Agentic Engineering Is About Harnesses, Not Just Models

Watch Source Video

Context

Kristijan shared a YouTube interview from David Ondrej titled “Why This Dev Ships 100x Faster Than 99% of Engineers”. The video is a 54-minute discussion with a senior developer who says AI now writes most of his production code. The useful part for WS is not the speed claim by itself, but the workflow behind it: agents work best when they are inside good harnesses, connected to the source code, and followed by review loops.

Summary

The interview frames “agentic engineering” as the move from typing prompts into a chatbot toward running specialized coding harnesses. The guest argues that the model still matters, but the surrounding harness matters just as much: tools, repository access, system prompts, local instructions, and the ability to inspect and edit the codebase. He describes using Cursor and high-end coding models for most implementation work, while relying on source-aware context instead of hand-written prompt documents whenever possible.

A central lesson is that agents should use code as the source of truth. Rather than copying docs into prompts, the guest points to tools that fetch open-source repositories into the working tree so agents can inspect real implementation details. That gives the agent concrete examples of APIs, architecture, and patterns, and it reduces hallucinated integration advice.

The workflow also emphasizes reusable skills and review loops. Skills are used to keep agents from rewriting existing functions or flattening architecture, while automated review tools such as Greptile-style loops check generated code repeatedly until confidence improves. The developer still owns the outcome, but spends more time steering, reviewing, and composing systems than typing every line.

Extracted Knowledge and AI Review

For WS, the practical takeaway is to evaluate AI coding setups as full systems, not model names. A strong internal agent workflow needs: repository-aware context, clear local instructions, reusable skills for project conventions, a way to run multiple agents safely, and a review loop that catches architectural drift before code lands.

This maps directly to OpenClaw and WS Daily work. If the agency wants faster delivery, the durable asset is not one prompt or one model subscription; it is a repeatable harness around each workflow. That includes project-specific AGENTS.md guidance, source fetchers, test commands, deployment checks, and a clear rule for when the human reviews before external action.

A useful next pattern for WS could be build_agent_harness_for_project: identify the repo’s source of truth, add project-specific instructions, list safe commands, define review gates, and teach agents how to reuse existing service layers instead of inventing new ones.

AI Research Notes

The video’s strongest point is operational: productivity gains come from better agent environments, not from treating the model as a magic chat box. The weaker point is the headline speed claim, which should not be copied as a metric without evidence. For agency use, the safe interpretation is: agents can compress implementation time when the harness gives them reliable context and when review loops keep quality visible.

