Using ChatGPT to Automate Cold Calling for Sales Leads [with Bland AI]

Tech-At-Work
17 Mar 202416:24

Summary

TLDRThis video script outlines a Python script designed to automate cold calling using an Excel sheet of contacts and Bland AI's services. The script calls potential leads, engages them with an AI agent about a specific product or service, and forwards interested parties to a sales representative. The tutorial includes setting up Bland AI, formatting data, and customizing call parameters. Viewers are guided through the process, from API key retrieval to generating reports on call outcomes, offering a hands-on approach to mastering cold calling with AI assistance.

Takeaways

  • 📝 The video discusses the common challenge of cold calling in sales, real estate, fundraising, and recruiting, highlighting its importance in lead generation.
  • 🎬 Hollywood movies like 'The Pursuit of Happiness' and 'The Wolf of Wall Street' emphasize the significance of exceptional cold calling skills for success in sales.
  • 🤖 The video introduces a Python script designed to automate the cold calling process using an AI from Bland AI, which can interact with potential leads and forward interested ones to the salesperson.
  • 📋 The script requires an Excel sheet with names and phone numbers formatted with 'Name' in column A and 'Phone Number' in column B, including the country code and 10-digit number.
  • 🔗 The Bland AI account setup involves obtaining an API key for the Python program to communicate with the Bland AI service.
  • 📁 The video instructs how to save the Excel data as a CSV file, which is essential for the Python script to access the data.
  • 🔗 The video provides a link for a discount on Bland AI services and encourages viewers to use it when signing up.
  • 🛠 The script includes customizable parameters such as the AI model, voice ID, and latency settings to tailor the AI's behavior during calls.
  • 📝 The video explains how to define the call's goal, transfer list, and tough-to-pronounce words to ensure clear communication during the AI's calls.
  • 📊 The script can generate a report analyzing the outcomes of the calls, including customer interest and reasons for disinterest, which can be saved as a CSV file for further analysis.
  • 🚫 The video mentions a 'test mode' feature in the script to prevent calling the entire list during initial testing, ensuring the AI's functionality before full deployment.

Q & A

  • What do jobs in sales, real estate fundraising, and recruiting have in common?

    -They all rely on the task of cold calling people to get leads, which is a critical skill portrayed in movies like 'The Pursuit of Happiness' and 'The Wolf of Wall Street'.

  • How does the main character in 'The Pursuit of Happiness' optimize his cold calling?

    -The main character realizes that by not hanging up the phone between calls, he can get through more calls per day, thus saving time and potentially increasing sales.

  • What is the purpose of the AI program described in the script?

    -The AI program is designed to automatically call contacts from an Excel sheet, engage with them about a product or service, and forward interested leads to the salesperson for further action.

  • What is Bland AI, and how is it used in the script?

    -Bland AI is a program that enables the use of AI agents for various tasks, including making calls. In the script, it's used to automate the cold calling process with an AI agent that can interact with potential customers.

  • Why is it important to format the Excel sheet data correctly for the Bland AI program?

    -Proper formatting is crucial because the Python script relies on specific column labels ('name' and 'phone number') to extract data and perform calls. Incorrect formatting would prevent the script from functioning as intended.

  • What is the significance of saving the Excel sheet as a CSV file?

    -Saving the file as a CSV allows the Python script to read and interact with the data from the Excel sheet, which is necessary for the automated calling process.

  • How does one obtain an API key from Bland AI for the script?

    -An API key is obtained by signing up for Bland AI, navigating to the account settings, selecting the API option, and then generating an API key which can be copied and used in the Python script.

  • What is the role of the 'payload' in the Bland AI calling process?

    -The payload defines the parameters for each call, including the purpose of the call, the script that the AI agent will follow, and the actions to take if the person is interested, such as transferring the call.

  • Why might someone choose to spell out numbers in the Bland AI script?

    -Spelling out numbers can help the AI agent to pronounce them more accurately, as it tends to handle spelled-out numbers better than numerical digits.

  • How can one customize the AI agent's voice and behavior in the Bland AI program?

