The Marketer's Guide to Chain Prompting with AI - AI Fundamentals Course Part 3

By Dan Sanchez · Episode published May 3, 2024

If you’ve been following my AI journey, you know I’ve been experimenting with different prompting methods to get better results from ChatGPT. But here’s the thing – I’ve been holding back on sharing one of my most powerful techniques.

Chain prompting is the secret sauce that takes AI from “pretty good” to “holy crap, that’s exactly what I wanted!”

What Is Chain Prompting?

Instead of throwing a massive prompt at AI and hoping for the best, chain prompting breaks complex tasks into smaller, sequential steps with feedback between each one.

Think of it like teaching a child to ride a bike vs. handing them a bike and saying “figure it out.”

Language models – even powerful ones like GPT-4 – struggle with complex, multi-step tasks. They’re much better at handling one clear instruction at a time. Chain prompting plays to this strength.

Here’s How It Works

Let me show you with a real example. Instead of asking AI to turn a podcast transcript directly into a LinkedIn post (which often gives mediocre results), I break it down:

First prompt: “Find 5 solid ideas that could be turned into LinkedIn posts”
My input: I select which idea I want to develop
Second prompt: “Break down idea #2 into 3 distinct actionable points”
My input: I confirm these points look good
Third prompt: “Turn this into a concise LinkedIn post following my template”

The result? A dramatically better post that captures exactly what I wanted – not what the AI thought I wanted.

Why Chain Prompting Beats Super Prompts

I’ve already shown you super prompts and the step method, so why bother with chain prompting?

You get to provide guidance at critical decision points
AI can focus entirely on one task at a time (what it’s best at)
You can course-correct before the AI goes too far in the wrong direction
The final output builds on confirmed, validated intermediate steps

The biggest difference? Chain prompting gives you control without sacrificing AI’s creative power.

Real Results From Chain Prompting

In my tests, chain prompting consistently produces better content than even well-crafted super prompts. When I created LinkedIn posts from podcast transcripts:

Super prompts: Good but sometimes too verbose or off-topic
Chain prompts: Concise, on-target, and captured the exact tone I wanted

The difference is night and day. I’ve seen it with client work too – chain prompting gets us to the “almost perfect” stage in fewer iterations.

Getting Started With Chain Prompting

Ready to try it yourself? Here’s my quick-start approach:

Identify the final output you want (post, email, analysis, etc.)
Break the creation process into 3-5 logical steps
For each step, write a clear, specific instruction
Add decision points where your input would be valuable
Keep the context flowing between prompts

The beauty of chain prompting is that it’s not just more effective – it actually saves time once you get the hang of it.

If you’ve been frustrated with AI marketing results, try chain prompting before you blame the AI. It’s often not the tool but the approach that makes all the difference.

But here’s the real kicker – what if you didn’t have to manually enter each prompt in the chain every time? What if you could automate this whole process? Stay tuned for my next post where I’ll show you how to turn chain prompts into custom GPTs that run your entire workflow with minimal input.

What complex AI task would you like to break down into a chain prompt? Let me know in the comments!

Frequently Asked Questions

What is prompt engineering for marketers?

Prompt engineering is the practice of giving AI clear instructions, context, examples, constraints, and output formats so it can produce more useful marketing work.

What makes a good marketing prompt?

A good prompt names the goal, audience, source material, tone, constraints, output format, and review criteria.

Is prompt engineering still useful?

Yes. Even as AI tools improve, clear instructions and strong context still help marketers get better, safer, and more repeatable outputs.

How can marketers improve prompts?

Marketers can improve prompts by adding customer context, examples, brand voice, success criteria, and a request for the AI to ask clarifying questions when needed.

What should prompts not do?

Prompts should not ask AI to invent facts, skip review, imitate private material without permission, or make claims that cannot be verified.

[Music]

