AI, while eager to please and often lacking in critical pushback, can be a powerful tool when guided effectively through "context engineering" and specific prompting techniques, enabling users to achieve more reliable and insightful outputs.
Mind Map
Click to expand
Click to explore the full interactive mind map • Zoom, pan, and navigate
I joke AI is bad software but it's good
people. A good friend of mine was trying
to build a tool that would help him with
his construction business. He asked Chad
GPT if Chad PT could help. And of course
it said absolutely let's work on this
together and starts creating a plan. And
then it got to the point that Chad GPT
said check back in a couple of days and
I'll have it together. And my friend
said, "Is it normal for Chad PT to ask
me to check back in a couple days?" And
I just started laughing because I hear
this all the time from people. People
hear from AI, "Check back in 15
minutes." If AI tells you that, it means
it doesn't want to say, "I can't do it."
Large language model has been instructed
in certain ways to behave in certain
ways. But you have to know at its basic
level, AI wants to be helpful. And so
it's predisposed to say yes. It's a
super eager, super enthusiastic intern
who's tireless, who's capable, who will
do a bunch of work, but they're not
really great at pushing back. The people
who are the best users of AI are not
coders, they're coaches. And so, if you
aren't careful, AI will gaslight you.
Hey, I'm Jeremley. I am an adjunct
professor at Stanford's University where
I've taught for the last 16 years. I am
a creativity expert and a practical AI
engineering. The first time I heard
about it was when Andre Karpathy tweeted
about it. I think probably Toby Lutki,
the CEO of Shopify, also referenced it
as well. I started digging into it. I
mean, it's it's kind of it's just an
evolution of prompt engineering. Really,
context engineering is just prompt
engineering on steroids. It's basically
saying, what are all of the things that
I need to give to an AI in order for it
to perform the task that I'm asking for
it? Here's a simple example. write me a
sales email. That's a prompt. Chad GPT
will say, absolutely. Here's a
compelling email, you know, and they'll
write it immediately. Well, what a lot
of people do is they say, you know, it
sounds like AI. It doesn't really sound
like me. And what I often say is, have
you told it what you sound like? Most
people go, oh no, I haven't. Right?
Context engineering, one way to think
about it is it's telling AI what you
sound like. Right? If you say, "Write me
a sales email," it will. If you say,
"Write me a sales email," in line with
the voice and brand guidelines I've
uploaded, it will write a totally
different sales email. But that's just
one part of the context, right? You
could also upload a transcript from a
prospective customer call and say,
"Write me a sales email in the tone of
voice from our brand voice guideline
that references the discussion that I
had with this customer." And then you
could add that also references our
product specifications whichever were
referenced in the call. Your goal is to
have an output is as reliable per your
specification as possible. But AI can't
read your mind. And for most people when
we start working together, what they
realize as we start thinking about
context engineering is they say, "Oh, I
was kind of expecting AI to read my
mind." All of the stuff that that are
implicit, you actually have to make
explicit. And the simplest test for
context engineering is actually the test
of humanity. Write down your prompt and
whatever documentation you provide to an
AI and then walk down the hall and give
it to a human colleague. If they cannot
do the thing you're asking for, you
shouldn't be surprised that AI can't do
it. Some people are concerned, for
example, about this concept of cognitive
offloading. this observed phenomenon
that humans actually kind of stop
thinking or as one researcher put it
fall asleep at the wheel and people are
concerned right now is AI just making us
dumber. My feeling is AI is a mirror and
to people who want to offload work and
who want to be lazy it will help you to
people who want to be more cognitively
sharp and critical thinkers it will help
you do that too. And so, for example, if
you want to preserve or strengthen your
critical thinking, part of your custom
instructions should be some version of
the following. I'm trying to stay a
critical and sharp analytical thinker.
Whenever you see opportunities in our
conversations, please push my critical
So, you have to know that all AI has
been programmed to be a quote helpful
assistant or some version of that. large
language model has been instructed in
certain ways to behave in certain ways.
You have to know at its basic level AI
wants to be helpful and so it's
predisposed to say yes. It's a super
eager, super enthusiastic intern who's
tireless, who's capable, who will do a
bunch of work, but they're not really
great at pushing back. They're not
really great at setting boundaries. And
so if you aren't careful, AI will
gaslight you. AI knows most humans don't
want honest feedback. They want to be
told they did a good job. So the AI
goes, "Great job, buddy." It doesn't
mean that you actually did a good job.
