How I Turned Codex Into My AI Life Coach in 13 Minutes (5-Step Tutorial)

Hey everyone. Today I'm really excited to show you how to build an AI advisor that helps you think through important life and career decisions. My advisor is

by far the most useful AI skill that I built so far. It knows my goals, gives me valuable feedback, and gets better the more I talk to it. So, I recently

made a video sharing why I decided to leave my job to bet on myself. And what

I didn't share is that I talked to my AI adviser for over three months leading up to this choice. It gave me great advice like your decision is psychological and about letting go of the person you spent

a decade becoming. Your kids are eight and four and will grow up fast. Your

goal isn't to maximize income. Is to

make enough so you can spend more time with them and other insights. So how

does this advisor skill work? Well, it's

basically a folder with a few text files. Here are the files in the advisor

files. Here are the files in the advisor folder. There is a skill.md about how I

folder. There is a skill.md about how I want the AI to give me advice. There is

a plan MD which is a doc with my goals, principles, what gives me energy and more. There is a learnings.md which

more. There is a learnings.md which

stores new insights from our conversations.

And then there is a eval which is a checklist for AI to make sure that's giving me useful advice before it actually gives me advice. All right. So,

I'm going to walk through each of these with some real examples, but first let me kind of do a quick demo of how the advisor skill works. Okay. So, here's an

example of me talking to my advisor in codeex. And you can also use clock code.

codeex. And you can also use clock code.

So, I asked it without revealing any confidential information, what should I focus on to grow my business? And it

came up with three things. Double down

on AI builder content sharing my journey as a AI builder. Make the pay substack product feel more different from the free YouTube and then make sure you fulfill your existing sponsorships

before taking on new work. And this

stuff is very relevant to what I'm actually focusing on now. And the reason it's able to give me such good advice is because I've given you so much personal context about myself and it also has learnings and evals to help it improve

its advice over time. Now, let's

actually go through each of these documents to see what they cover. Your

skill.md is basically how you want the AI to give you advice. It shouldn't

actually contain any personal information about yourself. That's for

the plan and other docs that we'll cover later in this tutorial. Instead, it

should focus on telling AI what role to play, what context to read, how to advise you, and what to remember over time. Here's a snippet of my skill. MD.

time. Here's a snippet of my skill. MD.

So right off the bat, it's very important to actually have a very detailed description to let AI know when you should use the scale. So use

whenever the user is stuck on a decision, working through a hard problem or asking for a gut check. And then it talks about how you are my trusted life and business advisor. Give me specific

advice based on my plan on my learnings and on other things. And then when advising me, maybe open by reflecting what you see. separate your facts from assumptions and give two or three

concrete suggestions, right? And a bunch of other tips that I've included in the scale so that it kind of gives me advice as a trusted friend in a voice and tone that I like. And again, I didn't write

all this from scratch. I kind of work with AI and iterate with AI to come up with the skill that MD. But an important thing to remember is that this file defines the advisor's behavior. And the

next file that we're going to cover has all your personal contacts. And this

next file is basically the plan.md. And

your plan.mmd has the important context about your work and life thereby making it the most important file to get right to set up this skill. So let's walk through each section that you should

cover. First it should have a goal which

cover. First it should have a goal which is a oneline statement for what you want to achieve this year. So my goal for example is by the end of 2026 I want to grow my business to a certain dollar

amount while keeping control of my time at work and having a clear measurable goal helps AI give advice that moves you closer to the life that you want. So

definitely open by having a clear goal.

And in this case, I also hooked up codeex and clock code to Mercury MCP which is my bank so that my advisor can actually pull information on how close I

am to achieving this monetary goal. But

this step is totally optional. Okay. So

the next section that you should include is your principles. When I was a PM, I always found it useful to define principles so my team could make better product decisions. And the same applies

product decisions. And the same applies to your career and life. And you don't have to be too crazy on the principles.

You just can just start with three. So

here's three actual principles that I put in my plan doc. Go work. Work feels

like play. I want to document my journey as a AI builder and share insights along the way. Keep the main thing the main

the way. Keep the main thing the main thing. I want to focus on growing my

thing. I want to focus on growing my YouTube and newsletter. I don't want to get distracted by other opportunities and do the simple thing first, which is to ship early and often and share what I

learn. And the fact of the matter is, as

learn. And the fact of the matter is, as a content creator, I get new opportunities come to me every week.

There's always some sort of AI conference or something new to attend.

And these principles help my advisor remind me when I'm drifting away from my core work. And you should set up your

core work. And you should set up your own principles. But the important thing

own principles. But the important thing is think of three or four things that help you make decisions and write them down. All right. Now, this next section

down. All right. Now, this next section is also extremely important. You know,

we do our best work when the work actually feels like play. So I think it's very important to tell your advisor what gives you energy and drains it. And

here's my list, right? So what gives me energy is building AI products that solve my own problems. It's teaching what I learned through my newsletter, YouTube, and behind a craft brand. And

it's also learning from other AI builders, through interviews, collaboration, and from the community.

