Dan Martell - You’re Not Behind (Yet)： How to Build Your First AI Agent (Full Guide)

00:00:00.080 I just read a study that by 2030,

00:00:02.280 AI is going to create 170 million new jobs,

00:00:05.560 but they won't be jobs where you just sit there

00:00:07.400 and chat with AI.

00:00:08.480 There'll be jobs where you build AI agents.

00:00:11.200 And I get it, the AI space is moving crazy fast.

00:00:14.000 I mean, what even is an AI agent?

00:00:16.360 Not too long ago, I was right there with you.

00:00:18.440 But after going deep myself and building dozens of agents,

00:00:21.880 I found out it's actually way easier to build

00:00:24.040 and manage these agents than it looks.

00:00:25.920 So much so that my whole team and I have hundreds

00:00:28.840 with AI agents doing 92% of all the work across my companies.

00:00:32.640 So today, we're gonna go through every step

00:00:34.800 on how you can build your first AI agent,

00:00:36.720 starting with AI chatbot versus AI agent.

00:00:41.040 A chat is like a meeting.

00:00:43.000 An agent is like an employee.

00:00:44.800 Chat is you ask it a question and then you get an answer.

00:00:47.260 And a lot of people just copy and paste things

00:00:48.760 and do something with it.

00:00:49.600 With an agent, you actually tell it what you want to do

00:00:52.420 and it runs the full workflow.

00:00:54.420 Think of it like these are the body parts.

00:00:56.400 I call it data.

00:00:57.640 So one is D, it can diagnose.

00:01:00.420 It can actually figure out what the problem is

00:01:02.900 and solve it on your behalf.

00:01:04.280 Kind of like hiring a consultant.

00:01:05.660 Next is A, it can assemble.

00:01:07.920 It can build a plan.

00:01:09.360 It can design tools.

00:01:10.680 In that way, I think of it like an architect.

00:01:13.220 It knows all the different pieces

00:01:14.760 that it can pull together to get something done.

00:01:16.780 Next, we have T, it can take action.

00:01:19.560 And that way, I think about it

00:01:20.460 like somebody that executes tasks.

00:01:22.760 And finally, A, it can assess.

00:01:25.560 It can check its own work,

00:01:27.220 see where the opportunities are,

00:01:28.920 and then make sure that it landed on the right answer.

00:01:31.060 And if not, it can review itself and make itself better.

00:01:33.760 This whole thing is called a loop.

00:01:35.720 And without a loop, an agent would just do the job

00:01:38.260 and then stop, that's called an automation.

00:01:40.260 But with an agent, it keeps learning,

00:01:42.020 it keeps getting better, it kind of acts like a person.

00:01:44.840 With chat, it pulls on us, it's ask us,

00:01:47.140 what do you want me to do?

00:01:48.040 We prompt it and then we wait.

00:01:49.560 With an agent, it pushes on us.

00:01:51.280 It's doing things and changing things all the time

00:01:53.460 and it's checking in to make sure

00:01:54.820 that it did it the right way.

00:01:55.860 so you might be able to buy back your time with chat but you'll actually learn to let go of whole

00:02:00.180 areas with an agent but how do we even know if it's worth giving something to an agent instead

00:02:04.660 of just doing ourselves for that i use the rule of r the first one is repetitive is this a task

00:02:10.340 that i'm going to do every week two is rules base does it take the same input and generate the same

00:02:15.300 output every time the third is does it generate a return on my time for the amount of time it takes

00:02:20.020 me to build this thing i'll show you how will i actually get my time back if the task takes two

00:02:24.660 minutes but it would take me two weeks to build this agent how about i just keep doing the two

00:02:28.100 minute task but if you think about it and the task is only done once in a while doesn't follow

00:02:32.820 a clear process or get to a specific outcome and doesn't save you more time to automate it than

00:02:37.540 just doing it manually then stick with what you got use the chat so now that we know the difference

00:02:42.420 between chat and agents how do we build one to make an agent it's super easy and i even turned

