YouTube Transcript:
Context Engineering is the New Vibe Coding (Learn this Now)
Skip watching entire videos - get the full transcript, search for keywords, and copy with one click.
Share:
Video Transcript
Available languages:
View:
The honeymoon phase for vibe coding is
The honeymoon phase for vibe coding is over and the new paradigm for AI coding
over and the new paradigm for AI coding
over and the new paradigm for AI coding is context engineering. I truly believe
is context engineering. I truly believe
is context engineering. I truly believe this is going to be the next big thing
this is going to be the next big thing
this is going to be the next big thing for AI as a whole. And let me show you
for AI as a whole. And let me show you
for AI as a whole. And let me show you why. So starting off earlier this year,
why. So starting off earlier this year,
why. So starting off earlier this year, Andre Karpathy coined the term vibe
Andre Karpathy coined the term vibe
Andre Karpathy coined the term vibe coding. It's all about relying 100% on
coding. It's all about relying 100% on
coding. It's all about relying 100% on your AI coding assistant to build
your AI coding assistant to build
your AI coding assistant to build applications for you with barely any
applications for you with barely any
applications for you with barely any input and no validation. And this
input and no validation. And this
input and no validation. And this concept completely blew up. We all fell
concept completely blew up. We all fell
concept completely blew up. We all fell for this trap because of the dopamine
for this trap because of the dopamine
for this trap because of the dopamine hit of instant code generation and also
hit of instant code generation and also
hit of instant code generation and also because vibe coding is great for
because vibe coding is great for
because vibe coding is great for weakened hacks and prototypes.
weakened hacks and prototypes.
weakened hacks and prototypes. Basically, you rely on intuition and
Basically, you rely on intuition and
Basically, you rely on intuition and repetition until your code seemingly
repetition until your code seemingly
repetition until your code seemingly works, at least until you try to
works, at least until you try to
works, at least until you try to productionize and scale it and then
productionize and scale it and then
productionize and scale it and then suddenly it doesn't. And you can read
suddenly it doesn't. And you can read
suddenly it doesn't. And you can read these statistics all over the internet.
these statistics all over the internet.
these statistics all over the internet. One article that I appreciate in
One article that I appreciate in
One article that I appreciate in particular is the state of AI code
particular is the state of AI code
particular is the state of AI code quality from Codto. They did a massive
quality from Codto. They did a massive
quality from Codto. They did a massive survey across the developer landscape.
survey across the developer landscape.
survey across the developer landscape. You can see in the bottom purple
You can see in the bottom purple
You can see in the bottom purple quadrant here, 76.4 of real developers
quadrant here, 76.4 of real developers
quadrant here, 76.4 of real developers have low confidence shipping AI code
have low confidence shipping AI code
have low confidence shipping AI code without human review. And they encounter
without human review. And they encounter
without human review. And they encounter a lot of hallucinations. And it's not
a lot of hallucinations. And it's not
a lot of hallucinations. And it's not like AI coding itself is bad. I mean, I
like AI coding itself is bad. I mean, I
like AI coding itself is bad. I mean, I love it myself. It's vibe coding. AI
love it myself. It's vibe coding. AI
love it myself. It's vibe coding. AI code without human review that is the
code without human review that is the
code without human review that is the problem. Because here's the thing,
problem. Because here's the thing,
problem. Because here's the thing, intuition does not scale. Structure
intuition does not scale. Structure
intuition does not scale. Structure does. I heard that recently. I thought
does. I heard that recently. I thought
does. I heard that recently. I thought it was so beautifully put. Because the
it was so beautifully put. Because the
it was so beautifully put. Because the biggest problem that we have with AI
biggest problem that we have with AI
biggest problem that we have with AI coding assistants right now is around
coding assistants right now is around
coding assistants right now is around context. Often times they miss or lack
context. Often times they miss or lack
context. Often times they miss or lack it entirely. So they don't have the
it entirely. So they don't have the
it entirely. So they don't have the necessary context to get the job done.
necessary context to get the job done.
necessary context to get the job done. We need better context. We need
We need better context. We need
We need better context. We need structure. That is where context
structure. That is where context
structure. That is where context engineering comes in. So let's kick
engineering comes in. So let's kick
engineering comes in. So let's kick things off right now by diving into what
things off right now by diving into what
things off right now by diving into what context engineering is. Then after we'll
context engineering is. Then after we'll
context engineering is. Then after we'll get into the lab with claude code. I'll
get into the lab with claude code. I'll
get into the lab with claude code. I'll show you how it works for real with a
show you how it works for real with a
show you how it works for real with a practical example that you can use as a
practical example that you can use as a
practical example that you can use as a template to instantly improve your AI
template to instantly improve your AI
template to instantly improve your AI coding. This is not theoretical. For
coding. This is not theoretical. For
coding. This is not theoretical. For some reason, YouTube has been obsessed
some reason, YouTube has been obsessed
some reason, YouTube has been obsessed with the Gemini CLI recently. Meanwhile,
with the Gemini CLI recently. Meanwhile,
with the Gemini CLI recently. Meanwhile, context engineering has been blowing up
context engineering has been blowing up
context engineering has been blowing up everywhere else on the internet, and
everywhere else on the internet, and
everywhere else on the internet, and context engineering is definitely a lot
context engineering is definitely a lot
context engineering is definitely a lot more important. Like I always say,
more important. Like I always say,
more important. Like I always say, capabilities over tools. The Gemini CLI
capabilities over tools. The Gemini CLI
capabilities over tools. The Gemini CLI is a tool. Context engineering is a very
is a tool. Context engineering is a very
is a tool. Context engineering is a very important capability that should really
important capability that should really
important capability that should really dictate the way that you work with AI as
dictate the way that you work with AI as
dictate the way that you work with AI as a whole. And context engineering was
a whole. And context engineering was
a whole. And context engineering was even condoned by Andre who originally
even condoned by Andre who originally
even condoned by Andre who originally coined Vibe coding. This is his response
coined Vibe coding. This is his response
coined Vibe coding. This is his response to a tweet from Toby, the CEO of
to a tweet from Toby, the CEO of
to a tweet from Toby, the CEO of Shopify, where he's comparing context
Shopify, where he's comparing context
Shopify, where he's comparing context engineering to prompt engineering. We'll
engineering to prompt engineering. We'll
engineering to prompt engineering. We'll talk about that in a second, but I
talk about that in a second, but I
talk about that in a second, but I really love his definition here. It is
really love his definition here. It is
really love his definition here. It is the art of providing all the context for
the art of providing all the context for
the art of providing all the context for the task to be plausibly solvable by the
the task to be plausibly solvable by the
the task to be plausibly solvable by the LLM. Here's a paradigm shift with this
LLM. Here's a paradigm shift with this
LLM. Here's a paradigm shift with this context which is our instructions and
context which is our instructions and
context which is our instructions and rules, documentation, so on that
rules, documentation, so on that
rules, documentation, so on that deserves the respect to be treated as an
deserves the respect to be treated as an
deserves the respect to be treated as an engineered resource requiring careful
engineered resource requiring careful
engineered resource requiring careful architecture just like everything else
architecture just like everything else
architecture just like everything else in software. When AI coding assistants
in software. When AI coding assistants
in software. When AI coding assistants fail, it's most often because they just
fail, it's most often because they just
fail, it's most often because they just don't have the information they need.