Transcript

Agentic engineering is the future. In
2026, the people who ship 100x faster
aren't typing prompts into a chatbot.
They're running multiple agent harnesses
in parallel. So, I had Mickey on the
podcast, a senior developer who has AI
write 95% of his code to walk through
his exact AI stack, the tools, the
models, the loops. This is the David
Andre podcast. Enjoy. Right, Mickey, how
do you think about building with AI in
2026? Yeah, it's quite changed since the
last time we talked. It's no longer
vibes, like we got to be serious with
this stuff, but at the same time, I'll
be honest, like I think I would say in
the last 3 months, all the code that
I've created, I'd say 95% was generated
by AI. And you're an actual developer,
right? So, Yeah, yeah, like I'm an
actual engineer developer, like and like
there's a part of me that misses writing
code for fun. I'll do it every now and
then in the weekends, but like I think
you'd be foolish to not see where we're
going. Yeah. The models are not perfect.
They're at a point where like there are
productivity gains, especially if you
understand the vertical that you're in.
So, any of the version of applications
people are building, a little bit of
brains and AI will take you a long way.
So, I'm going to share like the tools I
use in my workflow, and I think anybody
else can do this. It's super
replicatable. I'm actually going to give
the exact tools, and it's also going to
feel like Karpathy's like auto research
loop. So, I think it'll be fun. Awesome.
Let's jump into it. First is harness. I
chase the model, right? I think the
model is the more important thing, but I
use Cursor, and right now I'm using GPT
5.5. Interesting. Okay, so that's funny.
I'm using Opus 4.7 Max fast inside of
Cursor, but also inside of Cursor Agent.
Here's actually a big difference a lot
of people don't know. There have been
benchmarks, right? And like these are
like benchmarks done by like actual
developers, where Cursor performs both
Claude Code and Codex for their models,
right? So,
>> crazy. a lot of people have been dunking
on Opus 4.5 saying Opus 4.5 is terrible.
Some people on Twitter call it Slopus.
It's still a good model, especially when
it comes to UI changes. So, I will
preface there, whenever I do anything UI
or front end otherwise, I will use Opus
4.7, but I'm using it max. I have no
time for any other variant. But the
harness matters. Now, a lot of people
are priced out of Cursor cuz Cursor
doesn't subsidize the way Codex and
Claude does. Cursor, in my opinion, is
the best harness. I can switch between
models. Their new agentic view is
pretty, pretty nice. So, I guess let's
touch on the harness, right? Because a
lot of people say Word has become more
popular now in in the last two, three
months. Obviously, it's been around for
longer, but
>> of people it's their first time hearing
this, really, and they don't really
understand fully. So, you have the
model, what is the harness, right? It's
everything around it.
>> So, believe it or not, the model itself
can't do anything. The model is just a
predictor of next text. Technically, the
model doesn't even think. Whatever
English you give it, it converts it to
tokens. Those tokens are mapped on a
graph. And then what it does is it looks
at that graph and it predicts the next
token. Some cool mathematics happens
there, and then it returns a token to
you, which is converted to English. So,
the model doesn't think. The model
doesn't do. The model just predicts the
next text. What a harness does, you can
think of a harness as a wrapper of a
model, and this wrapper is APIs, tools,
a specific system prompt, markdown files
like agent.md files. These are all
things that wrap the model that guide it
to perform or specialize in a specific
action.
>> Real quick, if you want everything
mentioned in this video completely for
free, click the first link below the
video and I will email you all the
skills, all the repos, all the tools
mentioned in this podcast. Again, it's
completely for free. So, go below the
video and grab it now. Now, the main
important thing with the Cursors and the
Claude code and the Codex is the tools
it gives it. Whenever you use Cursor or
any sort of agent, you notice in the
trace and the response it gives you, it
says, "Oh, it read this file. It
searched this thing," right? Those are
tool calls that it's making. Again, the
agent doesn't have the ability to do so,
but the harness gives it the tool so
that the agent can do this. The models
have got to a point where an investment
in a really good harness will maximize
the output you get from the model. And
we know this because people's experience
with Claude code and cursor is not the
same. Yeah, as long as people use the
best model available. And that's the
thing, right? The model does matter. Um
I will GPT 5.5 extra high, especially I
work mainly on large code bases, so I
may be in that bias state. It's just
really good at understanding large code
bases, complex code bases, and it's been
2 weeks, and other than UI changes, this
is the only model I've been using. There
are some tools that I highly recommend.
The first one is open source. Now, it it
sounds like the term open source, but
it's actually a repo. If you go on
Google, it's actually by Vercel. Shout
out to Vercel for open sourcing this.
Basically, what open source does is it
fetches the source code of whatever
package you're working on and dumps it
into the code base. And I'll give a
specific example. Like, this is a pretty
large code base of an app I'm working
on. The structure doesn't really matter.
What matters is I have this grayed-out
folder here that says open source. A
folder called repos. If I click on that,
there's a folder called github.com where
you see a bunch of popular projects or
companies you may have heard of. Browser
use, Composure, Daytona, Openclaw. A lot
of the technology is actually open
source, which is fantastic for agents,
right? Instead of dumping in your docs
or what the docs or whatever that are
man-made, you can give the agents the
best source of truth, which is the code.
Because the code is the single best
source of truth. What I've done is in an
agents.md. Now, I'm not a big fan of
agents.md files, Interesting. um
it's
something that the agent wouldn't know
by heart. For example, like people will
put, "Oh, this is a React code base" in
the agents.md file. And I believe this
would have been a good idea if we were
using Sonnet 4th, you know, 4 4 4.5 or
like Opus 4.0. But again, the models
have gotten so good that it will just
read your code base and know exactly
what the text stack is and stuff like.
So, if you notice the the harnesses are
sort of getting lighter and lighter and
thinner and thinner. This is why Pi has
been winning so much. You actually don't
need much. Like, the models are really,
really good.
>> So, you just want to tell it the stuff
that's not obvious, right? Like, how
this project will be used, what's the
vision behind it.
>> Exactly. Like, if there's a certain
structure that I have and stuff like
that. Now, in this case, I tell it that
it can fetch for additional source code.
And, by the way, all this is AI
generated. I I didn't handwrite this,
right? So, if anyone's reads this and
say like, "Oh, so smart." I wish.
>> [laughter]
>> AI generated this. It's like, I think
and I tell the AI what to do. And,
literally, there's a small block that
says to fetch source code for a package
or repo you need to understand and run.
So, I tell it basically how to add
packages. And, the best way to add
package, I can like maybe show an
example. Actually, we'll just do open
source itself. So, let's say I'm
building a product that uses this
package or this open source repo. Or,
you're using something like browser use.
You find the repo and then you can
literally go to terminal and then I can
do MPX open source
and then just paste the repo.
And then, watch this. Okay, this failed.
Why did this fail? Usage. Oh, because
I'm on a Linux machine. Okay, um don't
mind that. But, literally, all I have to
do is just run this command and what's
going to happen and then it will pop up
here. Now, here's the cool part, uh
David. Whenever I want to build a
feature that uses said technology,
I will tell it in the prompt reference
the code base, right? So, I'll go back
to my drawing board here. Every time I
prompt, let's like, for this project I'm
using Daytona a lot, which is a really
powerful sandboxing platform. Um there's
a lot of cool stuff you can do. It's
very, very technical. It's very, very