00:02:47.860 it into an acronym called agent and the first step is a which means aim for a specific outcome

00:02:55.060 when i'm sitting down and i'm like i want to build an agent for this i have to first ask myself what

00:02:59.780 is the specific goal start with the outcome the agent is going to give you it's like if i'm

00:03:04.980 climbing a mountain taking a step is the task getting to the top is the outcome i want to define

00:03:10.340 the outcome and be really crystal clear because the cool part with ai and agents is that the ai

00:03:15.380 can actually figure its way there this is why creating ai agents is hard for people because

00:03:20.340 they want to control every step but the truth is it may know how to get there way better than

00:03:23.940 you can figure it out think about it like when you hire a person you say here's your job when

00:03:27.860 they applied for the job they had these specific outcomes that they would need to accomplish like

00:03:32.180 grow the business or get more customers or sell and get people to buy from you those are the

00:03:36.660 outcomes you don't start by telling them how to do the job you tell them what you're gonna need

00:03:40.500 from them that's the outcome aim the agent at the outcome you're looking for so like how do we make

00:03:46.340 sure we're being clear to the agent about what kind of outcome we want to achieve the first is

00:03:50.020 we got to give it the why before the how tell it why you're trying to achieve the goal so that it

00:03:55.460 can make some smart decision on its own to make this really easy for you i'm gonna use an example

00:04:00.900 we're gonna build together an agent to manage your inbox as an outcome i would prompt it and say i

00:04:06.500 need to spend less time managing my email inbox see how i'm not telling how to do it yet i'm just

00:04:11.140 saying this is the outcome the second is we have to write what's called a dod or a definition of

00:04:16.820 done it's giving them the instructions to know if they achieve the thing we want to be specific we

00:04:21.060 want it measurable ideally you have it in one sentence so for example building our agent for

00:04:25.620 our inbox we would not say handle my emails instead we would say done means every morning

00:04:30.900 at 9 a.m the inbox is empty replies are drafted in my voice and anything that needs me is flagged

00:04:36.180 to the top and nothing important slips if you can't picture it done the agent can't hit it it's

00:04:41.700 like a target they can't see and finally we got to start with the end and it's called reverse

00:04:45.940 prompting but we want to tell it the results that you want then we tell it to ask you the question

00:04:51.540 it needs to get full clarity this is the advancement this is what nobody out there is

00:04:55.460 teaching you then we let the ai do its thing because it's better than us and a lot of stuff

00:05:00.340 and it builds the plan itself and the truth is if we can't state the outcome in one sentence we're

00:05:05.300 not ready to build if you can talk the task like explain to somebody else then the ai can do the

00:05:10.580 task and the cool part is you knowing this already puts you ahead of most people using ai today even

00:05:16.260 folks you're like oh this person's so smart they don't know this stuff and we're just getting

00:05:19.860 started so we've got the agent it has its reason we have a clear target and now it has clarity and

00:05:26.100 now the next step is g give it an identity truthfully out of the box ai knows a little bit

00:05:32.820 about everything but it doesn't know anything specifically well so an identity allows us to

00:05:38.580 focus its power in the right expertise so when we build the identity instead of it knowing a

00:05:43.380 little bit about everything it gets really sharp about that one thing that you've hired slash built

00:05:47.700 it to do and the best part is that the tighter we define who it is the better it works the better

00:05:53.140 the outcome is the better the agent is an agent i remember reading a report where they built a

00:05:57.780 bunch of ai agents to do customer support for an airline and then they removed all the rule books

00:06:02.980 its identity from the agent and it dropped from 33 success rate down to 11 so we're talking same

00:06:09.700 model same task same request and it got three times stupider because it forgot who it was think 0.55

00:06:15.540 of your agent as a genius and he's sitting at a desk and he's wearing a blue shirt and he's got

00:06:20.100 great hair this genius has infinite potential but until you tell them the job they just sit there

00:06:26.100 doing nothing because they don't know what they're supposed to do so what we need to do