don't have the information they need.
don't have the information they need. And no, I'm not just talking about
And no, I'm not just talking about
And no, I'm not just talking about prompt engineering. Context engineering
prompt engineering. Context engineering
prompt engineering. Context engineering is very much a step up. Like Toby is
is very much a step up. Like Toby is
is very much a step up. Like Toby is saying, prompt engineering is all about
saying, prompt engineering is all about
saying, prompt engineering is all about tweaking wording, phrasing things in a
tweaking wording, phrasing things in a
tweaking wording, phrasing things in a specific way to get a single good answer
specific way to get a single good answer
specific way to get a single good answer from the LLM. But context engineering,
from the LLM. But context engineering,
from the LLM. But context engineering, supplying all relevant facts, rules,
supplying all relevant facts, rules,
supplying all relevant facts, rules, documents, plans, tools. So the LLM has
documents, plans, tools. So the LLM has
documents, plans, tools. So the LLM has a whole ecosystem of context. That is
a whole ecosystem of context. That is
a whole ecosystem of context. That is the paradigm shift from basic prompting
the paradigm shift from basic prompting
the paradigm shift from basic prompting and vibe coding. Prompting is just one
and vibe coding. Prompting is just one
and vibe coding. Prompting is just one piece of the bigger picture that we have
piece of the bigger picture that we have
piece of the bigger picture that we have here. And one last thing in X, I thought
here. And one last thing in X, I thought
here. And one last thing in X, I thought this was really funny. The top comment
this was really funny. The top comment
this was really funny. The top comment from Andre's reply to Toby is saying
from Andre's reply to Toby is saying
from Andre's reply to Toby is saying context engineering is the new vibe
context engineering is the new vibe
context engineering is the new vibe coding. And then Andre replied by saying
coding. And then Andre replied by saying
coding. And then Andre replied by saying he's not trying to coin a new word. But
he's not trying to coin a new word. But
he's not trying to coin a new word. But Andre, if you're watching this, I think
Andre, if you're watching this, I think
Andre, if you're watching this, I think it is too late. I'm sorry. There is a
it is too late. I'm sorry. There is a
it is too late. I'm sorry. There is a reason that people hang on to every word
reason that people hang on to every word
reason that people hang on to every word that you say. Thank you for everything
that you say. Thank you for everything
that you say. Thank you for everything that you do in the AI space. But anyway,
that you do in the AI space. But anyway,
that you do in the AI space. But anyway, if you are a visual learner, I also
if you are a visual learner, I also
if you are a visual learner, I also found this beautiful diagram in GitHub
found this beautiful diagram in GitHub
found this beautiful diagram in GitHub on context engineering. So all the
on context engineering. So all the
on context engineering. So all the different components that we have in
different components that we have in
different components that we have in here together make up what context
here together make up what context
here together make up what context engineering is. So we have prompt
engineering is. So we have prompt
engineering is. So we have prompt engineering as a part of it like we
engineering as a part of it like we
engineering as a part of it like we already talked about. We have structured
already talked about. We have structured
already talked about. We have structured output. It's a way to make the output of
output. It's a way to make the output of
output. It's a way to make the output of AI agents and coding assistants more
AI agents and coding assistants more
AI agents and coding assistants more reliable. We have state history and
reliable. We have state history and
reliable. We have state history and memory. So agents and coding assistants
memory. So agents and coding assistants
memory. So agents and coding assistants be able to remember what they built in
be able to remember what they built in
be able to remember what they built in the past. We can do things like provide
the past. We can do things like provide
the past. We can do things like provide examples. And then also rag is a huge
examples. And then also rag is a huge
examples. And then also rag is a huge component of context engineering. not
component of context engineering. not
component of context engineering. not something that I'm going to be focusing
something that I'm going to be focusing
something that I'm going to be focusing on a ton in this video, but that's
on a ton in this video, but that's
on a ton in this video, but that's actually because I have a lot more
actually because I have a lot more
actually because I have a lot more coming soon for you for rag and context
coming soon for you for rag and context
coming soon for you for rag and context engineering, being able to supply
engineering, being able to supply
engineering, being able to supply external documentation and knowledge to
external documentation and knowledge to
external documentation and knowledge to our AI coding assistants. And I will say
our AI coding assistants. And I will say
our AI coding assistants. And I will say there is a lot that is going on here. If
there is a lot that is going on here. If
there is a lot that is going on here. If you want to really do context
you want to really do context
you want to really do context engineering, well, you have to put a lot
engineering, well, you have to put a lot
engineering, well, you have to put a lot of time up front creating this context
of time up front creating this context
of time up front creating this context for your AI coding assistant. It's a lot
for your AI coding assistant. It's a lot
for your AI coding assistant. It's a lot different than vibe coding where you
different than vibe coding where you
different than vibe coding where you generally dive right into the actual
generally dive right into the actual
generally dive right into the actual coding. But I always love to quote
coding. But I always love to quote
coding. But I always love to quote Abraham Lincoln here. He said, "If you
Abraham Lincoln here. He said, "If you
Abraham Lincoln here. He said, "If you give me six hours to chop down a tree,
give me six hours to chop down a tree,
give me six hours to chop down a tree, I'm going to spend the first four
I'm going to spend the first four
I'm going to spend the first four sharpening my axe." And that is exactly
sharpening my axe." And that is exactly
sharpening my axe." And that is exactly what we are doing here. And it is well
what we are doing here. And it is well
what we are doing here. And it is well worth your time to invest upfront into
worth your time to invest upfront into
worth your time to invest upfront into creating this context because you're
creating this context because you're
creating this context because you're going to get infinitely better results
going to get infinitely better results
going to get infinitely better results versus diving straight into the
versus diving straight into the
versus diving straight into the implementation. You're going to have
implementation. You're going to have
implementation. You're going to have better code. You're going to actually
better code. You're going to actually
better code. You're going to actually save a lot of time in the end and then
save a lot of time in the end and then
save a lot of time in the end and then just not have to go through as much
just not have to go through as much
just not have to go through as much pain. That is the whole point. That is
pain. That is the whole point. That is
pain. That is the whole point. That is what I want to show you in action in a
what I want to show you in action in a
what I want to show you in action in a little bit here. And the very last
little bit here. And the very last
little bit here. And the very last article that I want to show you is the
article that I want to show you is the
article that I want to show you is the rise of context engineering from lang
rise of context engineering from lang
rise of context engineering from lang chain. This is definitely worth a read.
chain. This is definitely worth a read.