welcome back to the AI driven marketer

I'm Dan sanchz my friends call me danz

and I am on a journey to master AI in

2024 today is part three of AI

fundamentals course that I am releasing

on the podcast for free and it will

always be free I'm putting it on YouTube

and I'm also going to be stringing all

these videos together in a personalized

course powered by AI to come in the

future so once all these videos Drop

stay tuned for hearing about how I make

that because I'll be documenting that

whole journey as well but I'm trying to

get the videos out there as fast as I

can because enough people are asking me

about how to how to level up their AI

game so I'm trying to make a

step-by-step instructions on how to do

that so today like I said is part three

and we're going to be going into a topic

called chain prompting now this is a big

Topic in the AI community and lots of

people have talked about this and how to

do it and where to do it I'm going to be

showing it based on the topic that we've

been talking about first we talked about

super promps the last video we talked

about the step method for getting better

results with chat gp4 specifically today

we're going to be talking about how to

use chain prompting to level it up even

still because like thought we were done

with the step method you're like oh my

gosh these prompts are getting so

freaking long there's a reason for it

isn't there so if you haven't checked

out the super prompting or the step

method episode go back and watch those

uh they're right before this one in the

feed or close to it and let's get

started into this one now again if you

are listening I'm going to do my best to

uh explain everything that I'm doing but

this is a video it is going to be

available to watch on Apple podcast and

on YouTube or on the website Aid driven

marketer.com but if you're on Spotify or

one of the other podcast apps then hang

with me if you're on a run or something

I'm going to try my best to explain

what's going on but this is a video

podcast at least for this episode not

all of them are as visually intense as

this one but I am looking at chat GPT so

let's dive into

it I am here in chat GPT 4 um in open

ai's interface here and we are looking

at the very end of the last episode that

we had where we had a long Mega prop

using the step method to load in a PDF

that hod as a template and an example of

what we wanted this post to look like

but there's a problem with it that I

didn't tell you about in the last

episode and that in this one you could

see I even broke down the prompt into

multiple steps I have a PDF with that

example it has the transcript from the

episode we're trying to convert into a

LinkedIn post and it says very

specifically you are an expert sales

coach so has the role you take a deep

breath and follow these step-by-step

instructions step one based on the

transcript from the episode find one

solid idea in the episode then move on

to the next step next step two turn that

idea into one actionable post for

LinkedIn using the templ and explained

in the attached an example on attached

PDF to guide your writing and then

there's a bunch there's a little bit

more more written here with other

instructions to keep it more concise and

all that kind of stuff but there is an

issue when you're giving multiple steps

in one prompt and that is currently at

this moment with chat gbt 4 or 3.5 if

you're using the free version of AI um

and this goes for all the language

models not just chat GPT AI currently

struggles to break complex tasks down

into multiple steps by itself because of

that it often does much better if you

break it down the steps for it and I

don't mean just in one prompt and making

it clear I mean like actually giving it

time and space to execute step one Let

It Go and then based on the results it

gives you after step one ask giving it

another prompt if you can baby step it

through and Link them all together that

is what we call a chain prompt in fact I

posted about this back in January

because I turned uh one of my custom

gpts into a chain prompt in case you

weren't paying for uh chat GPT plus to

be able to run the the faster way to do

it I turned it into a chain prompt so

you can get pre-production down for your

podcast with just a chain prompt you can

see a lot of people are putting out

slide decks like this on LinkedIn and

I'm tuned into LinkedIn now where I'm

looking at the slide deck I made it's

like your AI showrunner here's the chain

prompt to make it happen if you scroll

through the pages has step one put this

prompt in and it has some places for you

to copy and paste it in there some

information about your show so you

prompt that and then you you let it load

and do it thing and it gives you some

information and then you give it a

second prompt and then after it loads

that you give it a third prompt and then

you give it a fourth prompt and then a

fifth prompt in order to walk it all the

way through the my showrunner process

and the results that I get from linking

together the prompts like that are

freaking amazing you can get better

results too in fact let's go back to our

original example here we're going to

keep going on this one train turning

browny's Matt brownley getting lots of

airtime here uh turning your episode

into fantastic LinkedIn post so let's

what see what happens let's see the

difference when you

turn uh a super prompt into a chain

prompt it even becomes better even using

the step method so let's look at let's

take a look at what happens when you do

this so I took the same prompt we had

and I just didn't put it all in there I

broke it down remember we have this

super long prompt and I'm like

highlighting the last one and from the

last video it's really long and of

course the whole transcript's embedded

in there it's got the PDF and I'm just

going to break it apart break it up a

little bit so that AI can you know just

handle one thing at a time much better

at that and let's take a look at what I

did I still have the role you are an

expert sales coach and former VPO sales

Matt brownley based on the transcript

from your recent podcast below find five

solid ideas that can be turned into a

LinkedIn posts and let me choose from

the

ideas so now instead of having it then

move from it selecting one because who

knows there's a couple of major points

Matt made in the episode if we can turn

it into a chain prompt we can take a

quick look at them and pick one for

ourselves

right so we let AI do less and us do a

little bit more that's what's possible

with chain prompting and then of course

I gave it the episode transcript so

let's take a look at the results it gave