    -Customization can be done by selecting different voices from Bland AI's voice presets or by defining variables such as 'wait for greeting', 'reduced latency', and 'temperature' in the script to modify the agent's responsiveness and creativity.

  • What does the script offer in terms of monitoring and reporting on the calls made by the AI?

    -The script includes a section that generates a report of the batch of calls, providing insights into customer interest, call outcomes, and reasons for not being interested, which can be reviewed or saved as a CSV file for further analysis.

Outlines

00:00

📞 Automating Cold Calls with AI

The video script discusses the commonality among sales, real estate, fundraising, and recruiting jobs, which is the reliance on cold calling to generate leads. It draws a parallel with Hollywood movies like 'The Pursuit of Happyness' and 'The Wolf of Wall Street,' where exceptional cold calling skills are portrayed. The script then transitions into a tutorial on creating an AI program to automate the cold calling process using a Python script. The program is designed to call contacts from an Excel sheet, engage with them using an AI agent, and forward interested leads to the user for potential sales. The tutorial utilizes Bland AI, a service for creating AI agents, and provides a step-by-step guide on setting up the program, including obtaining an API key, formatting the Excel sheet, and saving it as a CSV file for the script to access.

05:02

🔗 Setting Up the AI Cold Calling Script

This section of the script provides a detailed walkthrough of setting up the AI cold calling script using Google Colab. It explains how to install necessary Python libraries, import them, and define the Bland AI API key. The script is designed to load a CSV file containing names and phone numbers, define a 'payload' for the calls with specific parameters such as the call's purpose, and handle the transfer of interested leads to a predefined number. The tutorial also covers how to format the CSV file correctly, use the Bland AI developer portal to understand and modify call parameters, and set up the AI agent's voice and pronunciation settings. Additionally, it advises on spelling out numbers for clarity and using the test mode to ensure the script works as intended before running it on the entire call list.

10:03

🎚 Customizing AI Agent Settings

The third paragraph delves into the customization of AI agent settings within the Bland AI platform. It covers various parameters that can be adjusted to control the AI agent's behavior during calls, such as the model used for communication, waiting for a greeting, the first sentence spoken, and voice ID for the AI's voice. The script also touches on the reduced latency feature for more natural conversations and the temperature setting to control the AI's creativity. The tutorial explains how to use test mode for initial testing and how to generate reports on the calls made, including the ability to stop the batch of calls if necessary. It also provides instructions on accessing Bland AI's documentation for further customization options and understanding the parameters available for the AI agent's calls.

15:03

📊 Analyzing Call Results and Conclusion

The final paragraph of the script outlines the process of analyzing the results of the AI cold calls. It describes how to run the script to send calls, monitor the progress, and generate a report that includes details like call ID, whether the call was answered, customer interest, and reasons for disinterest. The report is presented in a readable format within the Google Colab environment, and there's an option to save the report as a CSV file for further analysis. The tutorial concludes with a reminder to use the provided link for a discount on Bland AI services and an encouragement to subscribe to the channel for more content like this.

Mindmap

Keywords

💡Cold Calling

Cold calling is the act of making unsolicited phone calls to prospective customers to generate interest in a product or service. In the video's context, it is a critical skill portrayed in movies like 'The Pursuit of Happyness' and is essential for jobs in sales, real estate fundraising, or recruiting. The script discusses mastering cold calling as a key to success, with the main character in the video leveraging it to increase sales efficiency.

💡Leads

Leads refer to potential customers or clients who have shown interest in a product or service and could potentially be converted into sales. The video emphasizes the importance of generating leads through cold calling, as the AI program is designed to identify interested parties from a call sheet and forward them to the salesperson for potential conversion.

💡AI Program

An AI program mentioned in the script is a software application that uses artificial intelligence to perform tasks. In this case, the AI program is designed to automate the cold calling process, interact with potential customers, and filter leads based on their interest in the offered product or service.

💡Excel Sheet

An Excel sheet is a grid of data cells organized into rows and columns within a Microsoft Excel workbook. The script describes using an Excel sheet to list names and phone numbers for the AI to call. It is a tool for organizing and managing data, which is essential for the AI to access and use contact information.