chain. This is definitely worth a read. So I'll link to this in the description
So I'll link to this in the description
So I'll link to this in the description of the video. And actually everything
of the video. And actually everything
of the video. And actually everything that I shared with you here I'll link in
that I shared with you here I'll link in
that I shared with you here I'll link in the description. I've definitely been
the description. I've definitely been
the description. I've definitely been doing a deep dive into context
doing a deep dive into context
doing a deep dive into context engineering. I hope that's very obvious
engineering. I hope that's very obvious
engineering. I hope that's very obvious to you. And so their definition of
to you. And so their definition of
to you. And so their definition of context engineering is pretty cool
context engineering is pretty cool
context engineering is pretty cool because it aligns very very closely with
because it aligns very very closely with
because it aligns very very closely with what we've seen already. But this is the
what we've seen already. But this is the
what we've seen already. But this is the key paragraph that I want to focus on
key paragraph that I want to focus on
key paragraph that I want to focus on here. LLM applications are evolving from
here. LLM applications are evolving from
here. LLM applications are evolving from single prompts to more complex dynamic
single prompts to more complex dynamic
single prompts to more complex dynamic agentic systems. And then here is the
agentic systems. And then here is the
agentic systems. And then here is the real kicker. As such, context
real kicker. As such, context
real kicker. As such, context engineering is becoming the most
engineering is becoming the most
engineering is becoming the most important skill an AI engineer can
important skill an AI engineer can
important skill an AI engineer can develop. That is a bold claim. Maybe
develop. That is a bold claim. Maybe
develop. That is a bold claim. Maybe it's a bit of an exaggeration. I don't
it's a bit of an exaggeration. I don't
it's a bit of an exaggeration. I don't really know if it's the most important
really know if it's the most important
really know if it's the most important skill, but yeah, this just shows the
skill, but yeah, this just shows the
skill, but yeah, this just shows the theme that's starting to emerge here
theme that's starting to emerge here
theme that's starting to emerge here where context engineering certainly
where context engineering certainly
where context engineering certainly feels like the thing to focus on right
feels like the thing to focus on right
feels like the thing to focus on right now. And so with that, let's now dive
now. And so with that, let's now dive
now. And so with that, let's now dive into cloud code. I'll show you how we
into cloud code. I'll show you how we
into cloud code. I'll show you how we can implement this for real to get some
can implement this for real to get some
can implement this for real to get some insane results with AI coding
insane results with AI coding
insane results with AI coding assistance. So here is my template for
assistance. So here is my template for
assistance. So here is my template for you in a GitHub repository that I'll
you in a GitHub repository that I'll
you in a GitHub repository that I'll have linked in the description. My
have linked in the description. My
have linked in the description. My introduction to context engineering. Now
introduction to context engineering. Now
introduction to context engineering. Now you can get very very deep with context
you can get very very deep with context
you can get very very deep with context engineering, diving into rag and memory,
engineering, diving into rag and memory,
engineering, diving into rag and memory, things that I'll cover a lot more in the
things that I'll cover a lot more in the
things that I'll cover a lot more in the near future here. What I want to do with
near future here. What I want to do with
near future here. What I want to do with this is introduce you to the idea of
this is introduce you to the idea of
this is introduce you to the idea of using AI coding assistance to create a
using AI coding assistance to create a
using AI coding assistance to create a super comprehensive plan for a new
super comprehensive plan for a new
super comprehensive plan for a new project and then implement that. And
project and then implement that. And
project and then implement that. And we're going to be using cloud code. This
we're going to be using cloud code. This
we're going to be using cloud code. This is going to work for really any AI
is going to work for really any AI
is going to work for really any AI coding assistant, but I'm focusing on
coding assistant, but I'm focusing on
coding assistant, but I'm focusing on cloud code here because it is the most
cloud code here because it is the most
cloud code here because it is the most agentic and widely considered the most
agentic and widely considered the most
agentic and widely considered the most powerful AI coding assistant right now.
powerful AI coding assistant right now.
powerful AI coding assistant right now. And we're going to use cloud code to
And we're going to use cloud code to
And we're going to use cloud code to plan, create the tasks, code, write
plan, create the tasks, code, write
plan, create the tasks, code, write tests, and iterate on that all end to
tests, and iterate on that all end to
tests, and iterate on that all end to end so that after just a few prompts, we
end so that after just a few prompts, we
end so that after just a few prompts, we have a full project implemented for us.
have a full project implemented for us.
have a full project implemented for us. That is the power that we have with
That is the power that we have with
That is the power that we have with context engineering. And by the way, a
context engineering. And by the way, a
context engineering. And by the way, a lot of what I'm about to dive into with
lot of what I'm about to dive into with
lot of what I'm about to dive into with you here is inspired by someone in the
you here is inspired by someone in the
you here is inspired by someone in the Dynamis community, Raasmus. He did a
Dynamis community, Raasmus. He did a
Dynamis community, Raasmus. He did a workshop last month in our community and
workshop last month in our community and
workshop last month in our community and it was an absolute killer. It was so
it was an absolute killer. It was so
it was an absolute killer. It was so awesome. He covered his agentic coding
awesome. He covered his agentic coding
awesome. He covered his agentic coding process focusing a lot on cloud code. He
process focusing a lot on cloud code. He
process focusing a lot on cloud code. He did a lot of things related to context
did a lot of things related to context
did a lot of things related to context engineering and he actually open sourced
engineering and he actually open sourced
engineering and he actually open sourced a lot of the resources that he shared
a lot of the resources that he shared
a lot of the resources that he shared with us in the workshop. So I'll link to
with us in the workshop. So I'll link to
with us in the workshop. So I'll link to this in the description as well. So
this in the description as well. So
this in the description as well. So credit where credit is due. Raasmus has
credit where credit is due. Raasmus has
credit where credit is due. Raasmus has inspired a lot of my ideas. And also if
inspired a lot of my ideas. And also if
inspired a lot of my ideas. And also if you want to dive a lot more into
you want to dive a lot more into
you want to dive a lot more into building AI agents using AI coding
building AI agents using AI coding
building AI agents using AI coding assistance, things like context
assistance, things like context
assistance, things like context engineering, definitely check out
engineering, definitely check out
engineering, definitely check out dynamis.ai. It is the place to be. We're
dynamis.ai. It is the place to be. We're
dynamis.ai. It is the place to be. We're constantly pushing the limit of what's
constantly pushing the limit of what's
constantly pushing the limit of what's possible with workshops like this. And
possible with workshops like this. And
possible with workshops like this. And so with that, back into my template that
so with that, back into my template that
so with that, back into my template that I have for you in the readme here, I
I have for you in the readme here, I
I have for you in the readme here, I have a quick start. You can follow along
have a quick start. You can follow along
have a quick start. You can follow along with this in just like 10 minutes and
with this in just like 10 minutes and
with this in just like 10 minutes and level up your AI coding game that fast
level up your AI coding game that fast
level up your AI coding game that fast with context engineering. But then also,
with context engineering. But then also,
with context engineering. But then also, I have this repo cloned locally. I'm
I have this repo cloned locally. I'm
I have this repo cloned locally. I'm just going to walk you through exactly
just going to walk you through exactly
just going to walk you through exactly what we're doing here. And then we'll
what we're doing here. And then we'll
what we're doing here. And then we'll see a demo in action. Now, before we
see a demo in action. Now, before we
see a demo in action. Now, before we move on, I just want to mention really
move on, I just want to mention really
move on, I just want to mention really quickly that there are definitely a lot
quickly that there are definitely a lot
quickly that there are definitely a lot of security risks when using AI coding
of security risks when using AI coding
of security risks when using AI coding assistance that are super important for
assistance that are super important for
assistance that are super important for you to keep in mind. It doesn't matter
you to keep in mind. It doesn't matter
you to keep in mind. It doesn't matter if you're using Cloud Code or Windsurf
if you're using Cloud Code or Windsurf
if you're using Cloud Code or Windsurf or something else like GitHub Copilot.