00:06:29.220 is tell it what his job description is and set some rules for how to do the work so this is how

00:06:33.300 we create the agent's job description using three plain english files the first one is the soul

00:06:39.220 file right it's the agent's personality i have a lot of fun when i create my agents i tell it

00:06:44.580 what kind of quirks i want what kind of values does it have how does it talk it's essentially

00:06:49.060 defining how it behaves the second file is the identity file that's its dna that's its name

00:06:55.220 that's a description of its role for example one of my primary agents his name is kai i just worked

00:07:01.540 with him for two weeks and we built a bunch of stuff and i said hey man it's time for you to

00:07:05.540 give yourself a name because i feel weird not knowing who you are and he's like oh how about

00:07:10.500 this and here's why and he gave me all the reasons and i said cool update your identity file so now

00:07:15.380 he knows who he is to the world the third is the user file and this is the context your agent needs

00:07:21.060 to know with you it knows who it's going to be interacting with so it can adjust its loops to

00:07:25.460 get better for you so for example in this file you might have your goals your role how you like

00:07:30.020 things done but essentially it defines who we are the sole file is how it behaves the identity file

00:07:35.540 is who it is and then the user file is who we are now here's a pro tip don't write these files

00:07:40.900 yourself no no no let's tell ai to write it as we build the inbox agent here's the prompt that

00:07:46.580 you use to generate them i want to build an ai agent that runs my inbox your aim from the previous

00:07:51.860 step we insert that there create its three identity files a sole file an identity file

00:07:56.580 and a user file and ask me any question you need to fill these in accurately then write all three

00:08:01.460 notice we did the reverse prompting where we asked it to ask us questions so now it'll go do

00:08:06.740 the research and then it'll hand back a template that is 99 awesome and complete for example here's

00:08:13.140 Here's what our inbox agent identity files

00:08:14.980 might look like after the AI interviews you.

00:08:17.740 Soul file, how it behaves.

00:08:19.420 Writes in my voice, concise, direct, zero corporate fluff.

00:08:23.900 Calm and reassuring, never pushy or salesy.

00:08:27.100 And avoids phrases like,

00:08:28.480 I hope this email finds you well.

00:08:30.320 Of course it found you well.

00:08:31.380 When it's unsure, it flags instead of guessing.

00:08:34.380 Identity file, who it is.

00:08:35.920 It has its name, Amelia.

00:08:38.100 E-mail-ing-ya. 0.51

00:08:39.700 See what it did there?

00:08:40.480 Isn't it cool?

00:08:41.040 It's got personality.

00:08:41.760 The role, personal inbox manager.

00:08:44.440 The job, you read, you sort,

00:08:46.940 you draft replies to every new email.

00:08:48.880 Lane, this is the parameters.

00:08:50.680 Inbox only, never touch my calendar.

00:08:52.960 Don't you touch my money or anything outside my email.

00:08:55.800 Now we got the user file, who it works for.

00:08:58.040 I'm a founder who gets around 100 emails a day.

00:09:00.580 We prioritize people, my team, my current clients,

00:09:03.600 my VIP list.

00:09:04.640 I have multiple AI companies, a media company,

00:09:07.100 it might list them all.

00:09:08.020 With these three files,

00:09:09.080 our inbox agent knows how to behave,

00:09:10.900 who it is, and who it's working for.

00:09:13.220 And look, building one agent changes how we work.

00:09:15.460 But if you're a CEO or founder,

00:09:16.980 the real unlock is a whole team of them.

00:09:19.480 That's why I put together my full AI company OS playbook.

00:09:22.340 It's the best way to plug AI agents

00:09:23.780 into every single department in your business.

00:09:26.140 If you want it, just DM me the word AI business on Instagram

00:09:28.940 and I'll send it right over.

00:09:29.960 So now our agent knows the job it needs to do,

00:09:32.140 but we haven't given it the necessary tools

00:09:34.040 to do the job with.

00:09:35.240 This is where we gotta go to E, which is equip it.