💡CSV File

A CSV file, short for Comma-Separated Values, is a type of file used to store tabular data, such as that in an Excel sheet, in plain text. The video script instructs how to save the Excel data as a CSV file, which is necessary for the Python script to access and process the contact information for the AI to make calls.

💡API Key

An API key is a unique code used to authenticate requests to an API (Application Programming Interface). In the context of the video, the API key is used to connect the Python program with the Bland AI service, allowing the program to make calls and interact with the AI service securely.

💡Bland AI

Bland AI is the service mentioned in the script that provides AI agents capable of making phone calls and interacting with humans. The video demonstrates how to use Bland AI for automating the cold calling process, showcasing its features and how it can be integrated with a Python script.

💡Python Script

A Python script refers to a sequence of programming instructions written in the Python language. In the video, the script is used to automate the process of making calls using Bland AI. It handles tasks such as reading the CSV file, defining call parameters, and sending calls based on the provided data.

💡Payload

In the context of the video, payload refers to the set of parameters and data sent with an API request. The script explains defining a payload for each call, which includes the purpose of the call, the message to be conveyed, and the conditions for transferring the call to a human representative.

💡Voice ID

Voice ID in the Bland AI service refers to the unique identifier for a specific voice that the AI agent will use when making calls. The video script describes how to select and set a voice ID for the AI agent to ensure that the calls have a natural and personalized tone.

💡Reduced Latency

Reduced latency is a setting that determines the responsiveness of the AI agent in a conversation. In the script, setting reduced latency to true makes the AI respond more quickly, simulating a more natural conversation flow during the calls.

💡Test Mode

Test mode is a setting in the AI program that allows for a controlled testing of the calling process. The script mentions setting the test mode to true to ensure that the AI only calls the first number in the list, providing an opportunity to verify the functionality before scaling up to the entire call sheet.

💡Analysis Report

An analysis report in the context of the video is a summary of the outcomes from the batch of calls made by the AI program. It includes details such as customer interest, reasons for disinterest, and whether they requested to be transferred. The script describes generating this report to evaluate the effectiveness of the calls and the engagement of the AI with potential leads.

Highlights

The video discusses the commonality of cold calling in sales, real estate, fundraising, and recruiting.

Hollywood movies like 'The Pursuit of Happiness' and 'The Wolf of Wall Street' showcase exceptional cold calling skills leading to more sales.

A Python script is introduced to automate cold calls using an Excel sheet of contacts for sales leads.

The Bland AI program is used to interact with contacts, answer questions, and forward interested leads to the salesperson.

Instructions on setting up a Bland AI account and obtaining an API key for script integration are provided.

The importance of correctly formatting the Excel sheet with names and phone numbers is emphasized.

A detailed guide on saving the Excel data as a CSV file for script compatibility is given.

The process of mounting Google Drive to Google Collab for file access is explained.

Customizing the Python script with the Bland AI API key and CSV file path is demonstrated.

The script's functionality to define call parameters such as the call goal and transfer list is covered.

Pronunciation guides for the AI agent to correctly pronounce difficult words are discussed.

Bland AI's documentation is referenced for further customization options of the AI agent's behavior.

The script includes variables for model selection, voice ID, and latency settings for a natural conversation flow.

The video explains how to generate a report of the batch calls for analysis and feedback.

Emergency stop functionality is included to halt the call batch if necessary.

A step-by-step guide on running the Python script in Google Collab is provided.

The video concludes with a summary of the script's capabilities and a reminder of the resources available in the description.