or something else like GitHub Copilot.
or something else like GitHub Copilot. These risks crop up that you might not
These risks crop up that you might not
These risks crop up that you might not even be aware of. Things like prompt
even be aware of. Things like prompt
even be aware of. Things like prompt injection, model poisoning, data
injection, model poisoning, data
injection, model poisoning, data leakage, these aren't theoretical
leakage, these aren't theoretical
leakage, these aren't theoretical threats anymore. That is why Sneak, a
threats anymore. That is why Sneak, a
threats anymore. That is why Sneak, a company that is trusted for securing AI
company that is trusted for securing AI
company that is trusted for securing AI generated code, is hosting a free live
generated code, is hosting a free live
generated code, is hosting a free live webinar Tuesday, July 15th at 11:00 a.m.
webinar Tuesday, July 15th at 11:00 a.m.
webinar Tuesday, July 15th at 11:00 a.m. Eastern time covering the OASP top 10
Eastern time covering the OASP top 10
Eastern time covering the OASP top 10 for LLMs. This is an event that you
for LLMs. This is an event that you
for LLMs. This is an event that you don't want to miss. A clear breakdown of
don't want to miss. A clear breakdown of
don't want to miss. A clear breakdown of these critical vulnerabilities. You get
these critical vulnerabilities. You get
these critical vulnerabilities. You get to see live defenses against these
to see live defenses against these
to see live defenses against these attacks like model poisoning and prompt
attacks like model poisoning and prompt
attacks like model poisoning and prompt injection and learn best practices for
injection and learn best practices for
injection and learn best practices for avoiding these security issues with AI
avoiding these security issues with AI
avoiding these security issues with AI code. Vendanna Verma from Sneak is going
code. Vendanna Verma from Sneak is going
code. Vendanna Verma from Sneak is going to be walking us through best practices
to be walking us through best practices
to be walking us through best practices for handling AI generated code and
for handling AI generated code and
for handling AI generated code and showing us real world examples that you
showing us real world examples that you
showing us real world examples that you can apply immediately. Plus, if you're
can apply immediately. Plus, if you're
can apply immediately. Plus, if you're an ISC2 member, you get one CPE credit
an ISC2 member, you get one CPE credit
an ISC2 member, you get one CPE credit just for attending. It doesn't matter
just for attending. It doesn't matter
just for attending. It doesn't matter where you're at with your technical
where you're at with your technical
where you're at with your technical ability. If you are using AI coding
ability. If you are using AI coding
ability. If you are using AI coding assistance, you have to understand these
assistance, you have to understand these
assistance, you have to understand these risks. So, I have a link in the
risks. So, I have a link in the
risks. So, I have a link in the description to register. Again, this is
description to register. Again, this is
description to register. Again, this is Tuesday, July 15th at 11:00 a.m.
Tuesday, July 15th at 11:00 a.m.
Tuesday, July 15th at 11:00 a.m. Eastern, and I'm definitely going to be
Eastern, and I'm definitely going to be
Eastern, and I'm definitely going to be there myself. So I have the repo cloned
there myself. So I have the repo cloned
there myself. So I have the repo cloned locally. Now let's dive into creating a
locally. Now let's dive into creating a
locally. Now let's dive into creating a super comprehensive plan for a new
super comprehensive plan for a new
super comprehensive plan for a new project and implementing it end to end
project and implementing it end to end
project and implementing it end to end with cloud code. And like I said,
with cloud code. And like I said,
with cloud code. And like I said, context engineering can be decently
context engineering can be decently
context engineering can be decently involved up front. So there are quite a
involved up front. So there are quite a
involved up front. So there are quite a few different files that I want to cover
few different files that I want to cover
few different files that I want to cover here. Markdown files for all the
here. Markdown files for all the
here. Markdown files for all the instructions, the different parts of our
instructions, the different parts of our
instructions, the different parts of our context. And so the first file that I
context. And so the first file that I
context. And so the first file that I want to cover is our claude.md.
want to cover is our claude.md.
want to cover is our claude.md. These are the global rules for our AI
These are the global rules for our AI
These are the global rules for our AI coding assistant. similar to, you know,
coding assistant. similar to, you know,
coding assistant. similar to, you know, winds surf rules or cursor rules if
winds surf rules or cursor rules if
winds surf rules or cursor rules if you've used those AI idees before. This
you've used those AI idees before. This
you've used those AI idees before. This is the highest level information that we
is the highest level information that we
is the highest level information that we want to give to our AI coding assistant.
want to give to our AI coding assistant.
want to give to our AI coding assistant. Things like best practices that we want
Things like best practices that we want
Things like best practices that we want it to follow, the way that we want it to
it to follow, the way that we want it to
it to follow, the way that we want it to write tests for our project, um the way
write tests for our project, um the way
write tests for our project, um the way that we want it to manage tasks, the
that we want it to manage tasks, the
that we want it to manage tasks, the style and convention guides, like all of
style and convention guides, like all of
style and convention guides, like all of this highle information we want to put
this highle information we want to put
this highle information we want to put in claw.md.
in claw.md.
in claw.md. And then going back to the readme here,
And then going back to the readme here,
And then going back to the readme here, the next file that I want to cover is
the next file that I want to cover is
the next file that I want to cover is our initial MD. This is where we
our initial MD. This is where we
our initial MD. This is where we describe the feature that we wanted to
describe the feature that we wanted to
describe the feature that we wanted to implement as it kicks off the project
implement as it kicks off the project
implement as it kicks off the project for us. And so going into this, I very
for us. And so going into this, I very
for us. And so going into this, I very much have it as a template for you. It's
much have it as a template for you. It's
much have it as a template for you. It's just a few different sections for you to
just a few different sections for you to
just a few different sections for you to fill out. So first, you want to describe
fill out. So first, you want to describe
fill out. So first, you want to describe at a high level the feature that you
at a high level the feature that you
at a high level the feature that you want implemented by cloud code or your
want implemented by cloud code or your
want implemented by cloud code or your AI coding assistant. So something like I
AI coding assistant. So something like I
AI coding assistant. So something like I want to build an AI agent that does ABC
want to build an AI agent that does ABC
want to build an AI agent that does ABC built with XYZ. And it's worth being
built with XYZ. And it's worth being
built with XYZ. And it's worth being pretty detailed in this section. And
pretty detailed in this section. And
pretty detailed in this section. And then second, it's so so important
then second, it's so so important
then second, it's so so important whenever you can provide examples to the
whenever you can provide examples to the
whenever you can provide examples to the AI coding assistant. This just helps so
AI coding assistant. This just helps so
AI coding assistant. This just helps so much. And so this could be from past
much. And so this could be from past
much. And so this could be from past projects that you've worked on that have
projects that you've worked on that have
projects that you've worked on that have some similar implementations for what
some similar implementations for what
some similar implementations for what you want to build now. It could be code
you want to build now. It could be code
you want to build now. It could be code examples or snippets that you found
examples or snippets that you found
examples or snippets that you found online. You just want to put that in
online. You just want to put that in
online. You just want to put that in this examples folder. And so I have this
this examples folder. And so I have this
this examples folder. And so I have this in the repo specifically to call out
in the repo specifically to call out
in the repo specifically to call out like this is your place to add examples
like this is your place to add examples
like this is your place to add examples for your AI coding assistant. And then
for your AI coding assistant. And then
for your AI coding assistant. And then also getting into the rag part of
also getting into the rag part of
also getting into the rag part of context engineering, we have
context engineering, we have
context engineering, we have documentation. So listing out any online
documentation. So listing out any online
documentation. So listing out any online docs that you want the AI coding
docs that you want the AI coding
docs that you want the AI coding assistant to reference or any MCP
assistant to reference or any MCP
assistant to reference or any MCP servers for rag that you wanted to use
servers for rag that you wanted to use
servers for rag that you wanted to use like my crawl for AAI rag for example.