00:09:38.500 Like any human team, an agent is gonna need some context.

00:09:42.400 It's gonna need some tools.

00:09:43.540 It's gonna need some logins to systems

00:09:45.340 so it can actually do its work.

00:09:46.440 When we give our agent the context, the history,

00:09:48.880 the data, the tools,

00:09:50.020 that's actually when it gets to do the real work.

00:09:52.260 And in all agent design, the context is the moat

00:09:55.740 because garbage context in, garbage context out.

00:09:59.120 Think of this whole desk

00:10:00.420 as what's called the context window.

00:10:02.360 I am the AI, the LLM, and I'm the genius,

00:10:05.560 and I'm sitting at the desk.

00:10:06.500 Over here, I've got my playbooks.

00:10:09.000 These are the processes and procedures

00:10:10.540 on how to do my work.

00:10:11.780 On top of it, I've placed my identity files,

00:10:14.120 the things we just created so that I understand

00:10:16.040 how I'm supposed to behave and who I'm working for.

00:10:18.680 This is like my constitution.

00:10:20.580 And then over here, I've got the tools.

00:10:23.240 These are the laptops, the monitor, the mouse,

00:10:25.880 anything I need to use to connect to other systems.

00:10:28.040 And above that, I've got my loops.

00:10:30.020 These are the schedules, the heartbeat

00:10:31.800 that I talked about earlier so that I know

00:10:33.520 when I'm supposed to get things done by.

00:10:35.100 It's like the calendar.

00:10:36.220 it's my schedule and then under the desk is where i have my filing cabinets this is my memory this

00:10:41.740 is where things that can't fit on my desk sit so that it's available but i'm not creating clutter

00:10:47.580 on my desk if you've ever heard a context rot that's when you just load the desk with a bunch

00:10:52.620 of files and it becomes complicated and i can't find things quickly and all of a sudden i'm

00:10:56.060 answering questions but i'm not clear about it because i'm not certain about it whereas a clear

00:10:59.740 context window is when everything on the desk is neatly put away so that i can refer to it so that's

00:11:05.980 why we have to equip our agent with the right context so now that we're here how do we equip

00:11:11.660 the genius agent with all the right context and the tools first off we have to capture our processes

00:11:17.100 so we can let it know how to do the work for this i've got two ways the first way which i've been

00:11:21.660 teaching forever not the best way is the camcorder method you do the work you record yourself using

00:11:26.780 zoom video or any kind of recording software and then you can give that to an ai to turn it into

00:11:31.820 a playbook and then you feed that to the agent as like a procedure think about our inbox it's like

00:11:36.460 do you have a documented process for how to label your emails and triage your emails and write

00:11:41.020 replies on your behalf just make sure that when you're recording yourself you're talking through

00:11:44.620 the task so that when the ai takes that to create the playbook it has all the details the better

00:11:49.100 way and this is my recommendation is to reverse engineer it from the source if i'm building an

00:11:54.300 agent to manage my inbox i can actually connect using the connector tool to my email in my case

00:11:59.900 gmail and ask the ai to reverse engineer and create a playbook based on historical emails

00:12:06.540 see you've already been in your inbox replying and doing stuff the ai can actually use that to

00:12:10.860 train itself and that is actually the way i build most of my agents if i have the source information

00:12:15.820 i just ask it to learn how i've done it in the past and then create a procedure go find the

00:12:19.820 pattern go find the best practices go find the little intricacies based on how i've done it and

00:12:24.060 all the people in the relationships and you write that file so for example if you want the prompt

00:12:28.060 to do this here's what you write connect to my email read the last 50 messages that i've sent

00:12:32.700 study how i actually write my tone my greetings how i do sign offs how long my sentences are the

00:12:38.380 phrases i use most often then write a style guide that captures my voice and tone and to test it

00:12:43.020 ask it to draft a reply on your newest emails that are unread as you based on what it learned then

00:12:48.060 you can rewrite those so that it can use that to learn and tighten it up like it already knew who

