforce’s evolving architecture

It’s hard to deny that Salesforce likes coming up with new names for platforms and products (what happened to Customer 360?) and this can sometimes make the observer wonder if something is brand new, or old but with a brand new name. In particular, what exactly is Einstein 1 and how is it related to Salesforce Data Cloud?

“Data Cloud is built on the Einstein 1 platform,” Jania explained. “The Einstein 1 platform is our entire Salesforce platform and that includes products like Sales Cloud, Service Cloud — that it includes the original idea of Salesforce not just being in the cloud, but being multi-tenancy.”

Data Cloud — not an acquisition, of course — was built natively on that platform. It was the first product built on Hyperforce, Salesforce’s new cloud infrastructure architecture. “Since Data Cloud was on what we now call the Einstein 1 platform from Day One, it has always natively connected to, and been able to read anything in Sales Cloud, Service Cloud [and so on]. On top of that, we can now bring in, not only structured but unstructured data.”

That’s a significant progression from the position, several years ago, when Salesforce had stitched together a platform around various acquisitions (ExactTarget, for example) that didn’t necessarily talk to each other.

“At times, what we would do is have a kind of behind-the-scenes flow where data from one product could be moved into another product,” said Jania, “but in many of those cases the data would then be in both, whereas now the data is in Data Cloud. Tableau will run natively off Data Cloud; Commerce Cloud, Service Cloud, Marketing Cloud — they’re all going to the same operational customer profile.” They’re not copying the data from Data Cloud, Jania confirmed.

Another thing to know is tit’s possible for Salesforce customers to import their own datasets into Data Cloud. “We wanted to create a federated data model,” said Jania. “If you’re using Snowflake, for example, we more or less virtually sit on your data lake. The value we add is that we will look at all your data and help you form these operational customer profiles.”

Let’s learn more about Einstein Copilot

“Copilot means that I have an assistant with me in the tool where I need to be working that contextually knows what I am trying to do and helps me at every step of the process,” Jania said.

For marketers, this might begin with a campaign brief developed with Copilot’s assistance, the identification of an audience based on the brief, and then the development of email or other content. “What’s really cool is the idea of Einstein Studio where our customers will create actions [for Copilot] that we hadn’t even thought about.”

Here’s a key insight (back to nomenclature). We reported on Copilot for markets, Copilot for merchants, Copilot for shoppers. It turns out, however, that there is just one Copilot, Einstein Copilot, and these are use cases. “There’s just one Copilot, we just add these for a little clarity; we’re going to talk about marketing use cases, about shoppers’ use cases. These are actions for the marketing use cases we built out of the box; you can build your own.”

It’s surely going to take a little time for marketers to learn to work easily with Copilot. “There’s always time for adoption,” Jania agreed. “What is directly connected with this is, this is my ninth Connections and this one has the most hands-on training that I’ve seen since 2014 — and a lot of that is getting people using Data Cloud, using these tools rather than just being given a demo.”

What’s new about Einstein Personalization

Salesforce Einstein has been around since 2016 and many of the use cases seem to have involved personalization in various forms. What’s new?

“Einstein Personalization is a real-time decision engine and it’s going to choose next-best-action, next-best-offer. What is new is that it’s a service now that runs natively on top of Data Cloud.” A lot of real-time decision engines need their own set of data that might actually be a subset of data. “Einstein Personalization is going to look holistically at a customer and recommend a next-best-action that could be natively surfaced in Service Cloud, Sales Cloud or Marketing Cloud.”

Finally, trust

One feature of the presentations at Connections was the reassurance that, although public LLMs like ChatGPT could be selected for application to customer data, none of that data would be retained by the LLMs. Is this just a matter of written agreements? No, not just that, said Jania.

“In the Einstein Trust Layer, all of the data, when it connects to an LLM, runs through our gateway. If there was a prompt that had personally identifiable information — a credit card number, an email address — at a mimum, all that is stripped out. The LLMs do not store the output; we store the output for auditing back in Salesforce. Any output that comes back through our gateway is logged in our system; it runs through a toxicity model; and only at the end do we put PII data back into the answer. There are real pieces beyond a handshake that this data is safe.”

Source link

Keep an eye on what we are doing
Be the first to get latest updates and exclusive content straight to your email inbox.
We promise not to spam you. You can unsubscribe at any time.
Invalid email address
Continue Reading

Trending