deep. Uh I can go in and spend some
time, but I want to build fast. I want
to ship fast, right? My competitors are
shipping at light speed. So, in my
prompt, I will tag the folder and I will
say reference the code base.
>> Is this like almost a diff of
documentation? Basically, right? Because
code is the best source of truth. Now,
there are people that might be like,
"Oh, but isn't this going to inflate the
context window?" You see, in the old
days, the harnesses used to index the
entire code base and they would use
vector and rag and all that stuff. Now,
the models are so good at search, all it
needs is a search tool. So, you just
need to guide it where to search, too,
right? And it's going to reference the
code base, it's going to find the exact
function. No guessing. It's going to
find the exact function and I can't even
tell you like eight out of 10 times,
like using this, like I'm getting it
spot on. Yeah, I think the point is that
like if you do your job properly in the
context engineering, you actually save
so much time on testing and debugging
because then you don't have any errors.
Yeah, context engineering is like it is
it's so important, right? Like if this
is your 227k
context window, your agent is smart
probably up to like this level. Maybe
I'm being a little mean. Maybe it could
go a little further, but like the more
you bloat it, the dumber it's going to
get. So, you want to stay in a sweet
spot like this, right? So, [snorts]
being able to give it the exact snippet
it needs or explaining exactly what you
need. And this is why agentic
engineering will yield better result
than vibe coding cuz in vibe coding,
you're offshoring the thinking to the
agent, right? In agentic engineering,
you're doing the thinking and then
you're just letting your minions do the
work. You're letting a bunch of junior
grads who are very cracked, but need a
lot of guidance do the work. So, if you
have like a 272k context model, I love
Codex cuz it'll tell you right here,
like at 77%
unless I'm done here, this is like I
just need to start a new thread. Like
this is too much information for the
agent. Now, I know a lot of harnesses
have like slash compact. What's funny is
with Claude Code David, um even like one
of their I forgot which developer it
was, but one of their lead devs in like
a tutorial he was showing, even he
didn't use slash compact, like the
compaction engine that Claude Code has.
He started a new session, right? And I
just goes to
>> slope is slow, you know. Yeah, right.
So, you just start a new session, but I
say that all to say, this tool allows
you to have super precise prompts, like
the agent doesn't have to do web search.
It literally like you're giving the best
documentation, which is code. So, so far
Harness Cursor with GPT-5 5 extra high
fast, we're using Slope is 4.7 max.
And then for tools, open source, which
again is completely open source, is a
great like way to like context engineer
your prompts, giving you the exact
reference it needs. And a tip for
context engineering is you just want to
keep it low. Like you want to keep your
features minimal. And that's the way you
keep this short is like
it's being very methodical with
like your feature plan. Like for
example, I don't know if you saw on X
David, a lot of people are debating
should the AI do the plan? Should it not
do the plan? Should you jump in straight
to the feature? I do the plan,
not even for the agent, but for me. The
plan is a great way for me cuz sometimes
I'll run multiple threads. The plan is a
great way for me to hold the agent
accountable. So, you'd be surprised
there are a lot of times where you'll
create a plan and it sounds like a good
plan and then you tell it to generate
and it will start to fumble somewhere.
And the reason being is the model
doesn't think about its context window
when it's generating a plan. You've
given it a task, it's going to dump
everything in that plan it needs to
complete the task. So, if you have a
large task that requires this much
context,
it's never going to do it right. But,
I'll get it to generate a plan, and then
once the plan is generated, I'll be
like, "Oh, this is a little too big. How
can we make this super small PR super
small chunks that are easy for you to
review?" Then, I have like multiple
action steps, right? I say that all to
say, context engineering might as well
be a a principle in engineering in it of
itself, cuz this is a a maker break an
output of how good things will be. And I
guess the principle is like staying in
charge, right? Like, even though the AI
is writing basically all of the code
now, you still have to stay in charge at
some degree because at any point you can
say, "What are the issues with this code
base?" And even if there are no issues,
it will happily suggest 10 issues,
right? So, like people who are new to
this, they, you know, relinquish the
control way way too easily and trust the
AI with too much with the things that
they shouldn't trust it on. Yeah, like
the model doesn't think the way humans
think, right? Like, I don't know if
anyone who's watching this notice, but
when ChatGPT when OpenAI shut down for
all, there was a huge like Oh, yeah,
that was huge.
>> people who were protesting. And because
they had developed a relationship with
the model. The model was so agreeable
that people started to fall in love with
it, right? Crazy. A lot of people might
think that's weird, but when you're
building applications using code, that
actually happens to a lot of people
where they think they're really smart
and like the model is like like leading
the right direction and you're like you
think you've made a right decision, but
the model has no idea. It just predicts
the next text. The next text can be
wrong. But, when you're in the driver's
seat guiding and making the decisions,
like you have to almost treat this like
a really dumb person with photographic
memory that knows everything but doesn't
know how to use everything. And that
sort of relationship allows you to build
again. 3 months, 4 months, 90% of the
code, 95% of the code is AI generated in
my work. And I'll get cooked if I drive
if I if
>> if bad code gets shipped. I'll continue
on the second tool. So, the second tool
is a skill of mine. Now, anyone can
generate this, especially if you you
have like development background, or you
can like go back and forth with it. One
thing that the agent will do, the agent
has a tendency of rewriting code that
exists. So, let's say you have a
function that streams a response from an
agent, right? Like you're basically
you're building a chat functionality,
you're you're building the response
function, where like it streams the
message once someone has sent a message.
And then you're like, "You know what? I
want to integrate Telegram." You tell
the agent, "I want to integrate
Telegram." And it'll build that for you.
Almost nine times out of 10, it's not
reusing the function that's already been
created, it's rewriting a new one. And
the reason why this becomes a problem,
you start to have code smell. Code base
is getting large, there's too many
moving parts, it it's going to be hard
for the agent to debug what's gone
wrong, cuz there's many many
touchpoints, right? What this skill
does, it will like structure the code in
what's called a service layer. And
basically what a service layer does, it
just creates these these functions that
can be reused again and again. What I'll
do first is I'll generate the feature,
right? So, I'll build the feature first,
right? GPT-5,
X high, and then Cursor. And then I'll
test, obviously, I'll test locally. Once
I like where I'm at, I know when I later
on when I come back to this feature, cuz
I'll probably forget how it works, I'll
probably forget where the code lives.
The the code that was probably written
is not the best shaped code. Now, the
model is capable of doing this, but out
of the box it won't do it for you,
right? It's like a lazy person. If you
tell me, "David, I want you to do this
task for me." You know, human nature
dictates that I will probably take the
least path of resistance, right? The
model's probably going to do the same
thing.
>> So, basically this lets anybody talk to
the model as if they were like a staff
engineer. Basically, right? So, like you
can see over here, I have all these like
plans. By the way, again, everything we
talk about in this podcast, all the
skills, all the tools, all the repos are
available below the video. Click on the
first link, it's completely free. So, go