Transcripts

play00:00

all right so what do jobs in sales real

play00:02

estate fundraising or recruiting all

play00:05

have in common well they all rely on the

play00:08

sobering task of cold calling people in

play00:10

order to get leads mastering this

play00:12

daunting challenge is a Hallmark of many

play00:14

Hollywood movies including the pursuit

play00:16

of happiness and the Wolf of Wall Street

play00:18

the main characters exceptional cold

play00:19

calling abilities is what sets them

play00:21

apart from many of their peers

play00:23

presumably leading to more sales I

play00:25

recently watched the pursuit to

play00:26

happiness and there's a scene where the

play00:28

main character talks about having to go

play00:30

through a call sheet and he realizes

play00:32

that if he doesn't hang up the phone he

play00:33

can get through more calls per day than

play00:36

his co-workers in order not to waste any

play00:38

time I wasn't hanging up the phone in

play00:40

between calls okay thanks very

play00:43

much I realized that by not hanging up

play00:46

the phone I gained another 8 minutes a

play00:48

day and this got me thinking could we

play00:51

write an AI program that would

play00:53

automatically call contacts in a call

play00:55

sheet and then only forward the leads

play00:57

that were interested in the product or

play00:59

service that you're selling well that's

play01:00

exactly what I'm going to show you how

play01:01

to do in today's video I wrote a python

play01:03

script that will take an Excel sheet of

play01:05

names and phone numbers and go through

play01:07

each one calling them individually and

play01:09

then an AI agent will speak with the

play01:11

person on the other line about whatever

play01:13

product or service you're offering the

play01:14

AI agent can answer questions give the

play01:16

person on the other line more

play01:17

information and then if the person's

play01:19

interested forward the call to you so

play01:21

that you can close the sale or give the

play01:23

person more information about the

play01:24

product or service now to do this I'm

play01:26

going to use a program called Bland AI

play01:28

now if you're not familiar with Bland BL

play01:30

AI I've done a couple videos that I'll

play01:31

link here on using Bland AI with a

play01:34

custom GPT for example or using their AI

play01:37

agents to lower your internet bill now

play01:39

for this video I've got all the code and

play01:41

everything you're going to need in the

play01:42

video description so go down there and

play01:44

check that out it also has a sign up

play01:46

link for Bland Ai and they'll give you

play01:48

25% off your first order when you use

play01:50

that link now if you enjoy this type of

play01:52

content or you enjoyed this video please

play01:55

consider subscribing to the channel and

play01:56

like the video it lets me know what type

play01:58

of content people enjoy and it really

play01:59

helps me out a lot okay so to begin I've

play02:02

got an Excel sheet here that has a

play02:04

column of names and then the associated

play02:07

phone numbers it's important that you

play02:08

have your data formatted exactly how I

play02:10

have here with the column a labeled as

play02:13

name and column b as phone number you

play02:16

also need to make sure that you have the

play02:17

country code and then the 10 digits of

play02:19

the phone number after that bland AI

play02:22

doesn't specify how many numbers you can

play02:23

have to use their service um hundreds I

play02:26

would assume you may want to try this

play02:28

out with a smaller data set first just

play02:29

to to kind of make sure that it's

play02:30

working right once you have your data

play02:32

formatted correctly then go to file save

play02:34

as and give your file a name I'm going

play02:36

to call mine call sheet example just

play02:38

like I have here and you'll see that it

play02:40

shows file format here and right now

play02:42

it's set to excel workbook if you click

play02:45

that you can go to CSV utf-8 comma Del

play02:49

limited. CSV we're going to save this as

play02:51

a CSV file and that's really important

play02:53

because that's what allows our python

play02:55

script to talk to our data in the Excel

play02:57

sheet so go ahead and save that

play02:58

someplace

play03:00

and we'll come back to that file later

play03:02

now we're going to actually set up our

play03:03

Bland AI account use the link in the

play03:05

video description to sign up for Bland

play03:07

Ai and once you're signed up you should

play03:09

see a page that looks something like

play03:10

this the first thing we're going to do

play03:12

is get what's called an API key and

play03:13

that's basically a way for Bland AI to

play03:16

talk to your specific Bland AI account

play03:18

through the Python program that we're

play03:20

using today so go to your account here

play03:22

and then you'll see API in the top right

play03:24

corner click that and then you'll see