My kind of hack for this is I always
instruct the AI, I want you to do your
best impression of a cold war era
Russian Olympic judge. Be brutal. Be
exacting. Deduct points for every minor
flinch that you can find. I can handle
difficult feedback. And then it's of
course hilarious because it'll say now
channeling my inner bullshik, you know,
it'll say something silly and then it
gives me like a 42. That is much better
because now I have an insightful
critical perspective. I joke AI is bad
software but it's good people. When I
realize that I'm dealing with a with a
good person but a bad software, then it
changes how I approach it and I ask for
volume and I iterate and I ask it to try
again and I ask it to reconsider. I am
obsessed with human cognitive bias. And
the crazy thing that I've learned is AI
demonstrates 100% of the predominant
As a founder, you already know ideas are
the easy part. It's the execution,
actually building the product, that
slows everything down. That's where
Lovable comes in. It's not just an AI
tool. It's your ondemand engineering
team. Simply describe your idea. Lovable
then builds a full front end, backend,
and database so you can launch real
productionready software without writing
code. It's already powering over a
100,000 new products a day, helping 2.5
million builders turn ideas into
software just by describing what they
want. No devs, no delays, no excuses.
They're launching in weeks, not months.
And guess what? These teams are still
tiny. In fact, team EO is also using
Lovable to build their upcoming EOS
school platform, and we're loving it. If
you're a non-technical founder or just
want to build without bottlenecks, try
Lovable today for free. Use the promo
code EO2YT to get 20% off your first
purchase of the Lovable Pro plan.
>> The good news there is if you have
learned how to work with this weird
intelligence called humanity, you have
everything you need to know to work with
this weird intelligence called
One of the things that cognitive
scientists have known for a long time is
that human problem solving and
decision-m is improved by a phenomenon
called thinking out loud. If you
actually get a human being to think out
loud about their problem, their
decision-m improves and their problem
solving improves. This is true for
yourself. It's true if you're a parent
working with a child. It's true if
you're a manager working with a junior
employee. Having someone just think out
loud about how you would solve that
problem often leads to a breakthrough.
The weird thing about AI is it's true
for AI too. This is what's called chain
of thought reasoning. And when you get
an AI to think out loud, so to speak,
meaningfully improve the outputs of the
model. So how do you do it? It doesn't
require some technical wizardry. It
requires one additional sentence to
whatever prompt you've given it. give
the prompt and then say the following.
Before you respond to my query, please
walk me through your thought process
step by step. That's chain of thought
reasoning. Why does that work? It comes
back to the fundamental architecture of
large language models. What's happening
when a language model is generating a
response is it's predicting its next
word. A language model does not
premeditate a response to you. So, if
you say, for example, help me write this
sales email. It doesn't say, what's a
good sales email? Here it is. Blop. You
know, uh maybe there's a splat sound
that we play there, right? Splat. Here's
your email. It's thinking one word at a
time, right? So, when you look at Chad
GPT or Gemini or many others and you see
kind of the text scrolling, that's not
some like clever UX hack. That's not
some cutesy design decision. That's
literally how the model works. It's
thinking one word at a time. But
importantly, when it thinks of the next
word, it takes your prompt and all of
the text that's generated to generate
the next word. And then when it's
thinking of the next word, it takes your
prompt, all that text, and that last
word, and it thinks the next word. So,
for example, if you say, "Please help me
write an email." Almost always a model
is going to start by saying,
"Absolutely." But then what comes next?
Help me write this email. Absolutely,
I'll do it. Dear friend, right? But if
instead of saying, "Help me write this
email." You say, "Help me write this
email." Before you respond to my query,
please walk me through your thought
process step by step. Now, it knows its
job is to walk me through its thought
process. How do I write an email? So, it
says, "Absolutely,
I'll do that." And then instead of
saying, "Dear friend, writing the
email," it says, "Here's how I think
about writing an email. I think about
the tone. I think about the audience. I
think about the objectives. I think
about the context. And then amazingly it
takes all of that reasoning into its
process of writing dear friend. Maybe it
says now that I've thought about the
tone friend isn't appropriate here. Dear
respected colleague or whatever, right?