ahead and grab it. Now again, this isn't
really for the agent, but more so for me
to remember. And look what the goal here
it says. It says, "Make deployment
provisioning and repair simpler by
moving repeated runtime mechanics."
Watch this. "Behind deeper structured
modules while keeping convex actions
responsible for domain policy." So,
there are repeated runtime mechanics. I
only need one. I don't need five or six
of them, right? And this causes issues.
I run this skill and I tell it, "Look at
the code base. Where do you see
duplicated code?" The agent will pop up.
It even brings it up here. It says, "Uh
modify this file, modify this file,
modify this." So, these are files where
I have repeated code that shouldn't be
repeated. So, with this type of skill,
and again, free for anyone to to check
out. We're going to link it below. It
allows your code to be cleaner. And what
I find is when the structure of the code
is cleaner, it's easier for an agent to
pick up on a new session, right? So, if
it's just messy and it's like all over
the place, if it's hard for a human to
read, it's probably going to be hard for
an Yeah, definitely. right? Clean
structure matters. Thank goodness you
don't really exactly need to know 100%
what that looks like. You can use a
skill like this. There's also another
person, I think his name is Matt Pocock.
Yeah, he has a bit of a similar skill. I
would say his is more for if you're a
bit more technical, it helps. If you're
not, you might shoot yourself in the
foot, but he has this improved code base
structure. This is another helpful
helpful one as well, right? So, I say
that to say, after every feature that I
build, I run one of these cuz I know
push comes to shove, if the agent needs
to work on it again, it's probably
written in a way that's going to confuse
itself. It's like applying the, you
know, age-old principles, but like in
the new way. After you build something,
you document it for others, but now it's
not for the human, it's more for so for
agent.
>> And and what's funny is a lot of the old
like engineering practices that, you
know, a lot of engineers shunned cuz it
was difficult or made life a living
hell, is actually great for agents,
believe it or not. So, like the code
being well-structured, there being
defined tests, is really great for the
agents. This being another. So, I use
open source, I use code structure. I'm
going to recommend a like a specific
tool. Like, this isn't me promoting a
tool, but like I just use it and I can
prove that I use it. I use Greptile for
code review. The reason why I like
Greptile is for actually a specific
skill called Grep Loop. And this skill
will make it feel like you're using auto
researcher uh from Karpathy. I can maybe
like explain through an example. The I
have this PR right here, PR 80. I've
done some changes giving the ability for
an agent to like fully ingest every row
of a spreadsheet. Greptile gives me
gives me these confidence scores. Four
out of five, three out of five, five out
of five. Let's say I get a confidence
score of three out of five, and almost
always it will give me like the issue.
It'll tell me why it gave me three out
of five, right? And I'm not going to say
this is perfect, but from my testing,
it's pretty darn good, right? Especially
if you're a non-technical person, you
need this. Like, you you you need need
need need this. So, let's say I get a
three out of five score. I install the
skill. All I do is {slash} Grep Loop and
I hit enter. The agent is going to read
the PR, it's going to read the feedback,
and it's going to fix the feedback, and
it's going to wait for a new review to
happen. So, let's say it was a two out
of five, and now let's say it gets a
three out of five. You know what it's
going to do, David? It's going to keep
going. It will not stop until it gets a
five out of five. This is why I led up
with all this first. I talked about
context being important, and then these
tools help you structure the code
because by the time you get here, you're
going to have a simple feature, a
minimal PR, and the code structure's
clean. Greptile, the review agent,
reviews it. You're going to get maybe a
three out of five to four out of five.
Then what I do is I'll literally run
{slash} Grep Loop, and then I work on
something else. And by the time it's
done, again, almost nine times out of
10, I get a five out of five. The
instance I don't get a five out of five
is because I gave it a PR that was like
9,000 lines, 10,000 lines, 12,000 lines.
We have to understand they're probably
using the same agent, the same model
that we're using. So, context window is
finite. So, we have to be smart about
it. If I respected the initial rules of
keeping context minimal, and like I
shipped this PR like 50-60%, and then
Greptile is reviewing this now, the
errors it gives me are the exact errors
that exist in that feature. Grep Loop is
going to catch them and fix them. The
last 3 months, I have like a a pretty
big app I'm going to
ship soon. The entire thing I agent
engineered. That doesn't mean I read the
code. Like I looked at the structure. I
have another developer working on it.
He's been asking me questions. You know,
knowledge still matters. Even if you
don't understand the syntax, which
syntax doesn't really matter nowadays,
understanding how like good code and
architecture works helps.
Yeah. Man, I'm telling you, I am going
far and fast. The app I'm launching
soon, if I told you I built it in 2
weeks, 3 weeks, a month, you would not
believe. But with this exact formula,
Cursor is the harness, the best-of-class
models. If someone says, "Can I do this
with Kimmy? Can I do No, you have to
have the best-in-class model. Like
>> Yeah. they are not OpenAI or Anthropic.
Yeah. It's true. It's just a night and
day difference, right? Cuz I know
there's a big local model movement. I
love that. I have
Gamma running on my machine, but it will
not write code like this. And then you
give it open source to download whatever
packages or libraries you're using, and
then you structure after every feature.
When you make the PR and you run Grep
Loop, notice how it said, "Oh, PR 80 is
good to merge. Greptile five out of
five." Right? So, it would have kept on
going. Like and I have times where like
it went on for like 20-30 minutes. Where
it's like, "Oh, the agent I Like Cursor
will tell me, 'Oh, I made a mistake and
I missed this. Greptile caught this.
Deploying a fix now.'"
Pushes it to GitHub. Greptile then sends
the review. When it's five out of five,
it stops automatically. Right? And the
one thing about the super
super duper models Opus 47 in particular
GPT 55 extra height. They write a lot of
tests. I don't know if you notice this
David, they write a lot of tests. And
this is actually great because now what
the model will do is whenever it gets
whenever it gets feedback whenever like
oh this is broken, it's going to write
the test in which that feature would
have worked that bug would have worked
and it won't stop working until that
test passes. Even though auto research
was interesting and unique paradigm by
Karpathy, that's essentially what
agentic engineering has become. You give
your agent just enough tools and just
enough context for it to work in a loop
where by the time it's done, the feature
is done.
>> The reason we're using these skills and
you know providing the right context is
that so the end outcome is clear, right?
Whether it's a test passing, whether it
is the app is deployed, whatever. You
know, I guess that's the main idea
behind also the slash goal feature
inside of Codex is that you give it the
end state, right? It's not just like a
dumb loop that runs forever which that's
how people understand it who don't use
it. It's all about how well can you
describe the desired outcome and if you
nail that, the agent can basically
figure out the way to get that. I think
of it like this like let's say like you
and me are on a basketball court and you
were telling me Michael this is how you
shoot, right? You shoot like this. Like
you explained it to me once and
properly.
I probably won't get it right the first
time. I probably won't get it right the
second time. You might interject the
second time give me some more feedback.
But then by the third time I get it,
fourth time I get it, fifth time I get
it. That's basically what we're doing.
All this is a giant massaging machine to
the agent to you give it just enough
information and it'll do the right
thing. And that's what this is, right?
This is agentic engineering as a whole.
Giving it enough info, enough