scrolling down it's a long transcript

and here it is based on Matt browny's

insights from the podcast episode here

are five potential LinkedIn post ideas

and it gives us and outlines the five

ideas with like a major title and a few

sentences describing the idea one is

discipline and focus in sales and sports

two is the importance of coaching in

achieving success three is Team Dynamics

in sales success four is results matter

learning from success and failure in

sales in life and five is strategic

focus in sales narrowing down to amplify

results and I was like huh I really like

this coaching idea so let's make a post

just about that one and I said can you

break down number two into three

distinct actionable points do not add

and this is important see this is a

prompt we don't need to do the full

super prompt because parts of it are

already in there we already gave it a

roll right and now I'm putting do not

add any major point that was not

mentioned in the transcript which is

important because AI can get off on its

own path and start adding in extra stuff

and you have to remind it to go back

farther up the chat to go and reference

the episode transcript again which it

has access to but you have to reference

that again in order for it to stay on

track because it will literally just

take what is it idea two here on

coaching and achieving success and then

kind of go make up some other stuff

about coaching in fact before before I

recorded this I ran and demo and then

had to go back and add that that

modifier at the end uh that limitation

so that it wouldn't actually make up

stuff because I ran it and it did it

just made up stuff I'm like he didn't

say that in the transcript what the heck

um so you have to keep it on track and

add little details like that in order to

keep it uh from just making up stuff and

it's not like what it made up was wrong

either it's just not what was talked

about in the episode so here it goes

certainly and I'm doing this because we

all know if you watch this last episode

the break down that I have for this post

Temple it actually uh takes three

Snippets and I wanted to be able to see

what it was going to do before it

actually went to the LinkedIn post so it

actually gave it coaches provide

structural feedback coaches help with

strategic thinking coaches as motivate

motivators and accountability Partners

which were all topics he talked about in

the post so then I do the last part of

the prompt that we had already created

in the last video um which is loading in

that post template an example and then I

start with the rest of the prompt turn

that into one actionable post for

LinkedIn using the template an example

in the attached PDF and a course sry

quote the PDF LinkedIn post post

template.pdf to guide your writing the

goal is to entice readers and listen to

the episode other instructions actually

modified this from the last time because

last time we noticed the post was a

little bit too long too many words

linkedin's very short very choppy much

more concise so I added one bullet in

nor from the normal one to say keep the

post extremely concise guess what it

caught it and it probably made it even a

little bit too concise for my liking for

LinkedIn post but it was still way

better it was really good so let's take

a look at what this LinkedIn look

LinkedIn post now looks like after

adding in our super prompt after adding

in the step method after adding in a

chain prompt in order to really narrow

it down what do we have let's take a

look and here it is ever feel like

you're running in a place a running in

place in your own sales career you're

not alone here's what coaching can do

for you and I love that it like just the

little metaphor at the beginning because

a lot of the conversation even as

concise as this post was and it's a

little too concise uh it still adds in

some of the flavor because the whole

thing was about like running triathlons

and races compared to sales so it's

still putting that in there you're not

alone here's what coaching can do for

you one and it has it broken down to the

three points structure and feedback

strategic thinking motivation motivation

and accountability and then breaks it

into like two super each point gets an

extra two sentences but they're like

five four word sentences structural

feedback keeps you on track shows you

where to improve they're fragments but

like it still works it keeps it short

and uh concise uh probably a little bit

too concise I would have liked to flush

those out a little bit more and I can go

and ask it now to like flush it out just

a little bit more a little bit too

concise and we could do that but I just

wanted to show you what this post can

now look like because this is now

looking like a really fantastic post it

just needs a little bit more

modification let it breathe a little bit

and it even finishes with the call the

action that we want find the full

episode here close mode. media fan

freaking tastic so you can see the power

of the chain prompt allows you to get a

little bit more control at it because

you can give input along the way and it

optimizes for what the AI can accomplish

it's really good at very small steps one

at a time it can analyze it can think it

can do research it can synthesize a lot

of data but if you give it a multi-step

project all in one go it'll try but the

more you can break it up into smaller

pieces especially with some gu along the

way the more likely it is to deliver you

better and better results so that is

chain prompting in the nutshell but stay

tuned for the fourth part of this series

where we're going to talk about uh how

to simplify this whole process because

believe it or not like you're probably

looking at this be like Dan I am not

going to go through this freaking amount

of mountain of work of having a super

prompt and the freaking template and

example for every time I need to turn a

podcast into just one LinkedIn post what

about the blog post what about all the

other stuff haha I got you covered cuz

that's what they've created custom gpts

for because believe it or not you can if

you're doing this over and over again

you have transcript after transcript and

you need to turn it into a LinkedIn post

every time we can automate that whole

process yes we can we can build this

this process out once in a chain prompt

and a and a template an example on the

super prompt we can build that all once

refine it and then just let that run

over and over and over again do you want

to see this turn into a custom GPT wait

for that next video on how to build

simple custom gpts and then complex ones

after that so stay tuned

[Music]