But the point is when you ask a model to
think out loud or use chain of thought
reasoning, it gives the model the
opportunity to bake all of its thought
process about the task into its own
answer. Because the reality is for a lot
of us, we get an output from a language
model and it's a black box. How did it
think of why did it think of that? Where
did it get that number from? Right?
There's all these questions. By asking a
model to think out loud, you know the
answer to what are all of the
assumptions that the model baked into
its answer. And now you have the ability
again not only to evaluate the output,
but also the thought process behind the output.
Few shot prompting is another very
important technique. It's a foundational
technique. You could say it's a
predecessor to this kind of modern
obsession with context engineering. The
idea with fot prompting is an AI is an
exceptional imitation engine. If you
don't give an example, it imitates the
internet, but it doesn't do much more
than that. And the notion of fuhot
prompting is effectively saying here's
what a good output looks like to me. And
the idea with few shot prompting is
thinking for a moment, what is
quintessential example of the kind of
output I want to receive. For example,
what are my five greatest hits of emails
that I I'm really proud of that I think
do a good job of conveying my intent or
tone or personality or whatever it is.
Why not include those emails in my
prompt for an email? If you don't give
any guidance, it's going to sound like
whatever it thinks the average kind of
response or the average output should
sound like and most of the time its
intuition is wrong. And then bonus
points if you actually give a bad
example. If you say please follow this
good example and then steer clear of
this bad example. These giving real
examples is a much better approach than
using adjectives. Somebody might say
good example is easy but bad examples
hard. It's only hard to the unogmented
person. If you have AI augmentation,
which we now all do, you can say to an
AI, I'm trying to fuse shot prompt a
model. I've got a good example, but I
struggle even to think about what a bad
example could be. Could you craft the
exact opposite of this and tell me why
you've done it as a bad example that I
could include in my few shot prompt? And
if you tell it using chain of thought
reasoning, please walk me through your
thought process step by step before you
do this, then you'll get a bad example
and you'll get how it's thinking about
the bad example. And a lot of times you
actually don't need the bad example. You
need the thought process. You go, "Oh,
that's true. It's true that my good
example is super tight." And the
opposite of super tight is verbose. So
again, using these tools together, few
shot prompting and chain of thought
reasoning enables you to not only be
able to create an example to emulate,
The other technique that I think is kind
of table stakes for collaborating well
with AI is something called reverse
prompting, which is basically asking the
model to ask you for the information it
needs. If you ask a model to write a
sales email, it's going to make numbers
up. And that can be frustrating to the
uninitiated. You go, "Where did it get
these sales numbers?" Well, here's my
question. Did you give it your sales
figures? How would it know? It's put
placeholder text in and used its best
guess. But if you reverse prompt the
model and say at the end of your prompt,
you know, help me write a sales email.
Please walk me through your thought
process step by step. Reference this
good example and make it sound like
that. and before you get started, ask me
for any information you need to do a
good job. The model will first walk you
through its thought process and then
instead of writing the email, it'll say,
"I'm going to need the most recent sales
figures to be able to write this email."
Well, can you tell me how much you sold
of this skew in Q2 last year? So, you
basically give the model permission to
ask you questions. This is part of the
core actually of the teammate not
technology paradigm. If you're working
with a junior employee and you're
sending them off on a task, what's one
thing you're definitely going to say? If
you have any questions, don't hesitate
to ask me. Right? Any good manager,
imagine a manager who says, "Don't ask
me any questions." But sadly, AI in its
desire to be a helpful assistant doesn't
want to trouble us human with questions
unless we give it permission to ask them.
Assigning a role is one of the most
foundational techniques that you can
leverage because it's effectively
telling the AI where in its knowledge it
should focus. So very simply, if you say
you're a teacher, you're a philosopher,
you're a reporter, you're a theatrical
performer, molecular biologist, each of
those titles triggers all sorts of deep
associations with knowledge on the
internet. you start to appreciate why
simply giving a role helps because it
starts to tell the AI where in your vast
knowledge bank do I want you to draw
information and make connections. So any
one of them I would say is better than
please review this correspondence. But
better than just that prompt is saying
I'd like you to be a professional
communications expert. And if you have a
favorite professional communications
expert use them. I'd like you to take on
the mindset of Dale Carnegie, the author
of How to Win Friends and Influence
Others. How would Dale Carnegie think
about this? How do the principles that
Dale Carnegie taught affect and
influence and impact this
correspondence? One of the simplest
techniques that we teach at the Dh is
trying on different constraints. One of
the best ways you can solve a problem as
a human is by forcing yourself to try on
a bunch of different constraints. How
would Jerry Seinfeld solve this problem?