00:12:52.940 it was in the best practice based on its research that's in the soul file but now it has clear

00:12:57.500 templates the step-by-step instructions and even examples that it can use to do this on your behalf

00:13:02.460 so now that it's captured all the information it still hasn't kind of solidified it into an actual

00:13:07.180 playbook and that's what we call a system prompt so then what you do is for each sub process in

00:13:11.900 the agent's activities like drafting emails but maybe it needs to sort emails you can have it do

00:13:16.540 the same activity either you tell how to do it or it researches and then it creates all these system

00:13:21.980 prompts based on the work you need it to do. Like I have it for my inbox, sort, reply, forward,

00:13:28.100 that's a big one, and even escalate things that it needs to show me and the reporting I want every

00:13:32.660 day. So then at this point, you actually have an AI agent running. This is exciting stuff.

00:13:37.980 You might feel right now, you're like, oh man, I'm going to give everything I got at it. Don't do

00:13:41.700 that. The N in the agent framework is to narrow the scope. The agent needs to have a narrow scope

00:13:48.160 of what it does so it doesn't confuse itself if you start asking it to do 17 other things then

00:13:52.640 all of a sudden this desk can get really busy which means it's not going to be a great agent

00:13:56.720 anymore just like you wouldn't give your administrative assistant the responsibility

00:14:01.120 to do marketing and take sales calls you want to make sure the scope is narrow for each agent

00:14:05.760 as an example i have an agent that writes code and then i have an agent that reviews code and

00:14:09.760 those are separate agents and they work together see how narrow the scope is we need to focus the

00:14:14.720 agent down to one specialist per job each agent great at one thing instead of having one agent do

00:14:21.040 everything which is what people usually do that's a mistake we'll have sub agents that do specialized

00:14:26.400 tasks under it that way it keeps all the context for the agent super clean it doesn't get confused

00:14:31.840 we don't have context rod we don't want to have a mega agent instead we need to spread out the task

00:14:37.120 to other sub agents so that it can handle other agents below it so for example kai who's like my

00:14:42.800 orchestration agent he's the one that not only creates other agents he also coordinates the

00:14:47.680 tasks of the different agents like my research agent and my relationship agent and my coding agent

00:14:52.480 and my reporting agent he then he pulls it all together and gives me answers so instead of giving

00:14:57.520 every task to one agent this is what we should do instead we build a manager agent its only job

00:15:02.960 is literally to manage and specialize in the management of the sub-agents think of it like

00:15:07.280 a real manager agent you are my manager agent i need you to manage my sub-agents and i need you

00:15:12.160 to make sure that you monitor the jobs and make sure they're moving along and if they're not

00:15:15.840 working you fix them and you decide what agents need to exist so for example we built our inbox

00:15:20.800 agent but we don't want to have to manage the inbox agent we create a manager agent that talks

00:15:25.600 to the inbox agent that might be responsible for a lot of different things like our inbox but also

00:15:30.320 sending stuff to other people on our team but we want to make sure each sub agent reports to that

00:15:34.480 manager agent so that it takes care of it so you might want to give it a prompt like this you're

00:15:38.480 my manager agent you never do any tasks yourself when it comes in you only move it to other sub

00:15:43.760 agents that are dedicated for that one specific job you hand it the task and then you let it run

00:15:49.120 so it's like one agent one lane and if a job touches multiple areas split it into the separate

00:15:54.160 sub agents one per area you're the one that coordinates and reports back to me like i said

00:15:59.200 mine's called kai he's awesome i talked to kai kai talks to all the sub agents i have one agent i

00:16:05.120 I got to talk to. If you want a pro tip, and I don't want to overwhelm you, but there's different

00:16:08.880 AI models. So for example, within Anthropic, you have Haiku. This is like for simple and high

00:16:14.780 volume stuff. If you want to sort things, you want to label things, quick draft, and it's the cheapest.