play03:26

this start out API key Now API keys are

play03:29

kind of like password so if anybody has

play03:31

this they can use it to access your

play03:33

account and your credits then so you

play03:36

want to keep this secret I'm going to

play03:38

deactivate mine after I publish this

play03:40

video so don't bother trying to steal

play03:42

mine once you've got that just click

play03:43

this copy button here on the right side

play03:45

and if you hit this little eyeball you

play03:47

can actually see the API key so you see

play03:49

it's just long string of characters so

play03:51

once you have that copied now go back to

play03:53

the video description and open the

play03:54

Google collab that has the python code

play03:56

that we're going to run today now when

play03:58

you open that it should look something

play03:59

like like this now if you look on the

play04:01

row down here it says your Bland AI API

play04:04

key go ahead and highlight that and

play04:05

delete it and then paste the API key

play04:08

that you just copied from Bland AI now

play04:10

the program is going to use your API key

play04:11

to talk to your Bland AI account next

play04:13

what we need to do is get the CSV file

play04:15

that we just saved into our Google

play04:17

collab window so to do that we're going

play04:18

to click the file icon here and you'll

play04:21

see a window that looks like this next

play04:23

click on this Mount Drive button and

play04:25

that's going to link your Google drive

play04:27

to your Google collab session window

play04:29

it's it's going to pop up and say do you

play04:31

want to permit this notebook to ask

play04:32

access Google Drive click connect to

play04:34

Google Drive and then that'll take a

play04:35

second to mount once that finishes

play04:37

you'll see this little drive folder pop

play04:39

up you can drop that down and navigate

play04:41

to where you want to save your file for

play04:44

your program here so you can see I've

play04:45

got a couple folders from past videos

play04:47

I've done and I've got this folder here

play04:49

called cold call assistant uh you can

play04:51

click the three dots and that's how you

play04:52

create new folder so that's how I

play04:54

created this folder specific to this

play04:56

project so now what I'm going to do is

play04:57

go back to my folder where I saved my C

play04:59

SV file with my Excel data and then I'm

play05:01

going to drag it in to my Google collab

play05:04

just like this into that cold call

play05:06

folder and then you'll see it actually

play05:07

adds it now into my program now what you

play05:10

need to do is click the three dots and

play05:12

hit copy path and now if you go into

play05:15

your program again you'll see your file

play05:17

path right here in large letters

play05:18

highlight and delete that and then paste

play05:20

the file path that you just copied now

play05:22

I'm going to close the folder view so we

play05:23

can see our code better now I'm going to

play05:25

walk you through exactly what this

play05:26

program is doing so you understand what

play05:29

you can modif ify and customize to make

play05:31

it work for your application the first

play05:33

thing is this installs the programs that

play05:35

we're going to need to use in our python

play05:37

Library so you load this each time next

play05:39

you're going to import the programs that

play05:41

you just installed so that's what this

play05:42

line does uh we already talked about

play05:44

this this is where you're defining the

play05:45

API key for Bland AI this just sets it

play05:48

up and formats it uh how bland AI needs

play05:50

so that it understands how to read your

play05:52

API key next here is load the call list

play05:54

from the CSV this is actually going to

play05:57

pull in the CSV file from the file path

play05:59

that you pasted here next we're going to

play06:01

actually Define what we call the payload

play06:03

for the batch of calls that we're making

play06:05

now the payload is basically defining

play06:07

the parameters for each call that you're

play06:09

going to make so Bas prompt is basically

play06:11

the goal of the call that you're going

play06:13

to have for each person that you're

play06:14

calling so you can see in this example

play06:16

here I said you're calling to speak with

play06:17

name about refinancing their mortgage

play06:19

down to 6% please tell them it's never

play06:21

been a better time to refinance and

play06:23

you're calling from a state of bliss

play06:25

realy if the person is interested

play06:27

transfer the call to default now I'll

play06:29

explain what the curly brackets and

play06:30

default and name are so we actually

play06:32

Define name just below here so you can

play06:34

see where it says Name colon row and

play06:37

then this is the column A from the Excel

play06:39

sheet so that's where it's pulling the

play06:41

name from and then phone number is

play06:43

actually defined as the phone number