like my crawl for AAI rag for example.
like my crawl for AAI rag for example. I'm not going to be focusing on this too
I'm not going to be focusing on this too
I'm not going to be focusing on this too much right now, but it still is a very
much right now, but it still is a very
much right now, but it still is a very crucial part of context engineering. And
crucial part of context engineering. And
crucial part of context engineering. And then last but not least, a place for any
then last but not least, a place for any
then last but not least, a place for any other kinds of considerations that you
other kinds of considerations that you
other kinds of considerations that you have for your AI coding assistant. And
have for your AI coding assistant. And
have for your AI coding assistant. And this is a really good place to include
this is a really good place to include
this is a really good place to include any gotchas, things that AI coding
any gotchas, things that AI coding
any gotchas, things that AI coding assistants mess up on a lot in your
assistants mess up on a lot in your
assistants mess up on a lot in your experience, just specifying how to avoid
experience, just specifying how to avoid
experience, just specifying how to avoid that right here. And so what I'm going
that right here. And so what I'm going
that right here. And so what I'm going to do for this build, because I am going
to do for this build, because I am going
to do for this build, because I am going to show you a full example here, is I'm
to show you a full example here, is I'm
to show you a full example here, is I'm actually going to delete initial.md and
actually going to delete initial.md and
actually going to delete initial.md and I'm going to rename the example that I
I'm going to rename the example that I
I'm going to rename the example that I have in the repo because we're going to
have in the repo because we're going to
have in the repo because we're going to use this to build out an AI agent here.
use this to build out an AI agent here.
use this to build out an AI agent here. And so going to initial.md, I'm building
And so going to initial.md, I'm building
And so going to initial.md, I'm building an AI agent with pideantic AI. I have
an AI agent with pideantic AI. I have
an AI agent with pideantic AI. I have some examples that I'll add into the
some examples that I'll add into the
some examples that I'll add into the folder off camera. For the
folder off camera. For the
folder off camera. For the documentation, I'm just going to have it
documentation, I'm just going to have it
documentation, I'm just going to have it reference Pantic AI. And usually I'd
reference Pantic AI. And usually I'd
reference Pantic AI. And usually I'd want to use an MCP server for rag, but
want to use an MCP server for rag, but
want to use an MCP server for rag, but I'm just keeping it simple here. Um, and
I'm just keeping it simple here. Um, and
I'm just keeping it simple here. Um, and then just for some other considerations
then just for some other considerations
then just for some other considerations here, some things that I haven't messed
here, some things that I haven't messed
here, some things that I haven't messed up on quite a bit is the use of
up on quite a bit is the use of
up on quite a bit is the use of environment variables. I'm telling it to
environment variables. I'm telling it to
environment variables. I'm telling it to make sure that it has a project
make sure that it has a project
make sure that it has a project structure in a readme. So, just little
structure in a readme. So, just little
structure in a readme. So, just little things like that. Just a couple of
things like that. Just a couple of
things like that. Just a couple of examples that I wanted to give here. So,
examples that I wanted to give here. So,
examples that I wanted to give here. So, that is my initial MD. And so now going
that is my initial MD. And so now going
that is my initial MD. And so now going back to the readme, we have our global
back to the readme, we have our global
back to the readme, we have our global rule set up. We have our initial prompt.
rule set up. We have our initial prompt.
rule set up. We have our initial prompt. Now it is time to generate a full plan
Now it is time to generate a full plan
Now it is time to generate a full plan for our implementation. And this is
for our implementation. And this is
for our implementation. And this is where we get into two of my favorite
where we get into two of my favorite
where we get into two of my favorite things for context engineering. Cloud
things for context engineering. Cloud
things for context engineering. Cloud code/comands and PRPS, which is short
code/comands and PRPS, which is short
code/comands and PRPS, which is short for product requirements prompts. And so
for product requirements prompts. And so
for product requirements prompts. And so they're similar to product requirements
they're similar to product requirements
they're similar to product requirements documents, PRDs. You've probably heard
documents, PRDs. You've probably heard
documents, PRDs. You've probably heard of this before if you've been diving
of this before if you've been diving
of this before if you've been diving into AI coding, but they are
into AI coding, but they are
into AI coding, but they are specifically designed to instruct an AI
specifically designed to instruct an AI
specifically designed to instruct an AI coding assistant. So, we're not creating
coding assistant. So, we're not creating
coding assistant. So, we're not creating like an architecture document. We're
like an architecture document. We're
like an architecture document. We're actually creating a prompt that we're
actually creating a prompt that we're
actually creating a prompt that we're going to run with cloud code. So, we use
going to run with cloud code. So, we use
going to run with cloud code. So, we use cloud code to build a prompt which is
cloud code to build a prompt which is
cloud code to build a prompt which is part of the project plan and then we use
part of the project plan and then we use
part of the project plan and then we use that to actually do the implementation
that to actually do the implementation
that to actually do the implementation end to end. It's so so powerful and
end to end. It's so so powerful and
end to end. It's so so powerful and we're using slash commands to take care
we're using slash commands to take care
we're using slash commands to take care of this. So we don't have to prompt a
of this. So we don't have to prompt a
of this. So we don't have to prompt a lot of things from scratch every time
lot of things from scratch every time
lot of things from scratch every time we're using this process to begin a
we're using this process to begin a
we're using this process to begin a project. And so in thecloud folder, if
project. And so in thecloud folder, if
project. And so in thecloud folder, if you have a folder called commands, any
you have a folder called commands, any
you have a folder called commands, any of the markdown files that you have here
of the markdown files that you have here
of the markdown files that you have here can be executed as custom commands for
can be executed as custom commands for
can be executed as custom commands for cloud code. It is a beautiful thing. And
cloud code. It is a beautiful thing. And
cloud code. It is a beautiful thing. And so our first command here is generate
so our first command here is generate
so our first command here is generate PRP. This is a prompt to create a very
PRP. This is a prompt to create a very
PRP. This is a prompt to create a very comprehensive plan as another prompt for
comprehensive plan as another prompt for
comprehensive plan as another prompt for cloud code. So there's a multi-step
cloud code. So there's a multi-step
cloud code. So there's a multi-step process here. We're getting a little bit
process here. We're getting a little bit
process here. We're getting a little bit more involved here now with context
more involved here now with context
more involved here now with context engineering. And so I'm not going to go
engineering. And so I'm not going to go
engineering. And so I'm not going to go through the details of this entire
through the details of this entire
through the details of this entire document, but we're walking it through
document, but we're walking it through
document, but we're walking it through what it looks like to take in a feature
what it looks like to take in a feature
what it looks like to take in a feature requirements. We're going to actually
requirements. We're going to actually
requirements. We're going to actually pass in initial MD and then do a bunch
pass in initial MD and then do a bunch
pass in initial MD and then do a bunch of research on our behalf, some
of research on our behalf, some
of research on our behalf, some architectural planning. We're having it
architectural planning. We're having it
architectural planning. We're having it really think through the problem step by
really think through the problem step by
really think through the problem step by step here to create a comprehensive plan
step here to create a comprehensive plan
step here to create a comprehensive plan for implementation. This is the
for implementation. This is the
for implementation. This is the engineered context that I'm really
engineered context that I'm really
engineered context that I'm really getting at with context engineering. And
getting at with context engineering. And
getting at with context engineering. And so the way this works and I'm going to
so the way this works and I'm going to
so the way this works and I'm going to go into my terminal here and I'm going
go into my terminal here and I'm going
go into my terminal here and I'm going to open up claude. When we have our
to open up claude. When we have our
to open up claude. When we have our commands within the commands folder now,
commands within the commands folder now,
commands within the commands folder now, I can do slashgenerate PRP and then the
I can do slashgenerate PRP and then the
I can do slashgenerate PRP and then the argument that I want to pass in here.