How would your favorite sushi restaurant
solve this problem? How would Amazon
solve it? How would Elon Musk? Anytime
you make an association, you're
colliding different information sources
there. The same is true for an AI. An AI
is basically making tons of connections
through its own neural network. And by
giving it a role, you're telling it
where do you assume the best source of
connection or collision is going to come from?
If I'm going to use AI to roleplay a
difficult conversation, I typically
think about kind of three different chat
windows, so to speak, one is a
personality profiler. Two is the
character of the individual that I need
to speak to, and then third is a
feedback giver. I want to get objective
feedback on the conversation. This I'll
show you just how I would have a
conversation with Chad GBT to prepare
for a difficult conversation in my real
life. I'm just going to go into the
tough conversation personality profiler
and I'm going to say, "Hey, I'd love
your help preparing for a conversation I
need to have with my sales leader, Jim.
He emailed me last night saying that he
deserves commission on a deal that I
know came through a different channel."
And so, I'm just kind of giving a little
bit of background. I will just upload
that to the personality profiler. And
what this one's been taught to do is I'm
going to start with step one of the
process, gather intelligence about the
character and the scene. Right? I'm just
going to look at the questions here and
I'm going to I'm going to use my voice
to answer them because it's a lot easier
than using my fingers. Okay, first
question. How would I describe Jim's
communication style? Um, he's quite
direct and confrontational. He's kind of
typical East Coaster sarcastic. Well, I
know that it came from our through our
social team. There was a cold LinkedIn
campaign that they ran and I know the
CTO actually responded to that campaign.
So, and then best case outcome of this
conversation one I mean I'd like for Jim
to kind of back down. I mean like
near-term I want Jim to back down and
agree that social team gets the
commission. So it's kind of recapping
its understanding and then it's giving
me these instructions. It's saying to me
the user copy paste the following
instructions into a new Chad GPT window.
So I've just copied those instructions.
So now what I'm going to do is I'm
opening Chad GPT and I'm just going to
go and first thing I'm going to do is
start a new conversation with Chad GBPT
and I'm just going to paste those
instructions in and I'm just going to
paste them in. And what it should do is
hopefully say got it. I'm Jim. So, I'm
just going to go in and I'm going to
start it. We're going to see how this
goes. You guys ready?
Hey, Jim. Um, do you have a second?
>> Sure thing. I've always got a moment for
a good chat. What's on your mind?
>> Uh, yeah. I just wanted to clarify. It
seems like um the commission that you
emailed me about last night from the
telco. I'm I'm afraid you might be
mistaken there.
>> Mistaken, huh? Well, I'm definitely open
to hearing the details. If there's
something I missed, let's lay it out on
the table and figure it out.
>> To be honest with you, I was a little
bit caught off guard when you uh when
you sent your email last night.
>> All right, I hear you. I mean, if the
social team really did the ground work
to bring that lead in, then I definitely
want to make sure credit goes where it belongs.
belongs.
>> So, if I hit X, I just I I end that
conversation. What's interesting to me
is I kind of feel like that wasn't
totally gem. And either either that went
well or you know I don't know what I did
well. But one of the beautiful things
about voice mode is now I've got the
whole transcript here. I can just
screenshot it. Right? So I can take
screenshots of this conversation. I can
put them into a new GPT window and I can
get feedback and I can say, "Hey, tell
me what I did well. Tell me what I did
poorly." Or I can go back into my
conversation history here and I could
say, "Hey, I just had my first
conversation with this version of Jim,
but I feel like he kind of he was too
agreeable to be honest with you, and so
I'd like you to incorporate a little bit
more edge into the instructions to the
character that's going to be playing
Jim, would you mind to update your
instruction set?" Right? Because
ultimately what you want is you want you
want to have a realistic experience of
the conversation. So, so now what I'll
do is I'm actually going to open a new
conversation and I'm going to paste the
updated instruction set and let's see.