guardrails, enough of a feedback loop,
right? If I told you, you know what? No
open source, no code structure,
like no like thinking about the feature.
I just tell it you'll build me this and
slash grep loop, we have Ralph Wickham.
And we've all seen where that led us,
right? It was cool at first. I even have
like a custom implementation called
Ralphy, but you're not going to get far.
Right now in engineering, human
approval, human thought really, really
matters. And I've noticed a lot of
people who are building, launching apps
and stuff, they're just letting the
agent think for them. So, it's actually
a great time to stand out. It's actually
a great time to to build something that
feels unique and that actually works. Um
and this is like my process. Another
thing I would also say is like using
um
popular tools, but not just popular
tools, tools that are very codified,
right? For example, I use a library
called Svelte um over React. And the
reason why I use Svelte over React is
even though it's a much newer framework
um and a lot of people argue that the
model hasn't been trained enough on it,
a lot of the syntax is HTML and
TypeScript,
which the agent is great at, right?
Versus React, especially if you're using
a newer version, there's all these
hooks, there's all these footguns. But
with Svelte, it's very um like it's very
to the core principle of HTML and
TypeScript. And here's what's cool, I
practice what I preach. I'm pretty sure
in this project, if I go to repos,
you're going to see the Svelte JS code
base under open source, right? So, if
there's something that I feel like it's
not doing right, I'll be like,
"Reference the Svelte JS code base."
Right? And it's going to use standard
practice, the best practice. So, I use
Svelte.
>> is this headed to like people are going
to be building basically only on open
source projects, frameworks, and stuff
like that because of this reason?
Yeah, like cuz code is the best context,
right? Like think about it. Like we give
like people are debating markdown files
or HTML files. Like it's not straight
English, right? It's some sort of
codified structured language, right? So,
code is the best context. And if a
company's building a developer tool,
uh again, this is a business decision,
they have to open source, right? Because
when the agent like human-written docs
are the worst. The worst, the worst, the
worst. Now, I know there's startups
where you give it the repo and it'll
generate the docs for you. But again,
why am I why are we taking that extra
step when you can just give me the code?
Exactly.
Right?
>> That's That's a good insight.
Uh there's a there's this other library
called Effect that everyone's been
raving about. Um it's like a a
TypeScript library. It's super
like super types, this, this, that. You
know what? I'm not going to care. I'm
going to find the repo, which it's a
library, so it should be open source,
right? I'm going to take this
and I'm going to use open source to
download it in my code base. And now me
and my agent are going to go back and
forth on me setting it up. So, even with
frameworks I'm using, uh in this case
I'm using Svelte, I'll use open source.
Um for backends, again, I know people
are fans of Supabase, and if it works
for you, you can. And I know I work at
Convex, so but in all honesty, I use
Convex. And here's the reason why.
Everything in Convex is code. The only
time you have to go to your dashboard is
when you want to set up a production
instance or your app is blown up and
it's time to pay. I want to set up
scheduled functions, meaning I want to
close my app and have something run in
the background, which your app should
have that, right? It's code. I want to
write a API, it's code. Everything
Convex, all the features, is TypeScript
code. Now, why is this great, David? The
reason why this is great is cuz the
agent has full context on what my
backend is doing.
>> It's not It's not guessing about the
schema and, you know,
I don't need to take a screenshot of the
dashboard and tell it this is what's
happening, and then tell me I don't know
if anyone's ever done this, tell me what
tab to click. Sometimes you get a little
lazy. But Convex is all code, right? And
if you notice everything I'm saying, it
goes back to really giving the agent the
perfect context it needs, right? So, the
back end its code, the framework, I give
it access to the code base.
When I combine these two
with the structure, I've been able to
ship like almost anything and
everything. Now,
it's not a smooth sailing. Like
obviously when you build anything, and I
think this is a mindset I know you
preach about a lot that's lost. People
understand that they have to work hard
either in the gym or in life, but for
some reason when it comes to agentic
engineering using an agent, if it
doesn't get it in one shot, it's over,
right?
Like you have to have some sort of
audacity, right? Like you're building
software that Okay, if it's an internal
tool, fine. But if you're building
software that you want people to use,
like care is important, being thoughtful
is important, spending time is
important, right? You're going to handle
people's credentials and information.
>> nothing to learn. Also, like people who
don't come from developer background,
they're like close their mind to any
technical concepts, right? It's crazy.
Yeah. Yeah, like someone will be like,
"Oh, it's like a CLI terminal thing."
It's like it's actually so simple. Like
it's actually so simple. And what's
funny is I'm starting to build on
technologies I've never really messed
with. Like I'm not a big network
engineer. And I've been using like the
agents to like explain to me and like
clean up my desktop and do these things.
Just yesterday, I don't know if you saw
it on Twitter, a some guy who lost his
wallet password
>> that tweet.
He used quad code, right? So, if
anything, these tools should expand your
mind. You should be delusional and
crazy. You should think you can build
anything. And maybe you can't, but dang
it, at least try, right? Like at least
give it a go, give it an honest effort,
you know, all the motivational David
David Goggins stuff, you know, fail
forward, yada yada yada. That same stuff
applies to engineering. But I find with
like these tools in this combination,
I've been able to get a really, really
solid output.
Yeah, and it's crazy to think that like
most of, you know, Vibe coders, they
don't have any of this or maybe they
only have one of these tools, but
they're completely unaware of the other
principles and the other tools that
exist or maybe they're using a cheap
model or a free version of some tool.
You know, you meet it every day. I meet
people every day who think like they're
on the cutting edge of AI and they have
like the free ChatGPT or a free cloth,
Yeah, like unfortunately,
this is going to be a uh like a a money
game, right? Um you know, we're being
subsidized now.
At some point the subsidies will end,
right? And it's going to be like the
people have money to play, like you're
going to get better results. So, I think
like even though like again $200 a month
is a lot and I understand everyone's in
different situations. Like if you're a
young person, right? I'm not going to
speak to people who have kids and
responsibilities and mortgage cuz that's
a whole different uh you know, life. But
if you're like young and you have a job
and the reason why you're not paying the
200 subscription on Codex is cuz you're
drinking out with the boys,
Crazy.
You know what I mean? Like again, for
the to the adult who has kids and a
>> Like even the 100 Codex subscription
gives you so much like AI is subsidized
and like crazy.
They are and like to be honest like as
long as you like if you want to continue
the subsidies to go go on Twitter and
glaze Open AI. They'll probably keep
pushing for it, right? So, like getting
like a $100 [clears throat] sub with
Codex in my opinion and just pushing it
to the limits and now they're like
turning it into like a super app where
like you can do stuff and like workflows
and stuff like that. I definitely think
it's worth it. I think it's worth the
investment. Um and a lot of these
>> not even coding, right? Like imagine
what that gives you. People like my only
see the coding is like I I don't know if
that's going to you know, I'm not a
developer. I'm not building any tools,
but like the difference between paying
$100 a month for ChatGPT versus free
plan is insane. You get 5.5 Pro extended
and you can like literally have like a