00:16:18.800 Then you might go to Sonnet. Sonnet's great for like day-to-day work, research, writing most code.

00:16:23.220 At a higher level, you've got Opus. This is a powerful model, good at reasoning, complex builds,

00:16:28.260 being a manager of agents. But now you have Fable, and that just dropped a few weeks ago. That's more

00:16:32.740 like an orchestrator a consultant it has full capabilities of opus but it's even more state

00:16:38.660 of the art it's extremely good at long running tasks and real complex things when you don't have

00:16:43.620 a lot of information to give it but it's the most expensive so depending on your task you might want

00:16:48.740 to give it different models because it'll cost less and it may not need that level of horsepower

00:16:52.660 to get the work done so for example my inbox agent since it's always running every 15 minutes

00:16:56.900 i just use sonnet because i don't need an opus level genius to run a process that we've already

00:17:01.380 defined to build the agent i might use opus that way it helps me create it i might even use fable

00:17:06.660 but then to run it i'm gonna run it on sonnet one time i had to do this whole refactor on my code

00:17:11.060 base and i could use a powerful model like opus it probably would have cost me 150 bucks instead

00:17:16.020 i use haiku and it only cost me a dollar fifty as of today here's a chart with gpt and other ai

00:17:21.700 equivalents that it's on screen so you can just take a screenshot of it to help guide you but

00:17:25.060 this is now changing every couple weeks if you've made it this far and you're still interested

00:17:30.020 congratulations but i need you to know something you're literally ahead of 99.999 percent of the

00:17:35.380 people out there and you're crushing it we've learned to aim the agent at an outcome give it

00:17:39.940 an identity so it knows its job equip it with the right context and tools so it can do the job and

00:17:44.740 narrow the scope so it doesn't get overwhelmed and instead use sub agents to accomplish specific tasks

00:17:50.500 now this last step is where our agent truly becomes autonomous t and it stands for trust

00:17:55.940 because we got to do it in stages.

00:17:58.500 Building an agent is actually the easy part.

00:18:00.720 Once you understand how to do that and you prompt it,

00:18:02.600 it just gets done.

00:18:03.540 The scary part is letting it act without us.

00:18:06.440 And I understand, especially as we talk about our inbox,

00:18:08.760 having somebody else write emails as you calm down.

00:18:11.940 I'm not doing that.

00:18:12.760 I'd rather it give me some ideas for copy.

00:18:14.760 The truth is, is we don't give the agent

00:18:16.380 the keys to the car on day one.

00:18:18.200 And what we do is we like give it stuff, see what it does.

00:18:20.440 Then we see if its response is what we expected.

00:18:22.560 If we do this right, you sleep well at night.

00:18:25.120 If you don't, you will not sleep.

00:18:27.500 The whole point of creating an agent

00:18:28.960 is so that you can go do other stuff.

00:18:30.940 If you're sitting there babysitting

00:18:32.080 or worrying about it all the time, it doesn't help you.

00:18:34.140 So up until now, we've let the agent

00:18:36.620 help us manage some emails.

00:18:38.840 Think about it.

00:18:39.360 First, you might sure it's doing his job properly.

00:18:40.920 When we tested it to write those drafts to unread emails

00:18:43.660 and we looked at how it did it.

00:18:44.900 At first, we're micromanaging him a lot,

00:18:47.400 but then we gotta learn to trust in stages.

00:18:49.940 So maybe the first stage is just like,

00:18:51.580 hey, can you sort the email?

00:18:52.940 And then we see what it does and we're like,

00:18:54.060 okay, that's good.

00:18:54.680 Then we like ask him to do more drafts.

00:18:56.660 So we already tested it, but now let's let it really do it.

00:18:59.040 So now it's running drafts and we're like,

00:19:00.600 okay, I like those drafts, change this, do this.

00:19:02.840 Okay, now it's doing its thing.

00:19:04.100 Then we might let it start sending emails on our behalf,

00:19:06.540 but not all of them.

00:19:07.560 Maybe just even forwarding emails to finance,

00:19:09.860 to our team, because it has the logic.