play06:45

column that we labeled so that's why

play06:46

it's important that you have it

play06:47

formatted exactly the same and then this

play06:49

line here it basically just says this

play06:50

program is going to go uh one by one

play06:53

through each row and perform the call

play06:55

now transfer list this is the phone

play06:57

number if the person on the phone wants

play06:59

to be transferred to a sales

play07:01

representative or you know a different

play07:03

department that's going to have more

play07:04

information this is where you're going

play07:05

to Define this so in this example I've

play07:07

got default which is if the person's

play07:09

interested you can transfer the call to

play07:11

default that's where I'm defining that

play07:13

phone number that the AI agent will then

play07:15

forward the call to so this would be my

play07:16

phone number for example you can also

play07:18

have multiple phone numbers that the AI

play07:20

agent could forward to uh for this one

play07:22

I've just got default and sales so you

play07:24

could have like billing or something

play07:25

depending on how complex your uh the

play07:28

call that you're trying to perform is

play07:29

this next section is kind of cool so

play07:30

this is where you can Define tough to

play07:32

pronounce words that the AI agent is

play07:34

going to pronounce when I was playing

play07:35

with this it would say real T kind of

play07:38

interesting and so I wanted it to

play07:40

pronounce it real T pretty

play07:41

self-explanatory you put the word that

play07:43

you wanted to pronounce correctly and

play07:44

then you annotate the pronunciation

play07:46

below that the other way you can use

play07:48

this is for like three-letter acronyms

play07:50

like API so when it comes across API you

play07:53

put a space p space I it'll make sure

play07:55

and say API and not pronounce appy or

play07:58

something like that another Pro tip I

play07:59

have for you you may notice that I put

play08:01

the mortgage as 6% and I spelled out 6%

play08:05

Bland AI recommends you spell out

play08:07

numbers the AI agent tends to say those

play08:10

better and handles them better that way

play08:12

so make sure you put numbers spelled out

play08:14

even phone numbers if you have that in

play08:15

here I recommend putting it as spelling

play08:17

out the the phone number using the words

play08:20

okay so now we're going to get into some

play08:21

of the specific things to Bland Ai and

play08:24

what they allow you to modify in your

play08:26

call I got all of this information from

play08:28

their document from their website I'm

play08:30

going to show you where to find that so

play08:31

that you can see the other things that

play08:33

you can modify in this program so going

play08:35

back to the developer portal you'll see

play08:36

on the left column here there's a

play08:38

section under resources called

play08:40

documentation if you open the

play08:41

documentation the variables that we're

play08:42

using today are in the send call section

play08:45

so if you click Send call here it'll

play08:47

actually give you kind of a breakdown of

play08:48

the different variables and parameters

play08:50

that you can adjust if you look on this

play08:52

side don't get confused by that if you

play08:53

click python it'll be in a more familiar

play08:55

format we have ours defined as batch

play08:57

payload and then these are the different

play08:59

param that they'll allow you to modify

play09:01

and kind of show you an example of what

play09:02

it can look like I've parsed mine down

play09:04

to just some of the more interesting

play09:06

variables but you can certainly include

play09:08

some of these if you're interested in

play09:10

adding that this middle section will

play09:11

give you more information on each

play09:13

variable so it'll tell you how to format

play09:15

it correctly what some of the different

play09:16

options are that kind of thing going

play09:18

back to our program the first one we

play09:19

have is models this is actually the

play09:21

Bland AI model that we're going to be

play09:23

using to talk to people on the phone so

play09:25

if you go to the model section of the

play09:27

documentation you'll see that they

play09:28

Define model as either enhanced gp4 Bas

play09:32

or Turbo and it says it defaults to

play09:34

enhanced so that means if I didn't

play09:35

include it in my code it would just

play09:36

automatically use that but I wanted to

play09:39

show this so I actually defined it in

play09:40

mine so you could make it gp4 uh base

play09:43

enhancer turbo but they give you some of

play09:45

the trade-offs here so for our

play09:46

application enhanced is probably the

play09:48

best to choose the next thing I've got

play09:49

is wait for greeting so this is

play09:52

basically telling the AI agent to wait

play09:54

for the person on the other line to say

play09:56

hello or pick up the phone and and say

play09:58