professional lawyer, a professional
doctor at your fingertips, and like
anything you're dealing with, you know,
maybe like some some dispute with
somebody on your team or somebody's
threatening lawsuit, you can just launch
a deep research, and within 15 minutes,
you have like an insane response that
like would cost you thousands of dollars
if you paid human lawyers.
I I I I'll give you an example, like
real-life example. I was sent a contract
for some work that I that, you know, a
company wanted me to do.
And when I tell you that contract was
like 27 pages. Now, for a long time, I
was a boomer, and I had a lawyer for
contracts, cuz I was like, oh, maybe
like, you know, an agent might miss
something.
But the lawyers are expensive. They they
they charge, especially in Canada,
America, they're very, very expensive.
So, I was like, oh, let me let me give
it to Claude. Let me give it to Claude
desktop. When I tell you every page
highlighted with every single point,
giving me a rebuttal.
I ended up getting like the money that
they were going to pay me
3x because of the nonsense I saw in the
in the in the in the contract. And then
I gave Claude like the analytics of all
the stuff that I've done, the work that
I'd done. And the agent was like, yo,
you need to charge more. Like, and I
literally was telling the agent, oh, but
I'm scared. Like, I don't want to lose
Like, I literally was I was like, I'm
I'm scared. I'm not a salesperson, you
know? I don't want to lose the contract.
And the agent was like, no, don't be
Like, it literally was like a coworker.
And then it wrote a message. I then
rewrote it in my language, cuz you know,
you don't want to you don't want to send
AI messages. Yeah. And then they
responded back saying, yeah, we'll
change the terms, and we'll 3x the
price. If if that was $200 a month, that
was infinitely many times way more
important, right? So,
um I think trying is the best thing.
Like, trying is the
>> another example from like a similar
thing, but it saved me a [ __ ] ton of
money.
It's accounting, right? So, I had to
like redo accounting for 2024 255 for
one of my companies.
I got accountants, and again, not some
crazy expensive firms, just like normal
accountants. They They said like, "Oh,
this is like 3,000 transactions. This is
going to be 42,080,
which is the Emirati currency." Let's
say like five or six thousand dollars,
right? I'm like, "Wait a minute. You're
charging me based on transaction
amount?"
And I was like, "Listen, let's check the
accounting software. Do they have API?"
They have API. So, I'm like, "Nah, I'm
doing this with Chris and Claude code."
I sat down for like, you know, two
hours, and it's done. And I saved
literally five or six thousand dollars.
And I honestly trust Chris and Claude
code more than some like, you know,
accounting associate at that firm.
Yeah.
Who Who like Like again, and
it's It's these things that even though
we're talking about like agentic
engineering and development,
I'm actually more bullish on knowledge
work. Like there's so much mundane, like
especially if you're running a business
or you're an entrepreneur, or you know,
you have a side hustle, or you work a
corporate job. Like I have friends who
are really above David in a corporate
job. And when I tell you the amount of
productivity in generating reports,
spreadsheets, all this type of stuff
that people would spend hours on that
like a hundred dollars subscription
saves you on. Like if you haven't made
the decision, again, I don't get paid by
any of these companies. I wish I did. I
wish I got some stock. Uh but I'm
personally telling you cuz I
Yeah, please.
But like I'm genuinely saying like if
they bumped it up to five hundred bucks
a month, I probably would still pay.
>> I'm buying into it.
You see Okay, so they're not even taking
about it. So, you see, like uh
getting exposed to the tools and using
it is probably the best thing. And I
don't want to sound like a super like,
you know, like one of those billionaires
on TVPN, but I genuinely think like you
have an advantage when you use the new
tools. Like maybe there's something
better that comes out next year, but the
fact that you have exposure with the
tools now means when the better tool
comes next year, you'll be better
equipped in using it and learning it,
and you move much faster than someone
doing it for the first time.
Absolutely. Now, one thing I want to
touch on because
you know, you mentioned you you've been
building something for like 3 weeks. A
lot of people get stuck in the building
phase forever, right? I know many people
who are like always when I follow up
with them, they're like, "Yo, I'm like 2
weeks away from launching." I follow up
in 6 months and they're 2 weeks away
from launching.
What advice would you give to these
people? Yeah, so I was in San Francisco
recently and to the people who
experience this, I was experiencing this
too until I went to San Francisco.
I don't know David if you've been there,
the level of the delusion and I'm not
saying in a bad way, but the level at
which people believe they will succeed
is so high. Like I know you have to like
believe in yourself and all
Believe me, most people do not believe
in themselves the way that people in San
Francisco do. That's number one. They
have this level of belief that whatever
they're building is going to change the
world. Like someone will tell you, "I'm
building an AI UGC app." Right? And
there's a couple of them out there. I'm
sure they can like, you know, make it
better in some different aspects, but
say AI UGC app.
When they explain it to you though, you
feel like this is the greatest app ever.
And at first, I thought it was like,
"Oh, maybe people are just grifters."
No, no, no, no, no. They genuinely
believe it. And because they believe it,
the moment they have a semi-functional
MVP, it might not even work. Auth might
break when 100 people get on the site.
They'll launch it anyway.
They'll launch it. They'll get hype. And
guess what? They'll raise the money.
And then they'll hire people or they'll
spawn a bunch of they'll do whatever and
at some point their product is good.
Meanwhile, you and me are overthinking a
simple feature. We haven't launched yet.
Those guys have raised $10 million.
Right? So, I say this all to say,
whether you're bootstrap, raise,
whatever it is,
you you got to launch early. And I know
it's hard because you don't want people
to catch the bugs that you catch, but
believe it or not, a lot of people are
actually most people are actually
invested in cool new tools. I I there's
communities. Forget technical people.
There's communities who search for new
Mac apps
to try out, right? So, people are you
know, most people are bored and they
want to try out something new, right?
And they're willing to try your thing
out and if it sucks, they'll give you
feedback. You fix and you go again. And
your product is better than just like
keeping it for yourself and like you
delude yourself you know, that it's good
when you have no touch with reality.
And I just want to and this is what I
want people to I want you to go on
Twitter and I just want [snorts] you to
look at all those launch videos. All
those animated videos. You know why
they're animated? Cuz the product barely
works.
Yet they're launching, they're getting
more users, they got more MRR than me
and you and what are we doing? We're
just
fixing this one more feature. It is it's
the biggest scam. I'm fighting it myself
but it literally is the biggest scam and
time after time, I see it all the time.
You have to be delusional, right? Um
again, I'm not saying be dumb as in
like, you know, don't make dumb
decisions. Don't say, you know, like for
example, like Delve, don't say you are
the best SOC 2 platform and you're
actually committing crimes. Don't do
that. But like just believe in what
you're building. Believe in the
abilities that you present. You know,
communicate a vision that like, okay,
it's it's this right now but it will be
this in the future
and share with the world. Build like,
you know, in public. Not the community
but like build in public and don't be in
the shadows cuz there going to be many
competitors, right? Unless you're like
Andrew unless you're Aporia and you're
building some sort of new paradigm. If
you are, then stay in the shadows. But
if you're not,
you have competition and they're going
to move fast and they're going to burn
more tokens than you and their app might
not even be as good.
But they're going to win. So, it might
as well be us
and that's what I like that's what I