argument that I want to pass in here.
argument that I want to pass in here. This is just anything that I enter after
This is just anything that I enter after
This is just anything that I enter after a space. This is what's going to be
a space. This is what's going to be
a space. This is what's going to be given and it's going to replace the
given and it's going to replace the
given and it's going to replace the arguments placeholder here. So if I say
arguments placeholder here. So if I say
arguments placeholder here. So if I say initial.m
initial.m
initial.m MD, I'm now telling this command that
MD, I'm now telling this command that
MD, I'm now telling this command that the feature file is going to be
the feature file is going to be
the feature file is going to be initial.md. So now cloud code is going
initial.md. So now cloud code is going
initial.md. So now cloud code is going to look at initial.m MD, use that to
to look at initial.m MD, use that to
to look at initial.m MD, use that to guide the feature that it is then going
guide the feature that it is then going
guide the feature that it is then going to plan. So I'm going to go ahead and
to plan. So I'm going to go ahead and
to plan. So I'm going to go ahead and run this right now. And this will take a
run this right now. And this will take a
run this right now. And this will take a good amount of time because cloud code
good amount of time because cloud code
good amount of time because cloud code really goes through this in a
really goes through this in a
really goes through this in a comprehensive way, making sure that it
comprehensive way, making sure that it
comprehensive way, making sure that it generates a complete PRP for us. And by
generates a complete PRP for us. And by
generates a complete PRP for us. And by the way, it is also using a PRP template
the way, it is also using a PRP template
the way, it is also using a PRP template that I have available in the PRPS
that I have available in the PRPS
that I have available in the PRPS folder. So this is kind of its starting
folder. So this is kind of its starting
folder. So this is kind of its starting point. This is the template that it
point. This is the template that it
point. This is the template that it bases the whole document off of that it
bases the whole document off of that it
bases the whole document off of that it produces after we are done with this
produces after we are done with this
produces after we are done with this command. And so I'm going to pause and
command. And so I'm going to pause and
command. And so I'm going to pause and come back once it's generated the PRP.
come back once it's generated the PRP.
come back once it's generated the PRP. Then we'll take a look at what that
Then we'll take a look at what that
Then we'll take a look at what that looks like and use it to build our
looks like and use it to build our
looks like and use it to build our project. All right. So I'm coming back
project. All right. So I'm coming back
project. All right. So I'm coming back just for a second here to show you the
just for a second here to show you the
just for a second here to show you the process in action. The thing that I love
process in action. The thing that I love
process in action. The thing that I love about using PRPs and just context
about using PRPs and just context
about using PRPs and just context engineering in general is watching these
engineering in general is watching these
engineering in general is watching these relatively large to-do lists that it
relatively large to-do lists that it
relatively large to-do lists that it builds autonomously and knocks out one
builds autonomously and knocks out one
builds autonomously and knocks out one at a time. And so what it's doing is
at a time. And so what it's doing is
at a time. And so what it's doing is researching different APIs on my behalf
researching different APIs on my behalf
researching different APIs on my behalf to really make sure that the PRP we
to really make sure that the PRP we
to really make sure that the PRP we generate for implementation has all the
generate for implementation has all the
generate for implementation has all the details necessary to not hallucinate the
details necessary to not hallucinate the
details necessary to not hallucinate the usage of APIs. And that's one of the
usage of APIs. And that's one of the
usage of APIs. And that's one of the biggest things that AI coding assistants
biggest things that AI coding assistants
biggest things that AI coding assistants mess up on a lot. And so it's doing
mess up on a lot. And so it's doing
mess up on a lot. And so it's doing research, analyzing the existing
research, analyzing the existing
research, analyzing the existing codebase and then the examples that
codebase and then the examples that
codebase and then the examples that we're giving it, reviewing
we're giving it, reviewing
we're giving it, reviewing documentation, pantic AI, creating the
documentation, pantic AI, creating the
documentation, pantic AI, creating the PRP based on that, writing it all, and
PRP based on that, writing it all, and
PRP based on that, writing it all, and then it is done. There's so much that
then it is done. There's so much that
then it is done. There's so much that it's taking care of here. Not just
it's taking care of here. Not just
it's taking care of here. Not just creating one markdown file, but all of
creating one markdown file, but all of
creating one markdown file, but all of the research and planning that it does
the research and planning that it does
the research and planning that it does beforehand. And so yeah, now I will come
beforehand. And so yeah, now I will come
beforehand. And so yeah, now I will come back once it is complete. And there we
back once it is complete. And there we
back once it is complete. And there we go. Our PRP has now been implemented.
go. Our PRP has now been implemented.