something first it's not just going to

play10:00

start talking as soon as that person

play10:01

picks up the phone if you want to change

play10:02

that if you want your AI agent to start

play10:04

talking right away you can change that

play10:06

to false and then it'll just start

play10:07

talking as soon as the person picks up

play10:08

the phone first sentence pretty

play10:10

self-explanatory this is going to be the

play10:11

sentence that the AI agent says uh when

play10:13

the person picks up or when it first

play10:15

starts talking so I have mine said to hi

play10:17

there calling about refinancing your

play10:18

mortgage down to 6% are you the current

play10:20

homeowner so for voice ID you can

play10:22

actually change the voice of the AI

play10:24

agent and even set it to a custom voice

play10:26

if you want again I covered this in a

play10:28

past video on how you can make a custom

play10:30

voice uh but I'll show you how you can

play10:32

change and use some of the default

play10:33

voices that they have from Bland AI so

play10:35

if you go back to the developer portal

play10:38

you'll see a section here called voices

play10:40

so if you click on that it's got voice

play10:42

presets or your voices if you click on

play10:44

your voices there's a voice ID that's

play10:47

set here you can decide if you want your

play10:49

AI agent to sound like Ryan or Adriana

play10:52

whoever you just need to copy this long

play10:54

string it looks like they've added a lot

play10:56

more voices since I was first on here so

play10:58

I'm going to use one of these other

play10:59

voices in my program for this example so

play11:02

let's use Josh so I'm going to copy this

play11:05

and then paste it here where it says

play11:07

voice ID in quotation marks so now it's

play11:09

going to use the Josh voice for each of

play11:11

the calls and you can change that to

play11:12

whatever you'd like okay after that

play11:14

there's reduced latency this is

play11:15

basically how quickly you want the AI

play11:17

agent to respond so if you wanted to

play11:19

have more of a natural conversational

play11:21

flow you want to set this to true if you

play11:23

don't have this set to true there can be

play11:24

like a lag or a delay when the person's

play11:26

talking or ask a question I have this

play11:28

set to true and I I think that's

play11:30

probably the best temperature is how

play11:32

creative you want the AI agent to be if

play11:33

I go back to the documentation it tells

play11:35

you that you can set it from a value of

play11:37

zero and one and it controls the

play11:39

randomness of the llm zero causes more

play11:41

deterministic outputs while one will

play11:43

cause more random in this program I have

play11:45

it set to 7 test mode so this is

play11:47

important so when you're first setting

play11:48

up this program you want to set this to

play11:50

true so what this does is you've got a

play11:52

call sheet of let's say 100 numbers and

play11:55

you're testing it out you don't want it

play11:56

to just start calling all 100 numbers

play11:58

while you're trying to get it figured

play11:59

out so if you set this to true it will

play12:01

only call the first number in the Excel

play12:03

sheet so when I was playing with this I

play12:05

set the first number to my phone number

play12:08

um and then that way I could talk with

play12:09

the AI agent and make sure that it was

play12:11

working the way that I wanted it to work

play12:13

campaign ID and label these are just uh

play12:15

ways to label the batch of calls that

play12:18

it's going to be making so that you can

play12:19

kind of manage it from your Bland AI

play12:21

account okay so now we've defined the

play12:23

payload that we're going to be sending

play12:24

for each of the calls this next section

play12:26

is just how we send the call so when you

play12:28

run the program it'll actually send all

play12:30

of that for each line of the Excel sheet

play12:33

this next section here is just a way for

play12:34

us to get a print out of whether it

play12:37

successfully started the calls or if it

play12:39

errored out and had a problem so if it

play12:41

works it'll say batch sent successfully

play12:44

and if it fails you'll get this uh

play12:45

failed to send batch print out in the

play12:48

code down below so that's useful because

play12:49

it lets you know the codee's working as

play12:51

you want like you wanted it to so now

play12:53

this thing's running and you're like

play12:54

okay I hope it's working or you know

play12:56

what's the feedback you know are people

play12:57

picking up is it just going to voicemail

play12:59

are people asking to be transferred so

play13:02

this next section allows you to generate

play13:03

a report of the batch of calls that

play13:05

you're sending so NE you can run this at

play13:07

any time you know presumably after it's

play13:09

been running for a little bit so that

play13:10

you actually get some data on the calls

play13:12