literally told like a couple people like
last couple weeks who had a really great
apps and but they're like, "Ah, I just
want one more feature." And I'm like,
"Yeah, your competition will smoke you
if you keep going like that.
Yeah, so like the delusion and the
belief is like half of the success.
So many other things fall into place.
And also, if you believe in it so much,
like any roadblock, you just like brush
it aside, right? But if you're kind of
like on the edge,
then like you quit.
Yeah, like
I'll share maybe like a personal
example. Like I have a full-time job.
And after the full-time job, I'm working
on this app that I'm launching very
soon. And like the cost of that is
sleep. The cost of that may be, you
know, get-togethers, right? So
>> Social events, yeah. Fun, whatever.
Whatever it is, right? So like if it's
like a product that you're really
bullish on, that you see yourself using,
then you know, just launch, get
feedback. If people dunk on you, great.
Now you release V2, and you know, be
funny with your marketing. Again, I'm
I'm not the best marketer, but like
go being out there and and and and
building in front of people, people
actually like that. People love the
underdog.
No one usually gets hate as an underdog.
You get hate once you've succeeded. So
might as well absorb all the love now
and succeed, and then later on you can
figure out the rest. But yeah, please
launch quick.
I want to talk about how you think about
security
in the agent era, right? Cybersecurity,
we see like every day is a new breach, a
new vulnerability, new hack, new attack.
But tell people who are not as technical
as you, how should they
think about this?
Yeah, it's cooked. We're cooked. I'm
going to just keep it a buck. It's It's
It's really scary, right? It's like
I would say maybe don't be super famous.
Like don't antagonize a specific group
of people who wield power or like
technological power. Like
all the jokes aside, it really is
a scary time
because the models are starting to get
really good. And you can imagine if you
can run this in a loop to fix a feature,
you can run the agent in in
to do very nefarious things, right? And
even now, you go on Hugging Face,
there's a lot of distilled models that
the guardrails are removed. Like you can
prompt it something nefarious and it'll
do it for you.
Um
uh
For for people personally, and this
might be a little crazy. Like for
example, in my family, we have a pass
phrase, right? So if you get a voice
that sounds like me asking me for money,
you're going to ask what the pass phrase
is, right? Cuz the voice cloning has
gotten really good.
>> [snorts]
>> 2FA is mandatory now. It's not even
uh it's not even a A password manager.
It's crazy how many people don't use
password managers. Yeah, please. Like
one password, something, right? Like you
need to have super complex passwords.
And then the key that one password gives
you, take half, give it to like your
mom, your dad, or someone you trust.
Like we have to be very, very secure
with like the accounts and the stuff
that we have. 2FA, not via text. I got
SIM swapped not too long ago.
It's happened. It's real. If people want
to get you through SIM swap, they will.
You use a uh
2FA like Google Auth, whatever, right?
And but most importantly is like if
you're in the agentic space, especially,
you're building tools and stuff, I would
be very careful with the packages you
download and stuff like that, right? Cuz
for the most part, I would say the the
consumer apps that everybody's using are
on very, very high alert, and they've
been getting hacked before. They'll
probably get hacked again. The dangerous
attack vector is when you're downloading
packages um and code, right? And
something you can tell your agent you
can really prompt your agent you can
just just prompt your agent this. You
can tell your agent, "Never install a
package that is uh
uh that is let that is younger than 14
days, right? Because a lot of the attack
vectors are packages that dropped
literally in the last couple days or
last couple of hours. Um that's number
one, right? So telling your agent to
never download a package that's like 14
days like that's not older than 14 days.
Um number two is generally being part of
the discourse on Twitter, right? I think
Twitter is just a great place. If you
follow the people uh David follows or I
follow, you'll probably have your
algorithm seasoned enough where like
when something happens, you're one of
the first people to know. Um and third,
this is actually going to probably be a
sector in the space that's going to keep
on growing, right? So, if any of you
young people watching this are in school
um for security or any such thing like
that, keep going. The job market's
looking really, really good for you. But
all in all from consumer apps, 2FA is a
must. Um
Also, side tangent, if you have any
older people in your family, please
explain to them these things, right? Cuz
I've heard stories of people's, you
know, grandfathers sending money to
strangers thinking it's like a a
granddaughter or an old lost family
member, right? Um like for us it might
not make sense, but for an old person,
seed dance is convincing enough. GPT
image 2 Oh, it's I mean GPT image 2 is
near perfect, you know? Yeah, so like
definitely like the old people in your
family, like get them to be like get
them to ask you first. Like the con of
this is like even on my WhatsApp, I have
like six different messages from older
people in my family saying, "Oh, is this
AI? Is this a scam?" And because like
they're easy targets, this is something
I'd recommend like people communicate
with. But all in all, it's 2FA. Um to
you know, one password, have a password
manager. Um really like don't do
something
>> more thing on on what you added with the
Twitter, right? When when you spot
something within minutes, you can just
have like ChatGPT, Perplexity research
it, get like every information about
this breach, and then tell it to give
you a one paragraph instruction on how
to analyze your MacBook to see if you're
exposed. You paste that into Claude
code, by Hermath, whatever you're are
and it will tell you like, "Yes, this
package is in this project or no, you're
safe. And you know, that's probably the
best
>> Yeah, and that's a big thing. Like
especially like Claude is really good at
this. Like you can like literally copy
the tweet, paste it and say like, am I
cooked? It will understand.
Um and it will like read the files. I
think there was one in particular, I
forgot which one. There was one in
particular where I thought I was uh
caught like cuz I downloaded the package
literally like a version before. And the
next version was a scam. And literally
Claude looked through every single
directory, looked at the system
directory, and it checked and was like,
oh, your machine is clean, right? So,
um doing a lot of that is necessary, but
also again, being smart with what you
install, right? That's how the big
attack vectors are happening now, it's
through packages. And if you're watching
this video, you're probably building
with agents. If you set up that prompt
where you don't install a package that's
younger than 14 days, by then, the
vulnerability would have been caught and
you would have been safe. So, like
that's the biggest thing. And on the
consumer side also, be smart.
Where do you see the future headed? Like
if you had to say like in 3 months or 6
months, what's going to be possible?
Yeah, um
it's like
I'm more bullish on knowledge work than
I am on like agentic engineering just
because I find that there's too large of
a surface area in engineering for the
models to just be good at all of them.
Like if you notice,
um GPT-55 is a tad bit smarter when it
comes to things of architecture and like
back-end stuff, and then Opus really
seems to be great at UI stuff, right?
So, there's like these two large of a
verticals, and now the question is, does
that mean we get we make a bigger model,
or do we make smaller specialized
models, right? So, there's a lot of like
thinking there, and obviously the model
providers, um you know, have the
smartest people uh figuring that stuff
out. But I'm more bullish on knowledge
work because I think the issue now with
a lot of knowledge work is tools not
being built around it. I actually don't
think it's not the models being not
capable enough. I think the models are
there for knowledge work. I think we
have smart enough
models where a ton of knowledge work can
be done through them. We just don't have
the tooling around them, which is why