00:19:11.760 It saw how we handled those emails in the past.

00:19:13.720 Maybe it categorized certain emails

00:19:15.240 like Slack notifications into a specific label.

00:19:17.340 But eventually we want this genius

00:19:19.740 to manage our whole inbox without us even opening it.

00:19:23.220 that's the equivalent of us leaving the room and having the agent at the desk do all the work for

00:19:28.600 us because at this step we learn to let go we've trusted it fully because if you don't do this it's

00:19:34.860 like hiring a driver to drive your car and you got your hand on the wheel now we got to take our hand

00:19:39.060 off the wheel and let the driver drive here's how you can do it in a really safe way you set the

00:19:43.780 guardrails first you can actually set that up in its identity files what is it capable to do on

00:19:47.780 our behalf maybe it has the ability to spend money maybe it has the ability to make decisions maybe

00:19:51.820 has the ability to write drafts only not send yet it's always your call and you can define those

00:19:56.380 two approve everything at first i've never created an agent and was like yolo go nuts no

00:20:02.380 show me what you would do i like what you did do it again tweak it just like i just talked about

00:20:07.020 for our inbox agent third we loosen the leash right it's like a dog you're walking with and

00:20:11.980 you're like hey i trust you more i trust you more and all of a sudden the leash goes limp but he

00:20:15.260 still holds the heel and then four would be give it a heartbeat that it can run on its own set up

00:20:20.860 that schedule that reoccurring tasks so maybe before did it once and you reviewed everything

00:20:26.220 now i might do it every 15 minutes you know every morning at 9 a.m it did it once now why are we

00:20:30.940 waiting why we wait until the next day why don't we have it run all the time this process is scary

00:20:35.420 but the whole point of learning to let go is to buy back our time to have the agent do the work

00:20:40.220 for us and learning to let go is part of the process if you trust so for example when i showed

00:20:46.700 this agent to my executive assistant she thought she was out of a job instead it actually freed

00:20:51.020 her up to do things that actually mattered not sorting emails and writing drafts or telling me 0.98

00:20:55.660 what's in there the ai can do that i'd rather pay her to do higher quality work manage higher level

00:21:01.500 projects then we rolled out the same system to the whole team i taught everybody how to do this

00:21:05.660 now i want to say congratulations we just tackled the topic that most people don't even want to

00:21:10.780 learn they're like that's not for me i hear about agents i don't get it i'm confused but no you

00:21:15.180 didn't you went all the way till the end and i want you to understand that you might feel a little

00:21:19.260 behind in this ai world but here's where i've gotten to i've accepted that i will always feel

00:21:23.900 behind and i could never be on top of all of it but you just learned a strategy a shift a different

00:21:29.340 way of doing work that if you can learn how to direct the ai you will co-create with it if you

00:21:34.780 don't don't be surprised if one day you might be working for it remember the rules of art repetitive

00:21:39.740 rules base and return on time that's where we want to start looking for opportunities to put

00:21:43.580 an agent in there instead of you keep doing it and i'm gonna give you the pro tip of all pro

00:21:47.500 tips you grab the link to this video you give it to your ai and you tell it to use everything

00:21:52.860 i've shared to create the ai for you and watch it cook because it can do it now here's what i

00:21:58.860 want to know from you we have some fun below in the comments answer this question if an ai agent

00:22:03.740 could manage your inbox and buy you back all this time scheduling things on your behalf what would

00:22:08.300 you have more time for i'm curious post a comment below and let me know and if you want my whole

00:22:12.060 system, the playbook that I use to manage AI and all my different businesses, just DM me the word

00:22:16.920 AI business on Instagram and I'll send it right over. And if you want to know what AI businesses

00:22:21.080 are worth starting in 2026, click here and I'll see you on the other side.

Dan Martell - July 15, 2026

You’re Not Behind (Yet)： How to Build Your First AI Agent (Full Guide)

Episode Stats

Summary

Transcript