that it's making but it'll create this

play13:14

report based on the goal that you set

play13:17

and then it'll ask this question for

play13:18

each call and then give you an answer

play13:20

for each of these questions in a report

play13:22

format so for this I'm saying are

play13:24

customers interested in refinancing

play13:25

their mortgage and for each call I want

play13:27

to know who answered the call was it is

play13:29

it a human or did it go to voicemail was

play13:30

the customer interested in refinancing

play13:32

yes or no did they ask to be transferred

play13:35

yes or no and what reason did the

play13:36

customer have for not wanting to

play13:38

refinance uh you'll notice for this one

play13:40

I set it to string so what that is is it

play13:42

allows it to be more than just a yes no

play13:44

or a numerical answer this is going to

play13:46

be um what we call a string of

play13:48

characters or words so you know the

play13:50

customer may say I'm not interested

play13:53

because my rate's lower than 6% right

play13:55

now this just lets you know that the

play13:56

report worked correctly and then defines

play13:58

some of the Vari based on the questions

play14:00

I asked you can modify this goal and

play14:02

these questions as well as the uh

play14:04

response and variables it'll print this

play14:06

report then in the window right here for

play14:08

the calls that it's already completed um

play14:10

and then comment it out here you'll see

play14:12

this uh hashtag sign if you remove that

play14:14

hashtag sign then it'll actually save

play14:17

the report as a CSV file in your Google

play14:20

Drive in the folder here so you know if

play14:22

you have 100 calls with statuses and

play14:24

reports and everything you'll want it to

play14:26

save as a report so that you can look at

play14:28

it more easily Excel and uh be able to

play14:30

do more with the data there um and then

play14:32

if for whatever reason this code doesn't

play14:34

work it'll tell you fail to analyze

play14:35

batch and so you know there's something

play14:37

going on up here that that didn't work

play14:38

right you can run this section here and

play14:40

it'll actually stop the batch of calls

play14:42

so it doesn't have to just finish

play14:44

through the rest of the calls that

play14:45

you're making so that's kind of the

play14:46

emergency break if you will that allows

play14:48

you to stop this thing from running but

play14:50

that's pretty much it so again to run

play14:52

this you're just going to hit these

play14:53

little play buttons I'll run this one

play14:55

just so we can kind of see an example of

play14:57

what it should look like when it runs so

play14:58

you see this little green check mark

play14:59

that means it's it's completed and then

play15:01

you'll run this one and if it runs

play15:03

successfully you should get the little

play15:04

check mark here and then at the bottom

play15:06

it'll say batch sent successfully so now

play15:08

it's going to start going through the

play15:10

call sheet but because I have it the

play15:12

test mode set is true it's only going to

play15:14

call the very first number in the call

play15:16

sheet so again if you want this to run

play15:18

for the entire call sheet you need to

play15:20

change this to false now I can run the

play15:23

analysis report should only have one

play15:24

call that it's performed and you can see

play15:26

this is the print out that it has here

play15:28

so batch analyzed successfully it gives

play15:30

you the call ID so each call is going to

play15:32

have a unique ID um and then answered by

play15:35

it says na here the call may not be

play15:37

completed yet or because I'm in test

play15:39

mode it may not generate it um and then

play15:41

interested in refinancing um and then

play15:43

it'll be the result here and then ask to

play15:45

be transferred and reason not interested

play15:47

so you can kind of see they're like

play15:48

right Justified basically but um you

play15:51

know if you had 100 numbers it would uh

play15:53

have 100 call IDs and go all the way

play15:55

down and if while it's running you

play15:57

wanted to stop sending the calls and

play15:59

proceeding through the call sheet you

play16:01

can uh use the bottom one here to stop

play16:03

the call but that's pretty much it so

play16:05

again I have all of the code and links

play16:08

in the video description if you use the

play16:10

link to sign up for Bland AI they'll

play16:12

give you 25% off so definitely use that

play16:14

and if you enjoyed today's video please

play16:16

consider subscribing to the channel it

play16:18

helps me out a lot and lets me know what

play16:19

type of content people enjoy but uh

play16:21

that's all for now so until next time

play16:23

thanks

Rate This

5.0 / 5 (0 votes)

関連タグ
Cold CallingAI ScriptSales TipsReal EstateFundraisingLead GenerationHollywood MoviesTime ManagementCustomer EngagementTelemarketing AISales Automation
英語で要約が必要ですか?