you have both Open AI and Anthropic
launching these like consulting
companies, right? And they're going to
deploy forward deploy engineers into
companies and small businesses to help
them set up. So,
if you're in a place that doesn't use a
lot of tools and you want to get a
little promotion, maybe sharing these
things, right? Like using these things,
being an example of these things, be a
leader in these things. Like I heard
David
some guy that literally I I I just met
at an event and he was telling me like
no joke like he at his job he helped
them like they do they they they do like
a lot of like contracts, right? And
they're not a law firm. They're not big
enough to afford like a like a proper
law firm. So, like they pay these guys
on retainer it's a lot of money for
them. He basically did one presentation
in front of them, showed them how Claude
co-work worked. And like they made him a
manager. Guy's like 24, right? So,
cuz like again he showed them with
knowledge work how valuable things could
be. So, I think in the next 3 to 6 month
we're going to start seeing even a boom
in knowledge work. In [snorts] terms of
agentic engineering, I'm really hoping
Opus 5 comes out and it just blows us
out the water cuz if everyone remembers
December 4 5 is what changed the game.
That's when we realized
oh, this is a shift. And I I think
that's what Opus is being that's what
Anthropic is gearing up for. Open AI is
taking too much share. I know they're
going to stop it. I hope they are
because this competition helps. So, in 3
months knowledge work is going to
continue to boom. Maybe we get a new
model, but in terms of the long-term
effects of all this,
I actually have no idea. And that's kind
of terrifying because
like
you know, when you when people say oh
jobs are going to get replaced this this
that not fully,
but some will. Yeah.
And what does that look like, right?
Like what does
you know, being job proof look like?
What jobs are safe, right? I I mean, if
you told me 3 years ago the agents would
be great at coding, I'd laugh at you.
I'd tell you programmers are going to
rule the world if anything cuz no one
can do programming and yet look where
we're at now, right? So, I think being
informed, being proactive, and just
making this fun. A lot of people are
dreading this. I don't know if you've
noticed this, David. A lot of people are
dreading like the growth in these tools.
I think if you just have a simple
mindset shift shift and this stuff
becomes fun for you, you actually end up
growing with the industry. You end up
learning new things. You end up maybe
picking up a new gig, a new job, consult
whatever it is, right? So,
don't take the change as this is
happening against me, but if we have a
little mindset shift and say this is
happening for me and you're learning
with the tools, I genuinely think it'll
be a fun time. And whether we go boom or
bust,
I'm going to win either way. And I think
that like that mindset shift mindset
shift helps a lot. Yeah. I'm I'm glad
you mentioned this because you know,
people who aren't as technical as you or
on the cutting edge as you, they feel
the same way and they think like us
we're in a club or something and we we
feel we have all the answers, right? We
know exactly what's going to happen, but
the answer is nobody knows, right?
Nobody knows. It's too much change, too
much unpredictability and you almost
have to embrace that and like you said,
have the right mindset to use that for
your own advantage and say like, okay,
if everything changes every 6 months,
that means there's new opportunities for
new businesses every 6 months. Yeah.
Yep. 100% and like even like those of us
in this bubble,
even our thinking changes like every 6
months. Like I remember last year when
windsurf and stuff were pop popular, the
goal was to give the agent all the
context. If you remember, there was even
services that would minify your code
base into like XML and you would give
that as context to the We believed
stuffing the agent with context was the
smart thing. Now we're doing the
complete opposite, right? So, even like
if you feel like uh things have
progressed so far, catching up and being
ahead is so easy. And for I'll draw one
more graph just for the non-technical
person cuz I know there's one person
saying, "Oh, but you guys understand
this that and the third." If this is the
If this is a line of you have non-techy
[snorts]
people here
and you have super techy people here, I
would say the people on Twitter who
really know their stuff that are talking
about this every single day on the
cutting edge,
I would say the people like that's It's
this It's this section of the graph.
I say this to say that even being right
here means you're ahead of most people,
right? So, this idea of like I'm not
technical, I'm sorry. I understand
you're not. You have two options.
Either go be technical so you stop
complaining or
bro, just have have that dog in you. You
know what I mean? Like use the tools.
You don't know how to use a CLI? Ask. I
don't know how to write Rust and I
properly probably will never learn how
to write Rust. You know what I do? I ask
the agent, "Okay, I want to write Rust.
What should we do?"
Um you know, I know this is a lost art.
Books? Maybe pick up a couple books.
Read on some things, right? You want to
learn engineering principles, there's
tons of engineering books that you can
read, right? There's just To me, like
I'm non-technical pisses me off cuz I
have non-technical friends who are so
like David who are so on the like as you
could say, the cutting edge that it's
just a matter of grit, mindset, and
maybe a $200 a month subscription,
right? So, there really is no excuse.
You just need to be motivated and
excited
uh to use these things. And I think that
will take you a a long way. If you're
having fun, it doesn't feel like work.
I'm sure if I ask David, "David, does
the stuff you do feel like work?"
With building with AI, no. Like I could
be doing that 12 hours a day. Everything
else feels like work, you know. Yeah,
and and honestly like they almost feel
like slot machines. It almost feels like
a casino cuz like I noticed and my wife
told me this
like every now and then like I'll game I
used to game a little bit just to like
you know relax whatever. I stopped doing
that now. My gaming has been just
spinning up an agent and I just building
some random thing, right? So like
I think there's a place where people can
make this fun.
Um and you will find that you'll be a
lot more useful
um in the next couple months when you do
that.
Yeah, and to you know double down on
your point, the fact that like you
cannot say I'm not technical because
everything will be technology. AI will
be everywhere, right? It will see it
first in the realm of software, but like
it's going to be in the physical atom
world soon enough with humanoid robots,
drones, and everything. So the the kind
of mindset like I'm not technical, it's
saying like I'm the past. It's like I'm
not future, you know? If you rephrase
that like I'm not future, it's like
woah. Obviously everybody wants to be
future-proof and you know future-ready.
So yeah, everybody will be technical.
The question is how fast you embrace
this and how fast you try to get on the
cutting edge.
100%, right? It it really it it really
is a do you have that dog in you
question, right? And I know people who
are very much less technical than me who
I would say are on par, maybe even
better when it comes to using these
tools and these harnesses and
configuring them and stuff like that and
they don't even know how to write code,
right? So
you know, take advantage.
Yeah. All right, so where should people
find you, Mickey?
I'm on YouTube, X,
Ross Mike r e s m i c. I talk about cool
stuff. I don't post as much as David,
but I'm trying.
and yeah, I appreciate you for having me
on, man. Thanks. Means a lot.
>> I'm going to link all your socials
below.
Uh have a great day, Mickey.
Have a good one. Bye-bye. Thank you for
watching the entire thing, but watching
without action is pointless. So go ahead
and apply all the things that Mickey
talked about by grabbing the bundle of
the skills, the presets, the repos,
everything we mentioned in this whole
podcast, it's the first link below the
video. Go grab it now and implement it
into your own agentic engineering
workflow. Again, it's completely free,
so go get it now.

References

• https://www.youtube.com/watch?v=PzVV4X37ihg
• https://www.davidondrej.com/micky-podcast
• https://x.com/Rasmic
• https://www.youtube.com/@rasmic