go. Our PRP has now been implemented. It's in research emailagent.mmd in the
It's in research emailagent.mmd in the
It's in research emailagent.mmd in the PRPS folder. So it gives us a summary of
PRPS folder. So it gives us a summary of
PRPS folder. So it gives us a summary of its research and analysis, some things
its research and analysis, some things
its research and analysis, some things it did for the environment setup to get
it did for the environment setup to get
it did for the environment setup to get things ready to implement the project,
things ready to implement the project,
things ready to implement the project, and then it describes the content at a
and then it describes the content at a
and then it describes the content at a high level. And so I definitely don't
high level. And so I definitely don't
high level. And so I definitely don't want to dive in and explain everything
want to dive in and explain everything
want to dive in and explain everything that it creates here. And this is like
that it creates here. And this is like
that it creates here. And this is like brand new for me too. Um, but just going
brand new for me too. Um, but just going
brand new for me too. Um, but just going through this, it describes core
through this, it describes core
through this, it describes core principles, the primary goal for this
principles, the primary goal for this
principles, the primary goal for this project, and success criteria. A lot of
project, and success criteria. A lot of
project, and success criteria. A lot of specifics here that make a huge
specifics here that make a huge
specifics here that make a huge difference. And a lot of this is based
difference. And a lot of this is based
difference. And a lot of this is based off of the PRP base template that I uh
off of the PRP base template that I uh
off of the PRP base template that I uh used from Raasmus. And then talks about
used from Raasmus. And then talks about
used from Raasmus. And then talks about all the different documentation
all the different documentation
all the different documentation referencing both websites and things
referencing both websites and things
referencing both websites and things that I have in the examples folder that
that I have in the examples folder that
that I have in the examples folder that I included off camera like I said I
I included off camera like I said I
I included off camera like I said I would do. And man, this is just so
would do. And man, this is just so
would do. And man, this is just so powerful because now that we list these
powerful because now that we list these
powerful because now that we list these things and we instruct it in the PRP to
things and we instruct it in the PRP to
things and we instruct it in the PRP to look at each of these files and
look at each of these files and
look at each of these files and websites, we're going to have that all
websites, we're going to have that all
websites, we're going to have that all in the context as it's coding
in the context as it's coding
in the context as it's coding everything. And that's going to reduce
everything. And that's going to reduce
everything. And that's going to reduce hallucinations a lot. Even just this
hallucinations a lot. Even just this
hallucinations a lot. Even just this part alone is so powerful. And then
part alone is so powerful. And then
part alone is so powerful. And then another thing that I really like is we
another thing that I really like is we
another thing that I really like is we describe the current code base, what it
describe the current code base, what it
describe the current code base, what it looks like right now, and then our
looks like right now, and then our
looks like right now, and then our desired code bases. So we're laying out
desired code bases. So we're laying out
desired code bases. So we're laying out every single file that we want to have
every single file that we want to have
every single file that we want to have created ahead of time. And we're still
created ahead of time. And we're still
created ahead of time. And we're still flexible enough where like it can change
flexible enough where like it can change
flexible enough where like it can change the structure if it deems that worth
the structure if it deems that worth
the structure if it deems that worth doing in the middle of implementing. But
doing in the middle of implementing. But
doing in the middle of implementing. But yeah, this just shows the kind of
yeah, this just shows the kind of
yeah, this just shows the kind of architecture planning that we're doing
architecture planning that we're doing
architecture planning that we're doing ahead of time. It's so powerful. And so
ahead of time. It's so powerful. And so
ahead of time. It's so powerful. And so with that, going back to the readme
with that, going back to the readme
with that, going back to the readme here, there's really just one last step
here, there's really just one last step
here, there's really just one last step that I want to show you. We've already
that I want to show you. We've already
that I want to show you. We've already did a lot of context engineering. This
did a lot of context engineering. This
did a lot of context engineering. This PRP, this is the pinnacle of context
PRP, this is the pinnacle of context
PRP, this is the pinnacle of context engineering, at least what I want to
engineering, at least what I want to
engineering, at least what I want to introduce you to right now. And so going
introduce you to right now. And so going
introduce you to right now. And so going back to the readme, if I go down to the
back to the readme, if I go down to the
back to the readme, if I go down to the bottom, now that we have the command run
bottom, now that we have the command run
bottom, now that we have the command run for generate PRP, now we just want to
for generate PRP, now we just want to
for generate PRP, now we just want to execute the PRP. It's very, very simple.
execute the PRP. It's very, very simple.
execute the PRP. It's very, very simple. There's not much that we have to type
There's not much that we have to type
There's not much that we have to type within cloud code itself because we are
within cloud code itself because we are
within cloud code itself because we are doing all the planning in these markdown
doing all the planning in these markdown
doing all the planning in these markdown files. We have our initial planning and
files. We have our initial planning and
files. We have our initial planning and initial MD. We're generating a PRP with
initial MD. We're generating a PRP with
initial MD. We're generating a PRP with this command and then executing it with
this command and then executing it with
this command and then executing it with this one. And all the prompting just
this one. And all the prompting just
this one. And all the prompting just lives in those files. And so now I can
lives in those files. And so now I can
lives in those files. And so now I can literally do slashexecute PRP and then
literally do slashexecute PRP and then
literally do slashexecute PRP and then if I open up my full terminal here, then
if I open up my full terminal here, then
if I open up my full terminal here, then what I can do is reference PRPS slash
what I can do is reference PRPS slash
what I can do is reference PRPS slash and then research email agent.m MD. So
and then research email agent.m MD. So
and then research email agent.m MD. So just calling out where that exists in my
just calling out where that exists in my
just calling out where that exists in my codebase. And then I'll send that in and
codebase. And then I'll send that in and
codebase. And then I'll send that in and it's going to go ahead and create
it's going to go ahead and create
it's going to go ahead and create another decently long task list. This is
another decently long task list. This is
another decently long task list. This is going to be very very end to end. And so
going to be very very end to end. And so
going to be very very end to end. And so I'm going to pause in a second and come
I'm going to pause in a second and come
I'm going to pause in a second and come back once it is done implementing. But
back once it is done implementing. But
back once it is done implementing. But I'll show a screenshot right here of the
I'll show a screenshot right here of the
I'll show a screenshot right here of the task list that it creates. It's very
task list that it creates. It's very
task list that it creates. It's very very comprehensive. That's the goal that
very comprehensive. That's the goal that
very comprehensive. That's the goal that we have with this. It's so cool how
we have with this. It's so cool how
we have with this. It's so cool how agentic our AI coding assistance can be
agentic our AI coding assistance can be
agentic our AI coding assistance can be when we give it the right context and
when we give it the right context and
when we give it the right context and how much we can reduce hallucinations as
how much we can reduce hallucinations as
how much we can reduce hallucinations as well. And so I will come back once we
well. And so I will come back once we
well. And so I will come back once we have the first version of our agent
have the first version of our agent
have the first version of our agent created. And there we go. After more
created. And there we go. After more
created. And there we go. After more than 30 minutes, Claude code has
than 30 minutes, Claude code has
than 30 minutes, Claude code has completed and tested our agent end to
completed and tested our agent end to
completed and tested our agent end to end. That is the power of agent coding
end. That is the power of agent coding
end. That is the power of agent coding with cloud code and context engineering.
with cloud code and context engineering.
with cloud code and context engineering. And it did take quite a few tokens to do
And it did take quite a few tokens to do
And it did take quite a few tokens to do this to say the least. So I'll have a
this to say the least. So I'll have a
this to say the least. So I'll have a screenshot right here of the token usage
screenshot right here of the token usage
screenshot right here of the token usage in the middle of the development towards
in the middle of the development towards
in the middle of the development towards the end. But I'm not bringing my own API
the end. But I'm not bringing my own API
the end. But I'm not bringing my own API key. I'm taking advantage of the max
key. I'm taking advantage of the max
key. I'm taking advantage of the max plan for Claude. And so I didn't have to
plan for Claude. And so I didn't have to
plan for Claude. And so I didn't have to pay anything more for it to do all this
pay anything more for it to do all this
pay anything more for it to do all this work for me. It is a beautiful thing.
work for me. It is a beautiful thing.
work for me. It is a beautiful thing. And so yeah, this is the output here at
And so yeah, this is the output here at
And so yeah, this is the output here at the end describing what it did for us.
the end describing what it did for us.
the end describing what it did for us. There is one bit of iterating that I had
There is one bit of iterating that I had
There is one bit of iterating that I had to do here. There's some weirdness for
to do here. There's some weirdness for
to do here. There's some weirdness for how the tools were set up for the agent.
how the tools were set up for the agent.