And what drains my energy is having too many live meetings, calls, and recurring commitments, doing a bunch of admin work that does not compound. and also selling or teaching stuff that I personally

don't want to build. Right? So again,

you don't have to go crazy here. Just

list three things that give you energy and three things that drain your energy and put it in your plan. MD. And the

rest of my plan MD beyond these sections includes sections on my business. So who

is my ideal customer profile? What are

their pain points? And what kind of promise am I making to them? Includes

another section about my life, which is about where I live in the expensive Bay Area. context about my family and also

Area. context about my family and also what my financials look like so that I can understand how much risk I'm willing to take and also I've kept a history of my past goals and how close I came to

achieving them. So even if you actually

achieving them. So even if you actually don't build this AI advisor just having all this stuff defined in a clear one-page plan will force you to clarify your priorities. So it's definitely

your priorities. So it's definitely worth doing this exercise. Okay, so now we're back in codeex and I want to just quickly demo and ask my advisor what insightes can I draw from my plan

document. So here we go. So take a look

document. So here we go. So take a look at my plan doc and figure out if there's any insights or sections that you can draw. You can share with my audience

draw. You can share with my audience again without revealing sensitive information and let's see what it comes up with. Okay, so here's the output that

up with. Okay, so here's the output that I came up with. So the overall structure is there's updates plan and other things. There's core principles that

things. There's core principles that like I said before go work feels like play. There is a business loop um build

play. There is a business loop um build useful AI workflows for my own problems, share the journey publicly and turn the best workflows into maybe paid assets.

And there's other things like energy filter and the strategic insight. Right?

So you can see here that it's pretty detailed document but I try to keep it to one page because I actually want to read it and update it myself. It has

again the most important context about my business and my life. Okay, so now let's move on and talk about the third document as part of the advisor scale

which is the learnings.md.

So plan MD is what I believe about my life and business right now. And

learnings.mmd is what the advisor learns about me over time during our conversations. So to set this up, it's

conversations. So to set this up, it's as simple as just adding a line to your skill file that AI should offer to store new learnings after every meaningful

conversation. Right? So let's give this

conversation. Right? So let's give this a test now in codeex. I'm going to ask the advisor based on my learnings.md,

can you share three insights about me?

And you should look at the file and hopefully pull the three most relevant insights. Great. So here are the

insights. Great. So here are the insights. So you get energy from

insights. So you get energy from building, not just advising. Yeah, I

definitely want to keep building instead of just like being a content creator.

your best positioning is AI builder.

Maybe that's not true. Maybe I'm still learning how to build with AI. So maybe

like curious beginner. And then I prefer grounded advice over generic strategy, which is definitely true. Like I don't really like like very vague strategy. As

you can probably tell from this channel, I really prefer to give all of you guys just like really practical things that you can copy right away. So basically

the learnings.m MD think of it as kind of like a change log of learnings that AI has learned from me over time through all the conversations that I have with it about my business and life. And the

skill.md has a reference point to look at this file before it gives me any new advice. Now let's move on to the last

advice. Now let's move on to the last file which is the eval.

And this is basically a yes no checklist that my advisor runs before giving me advice. So mine has about 20 checks, but

advice. So mine has about 20 checks, but here are three of the most useful ones, right? So first one is did it read the

right? So first one is did it read the latest context before giving me advice?

Did it actually read learnings.md and

plan MD? Second one is did it site my actual goals, principles, and recent updates before giving me advice. Good

advice should be personalized to me, right? And another checklist is did it

right? And another checklist is did it give two or three concrete next steps? I

don't I don't really just want generic advice. I want something that I can

advice. I want something that I can actually do this week. So if the advice is vague, then this eval fails. So

basically the eval forces AI to slow down and check whether it actually use my context, name this assumptions and give me advice that I can act on. It's

going to keep checking these 20 evals and only when everything is marked as yes will it actually give me advice. All

right. So, I posted this on X recently about how amazing Anthropic's new fable model is at using this personal advisor scale and unfortunately the model got restricted by the US government right

after it. So hopefully it'll come back

after it. So hopefully it'll come back at some point because using the best model really does make a difference in giving you detailed practical advice. I

actually want to show you guys the advice that I got from Fable. I was

lucky enough to save it into a document before the model got banned. So here's

the detailed advice that it gave me for things like how to grow my pay subscribers.

It read my plan and learnings and then did outside research on other newsletters, YouTube channels, and AI product creators. And it found a lot of

product creators. And it found a lot of really great insights that other models couldn't find like the fact that renewal is actually the bottleneck for growing pay subscribers, improving retention,

and also the fact that Substack notes was underused. similar creators were

was underused. similar creators were posting to substack notes multiple times a day to grow faster. So overall, I was just really impressed by how Fable was able to combine my personal context from

this skill with outside research to help me see opportunities more clearly.

Hopefully Fable comes back by the time this video drops, but if not, you can always use the next best specs model like GPT and Opus is still very valuable if you set up the scale correctly. All

right, so let's recap the files that you should work with AI to create to make your personal advisor. You got to make a skill.m MD. Tell AI what role to play,

skill.m MD. Tell AI what role to play, what files to read, and how it should give you advice. Then you should make a plan MD, which is just your goals,

principles, energy, business life, and financial situation.

Next, ask AI to make a learnings.md,

which is just saving short notes to this file whenever it learns something meaningful from your conversations. And

also make a eval, which is creating a short yes no checklist to check itself before giving you advice. So, examples

of this checklist include grounding its advice on your plan, on your learnings, giving concrete next steps, and more.

Whatever you want it to check before giving you advice, right? And like we just covered, you should try to use the best model that you can when you're running this skill. So just to make this

super practical, I've uploaded my full advisor skill to behindthecraft.com where you can find a dozen other skills built with the same quality bar. Now

behindthecraft.com is available to pay subscribers of my newsletter. Otherwise,

the next best thing to do for free is to just copy and paste the entire transcript of this video into codeex and clock code and ask it to walk you through setting up the skill. I also

linked the newsletter post that you can copy as well. I don't think there's any exaggeration when I say that my AI advisor has fundamentally changed how I make important decisions. I feel like I

never have to make an important decision alone now. I always have my adviser to

alone now. I always have my adviser to consult along the way. And I hope that yours has the same transformation for you. So definitely don't give up until

you. So definitely don't give up until you set this up for yourself. All right,

so that's it. Please like and subscribe if you enjoy practical nobullshit tutorials like this. and I'll see you next time.