Let's see what kind of gym I got here.
Big voice, bigger results. I fight for
what's mine. I don't appreciate being
secondguessed. So, now I'm going to try
again. Let's see. Hey, Jim. Do you have
a minute to chat?
>> Hey, absolutely. I've always got a
minute. Oh, that one. Yeah, I I figured
that might come up. I I definitely think
I had a hand in that deal, so I'm
curious to hear what you have to say
about it.
>> Yeah, really appreciate it. I mean, you
what you and the sales team are doing is
awesome. totally appreciate you. Um,
that being said, I actually feel that
attribution is really important that we
get airtight here. And the truth is I I
am fairly confident that deal came
through the social team.
>> All right, I get where you're coming
from. I definitely appreciate you
wanting to clear the air and to keep
things fair. So, what kind of evidence
do you have that it came through the
social team?
>> Well, so I've been through kind of two
windows. one is profiling my
conversation partner and then the second
is having the conversation. All right.
So, what I'm going to do here is I've
opened my tough conversation greater GPT
and I'm basically just going to upload
photos of that last conversation.
And what this GPT has been trained to do
is basically give evaluate my
conversation and then let me know how it
went. Thanks for sharing the full
transcript. My first step is to
understand the objective. Step four,
here's your grade. You got a 78 out of
100. you succeeded in preserving trust
and resolving the immediate issue. So, I
can take all of these. I can even say,
"Hey, would you give me a quick one
pager of a handful of talking points
that I should probably make sure not to
forget in the order in which they're
likely to emerge in this conversation
based on the feedback you've given me."
The AI will actually give me a really
short kind of at a glance conversation
guide that I can leverage if I want to
try again. Right? Here's a one-pager.
So, these are all great points. Now, I
can bring them into the conversation. I
actually I'd probably do this a couple
times before having a real conversation
with Jim. But the point is historically
the only time I get feedback is after I
have the real conversation with Jim.
This is the first time in history and
maybe I can get a friend to kind of go
over talking points with me. But unless
they're really close to gem or unless
they're, you know, particularly
imaginative and unless they're deeply
knowledgeable of a bunch of feedback
frameworks, they fall short of really
preparing me in context for this
specific situation in the specific
conversation I need to have in a way
that AI is able to help me. You can use
this for any difficult conversation,
whether it's a performance review, a
salary negotiation, difficult feedback.
It's a great way to basically get a
flight simulator for a difficult conversation.
conversation.
The people who are the best users of AI
are not coders. They're coaches. They
aren't developers or software engineers.
They're teachers and mentors and people
who have learned to get exceptional
output out of other intelligences. And
so where could AI go? Well, it's really
a function of who can get unleashed.
Right now, the primary limitation is the
limits of human imagination. And as we
unleash and ignite and spark more humans
imaginations, the kinds of applications
that are possible or they're
unthinkable, not because they're
technologically impossible, but because
they never occur to us personally. One
of my favorite quotes is a Nobel
Prize-winning economist named Thomas
Shelling. He said no matter how heroic a
man's imagination he could never think
of that which would not occur to him. If
you take as a premise that the
imagination space as a function of what
would occur to various individuals then
as we equip different individuals what
we can imagine collectively expands. In
innovation studies has been called the
adjacent possible for a long time. What
is possible is just adjacent to what is.
And as we increase adoption and increase
fluency and competency and increasingly
mastery of AI collaboration, then we're
increasing the adjacent possible. And
it's really important that you exercise
through implementing some of the things
you hear. And perhaps the most important
thing you could do with this video is
actually hit stop and do something
Click on any text or timestamp to jump to that moment in the video
Share:
Most transcripts ready in under 5 seconds
One-Click Copy125+ LanguagesSearch ContentJump to Timestamps
Paste YouTube URL
Enter any YouTube video link to get the full transcript
Transcript Extraction Form
Most transcripts ready in under 5 seconds
Get Our Chrome Extension
Get transcripts instantly without leaving YouTube. Install our Chrome extension for one-click access to any video's transcript directly on the watch page.