how the tools were set up for the agent. like it was creating these functions as
like it was creating these functions as
like it was creating these functions as dependencies for the agent which isn't
dependencies for the agent which isn't
dependencies for the agent which isn't really how you're supposed to do it with
really how you're supposed to do it with
really how you're supposed to do it with padantic AI. So I did one round of
padantic AI. So I did one round of
padantic AI. So I did one round of iterating but that was it and everything
iterating but that was it and everything
iterating but that was it and everything is working really really well. And so I
is working really really well. And so I
is working really really well. And so I do like I just did I highly recommend
do like I just did I highly recommend
do like I just did I highly recommend not vive coding actually validating the
not vive coding actually validating the
not vive coding actually validating the output but if you validate the output
output but if you validate the output
output but if you validate the output have your context engineering set up you
have your context engineering set up you
have your context engineering set up you are set. And so yeah we can go into the
are set. And so yeah we can go into the
are set. And so yeah we can go into the terminal here. I can run pi test. So we
terminal here. I can run pi test. So we
terminal here. I can run pi test. So we can see all of the tests that it created
can see all of the tests that it created
can see all of the tests that it created and used to iterate on our agent.
and used to iterate on our agent.
and used to iterate on our agent. Everything is passing. Just a couple of
Everything is passing. Just a couple of
Everything is passing. Just a couple of warnings that we can ignore. And then
warnings that we can ignore. And then
warnings that we can ignore. And then also we can run our CLI. So, I followed
also we can run our CLI. So, I followed
also we can run our CLI. So, I followed the instructions that it created in the
the instructions that it created in the
the instructions that it created in the readme for me to set things up and I
readme for me to set things up and I
readme for me to set things up and I implemented my environment variables.
implemented my environment variables.
implemented my environment variables. And so, now I can run Python CLI.py.
And so, now I can run Python CLI.py.
And so, now I can run Python CLI.py. We're connected to our agent running
We're connected to our agent running
We're connected to our agent running GBT4.1 Mini for our model. And you could
GBT4.1 Mini for our model. And you could
GBT4.1 Mini for our model. And you could really use any model that you want.
really use any model that you want.
really use any model that you want. Actually, one of the things that I had
Actually, one of the things that I had
Actually, one of the things that I had in my examples was showing how to make
in my examples was showing how to make
in my examples was showing how to make it so you can set up different providers
it so you can set up different providers
it so you can set up different providers for your podantic AI agent like Gemini
for your podantic AI agent like Gemini
for your podantic AI agent like Gemini or Olama or OpenAI. So, we can actually
or Olama or OpenAI. So, we can actually
or Olama or OpenAI. So, we can actually do that as well. It's really cool. And
do that as well. It's really cool. And
do that as well. It's really cool. And so, within here, I can just say hello.
so, within here, I can just say hello.
so, within here, I can just say hello. We can test a basic message to our
We can test a basic message to our
We can test a basic message to our agent. Looking really good. We got our
agent. Looking really good. We got our
agent. Looking really good. We got our output here. Our terminal is looking
output here. Our terminal is looking
output here. Our terminal is looking really beautiful. And I can say
really beautiful. And I can say
really beautiful. And I can say something like search the web for the
something like search the web for the
something like search the web for the latest
latest
latest on clawed code. So we can have it use
on clawed code. So we can have it use
on clawed code. So we can have it use the web search tool because that's our
the web search tool because that's our
the web search tool because that's our research agent. I'm not going to test
research agent. I'm not going to test
research agent. I'm not going to test this out a ton right here. I'm just
this out a ton right here. I'm just
this out a ton right here. I'm just showing you right now that like
showing you right now that like
showing you right now that like everything is working. We're using the
everything is working. We're using the
everything is working. We're using the Brave API. We're using the OpenAI API.
Brave API. We're using the OpenAI API.
Brave API. We're using the OpenAI API. We got some results here. It's going to
We got some results here. It's going to
We got some results here. It's going to spit out a response for us in a second.
spit out a response for us in a second.
spit out a response for us in a second. It's just doing a lot of web searching
It's just doing a lot of web searching
It's just doing a lot of web searching for us, I guess. And there we go. All
for us, I guess. And there we go. All
for us, I guess. And there we go. All right, we got our response from our
right, we got our response from our
right, we got our response from our agent. So, this is working really,
agent. So, this is working really,
agent. So, this is working really, really well. Like I said, I just had to
really well. Like I said, I just had to
really well. Like I said, I just had to iterate once. So, I just kicked off this
iterate once. So, I just kicked off this
iterate once. So, I just kicked off this build and I set up all the permissions
build and I set up all the permissions
build and I set up all the permissions ahead of time. So, I just went and, you
ahead of time. So, I just went and, you
ahead of time. So, I just went and, you know, took my dog on a walk, came back,
know, took my dog on a walk, came back,
know, took my dog on a walk, came back, and the agent was it done. And that's
and the agent was it done. And that's
and the agent was it done. And that's what I'm showing you guys right here.
what I'm showing you guys right here.
what I'm showing you guys right here. So, really, really cool. That is the
So, really, really cool. That is the
So, really, really cool. That is the power of context engineering. And this
power of context engineering. And this
power of context engineering. And this is just getting your feet wet. I very
is just getting your feet wet. I very
is just getting your feet wet. I very much encourage you to use this template
much encourage you to use this template
much encourage you to use this template that I have for you. dive into creating
that I have for you. dive into creating
that I have for you. dive into creating these comprehensive plans and using them
these comprehensive plans and using them
these comprehensive plans and using them with an AI coding assistant like cloud
with an AI coding assistant like cloud
with an AI coding assistant like cloud code and then just take it from there.
code and then just take it from there.
code and then just take it from there. There's so much more you can do with
There's so much more you can do with
There's so much more you can do with context engineering with memory and
context engineering with memory and
context engineering with memory and state and rag a lot of things that I
state and rag a lot of things that I
state and rag a lot of things that I want to cover soon on my channel as
want to cover soon on my channel as
want to cover soon on my channel as well. So you can really go down the
well. So you can really go down the
well. So you can really go down the rabbit hole of context engineering and
rabbit hole of context engineering and
rabbit hole of context engineering and like we talked about at the start of
like we talked about at the start of
like we talked about at the start of this video it is really the thing to
this video it is really the thing to
this video it is really the thing to focus on right now and so dive deep have
focus on right now and so dive deep have
focus on right now and so dive deep have fun with it. I hope this helps as a
fun with it. I hope this helps as a
fun with it. I hope this helps as a starting point for you as well. And so
starting point for you as well. And so
starting point for you as well. And so if you appreciated this video and you're
if you appreciated this video and you're
if you appreciated this video and you're looking forward to more things AI
looking forward to more things AI
looking forward to more things AI coding, AI agents, and context
coding, AI agents, and context
coding, AI agents, and context engineering, definitely give me a like
engineering, definitely give me a like
engineering, definitely give me a like and a subscribe. And with that, I will
and a subscribe. And with that, I will
and a subscribe. And with that, I will see you in the next
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.
Works with YouTube, Coursera, Udemy and more educational platforms
Get Instant Transcripts: Just Edit the Domain in Your Address Bar!
YouTube
←
→
↻
https://www.youtube.com/watch?v=UF8uR6Z6KLc
YoutubeToText
←
→
↻
https://youtubetotext.net/watch?v=UF8uR6Z6KLc