LongCut logo

How To Build a Startup Team of AI Agents (n8n, OpenAI, FeedHive)

By Simon Høiberg

Summary

Topics Covered

  • AI agents replace over half my startup team
  • Fine-tuning AI is crucial for quality output
  • AI agents need brand briefs, not just prompts
  • Automate content creation with an AI agent team

Full Transcript

this was my startup team in 2024 we were nine people in total but this year we only four people

left I replaced more than half of my team with AI agents and in this video I'll show you how you can create your

own AI startup team yes you can do this without riding code every business is going to have a um an AI agent that their customers can talk to agents will

begin to deliver on hype I got to tell you K opportunity for agents is gigantic as we AI agents are AI systems that can do work for hundreds of millions of billions of different AI agents billions

of different AI agents whether you think this is good or bad AI agents are here and you can be certain that they're here to stay millions of jobs worldwide will

soon be replaced by AI agents and thousands of tech companies and small startups will reduce their headcount and their dependency on human labor it's very likely that startup Founders just

like myself can go back to basics and become a solopreneur running everything as a oneman business without reducing the output and without losing revenue and for you the upcoming founder who

wants to run a SAS business but is blocked by the sheer thought of having to manage a team this is incredible news we're still very early so don't miss out

on this opportunity let's get ready cuz we have work to do in this video I will show you step by step how you can create a fine-tuned specialized AI model how

you can use it as an AI agent and how to make it collaborate with other AI agents on your team let's get started one area of work I replaced with AI is content

creation I used to have people help me write content for social media for my weekly SAS newsletter and my YouTube scripts so in this video we'll set up an AI agent that creates content for social

media though the process I'll demonstrate here can be used for almost any type of task you typically run into on a startup team fortunately open AI

has made this incredibly easy for us we can just ask chat GPT to generate some content right hey chat GPT can you create a

banger post about SAS and Entrepreneurship for me please sure how about this exciting times in the world of SAS and Entrepreneurship every day presents new opportunities to innovate

and lead in this dynamic industry uh that's no that's not something I would post uh try again please okay how about this feeling

grateful for the amazing journey of SAS and Entrepreneurship here's to more coffee fueled brainstorms and chasing dreams that's really tacky and lame and

what's up with all the Emojis no all right all right I got you leveraging and utilizing synergies in the existing realm of SX you know what thank you this

is not going to work so it turns out we cannot just ask chat gbt to create content for us and expect it to create anything of good quality and many people

who try this will stop here they'll conclude that AI is bad it's generic poor completely lacking substance and so on but let's just back up for a second

and compare this to hiring a new employee If you hired a Content writer and you gave them no onboarding access to no brand guidelines no initial instructions and just ask them to create

a post about some topic how do you think they do do you think you would magically be happy with their first result or would you expect them to First learn about your brand your core values your

style of writing and the history of your company and then start delivering good results cuz that's exactly what we need to do to prepare our AI agent now I've seen many different approaches to this a

common method is including examples and instructions in the system prompt or the first message of the conversation it rarely produces good results that's why

most of the custom gbts suck cuz that's exactly what they are it's just a chat gbt with some instruction in a system prompt injected into the chat before the conversation starts these are not AI

agents even though some people incorrectly call them that we need to fine tune a model in essence instead of explaining

what the AI should do we will show it a whole bunch of examples of what an out outut should look like fine-tuning an AI model is the process of specializing an

AI by training it on specific data so in this case we will prepare examples of social media content it can be your own content it can also be content from other creators that you really like we

should put together 20 to 50 good examples now for each of them we need to reverse engineer The Prompt so take this post and imagine chat GPT generated this

what would the prompt have looked like probably something like this perfect we need to repeat this for all examples if you want to save some

time you can actually ask chat gbt to reverse engineer the promps for you in most cases it actually does quite

well now let's head over to platform.

open.com and sign in with your chat DPG account click fine tuning in the left side menu and click create this is where we create our fine-tuning

job but before we can upload our training data we need to turn it into this specific format called Json L it's Json and it's one example per line if

you're a programmer you can write a quick script to automate this if you don't know what Json is just follow my lead here for each example we need one

line on this specific format we have a field called messages which is a list that has two messages one from the user that will be our [Music]

prompt and one from the assistant which would be the reply from the AI if you want to include the line breaks as part of the data you just need to use back

sln there we go once we have all our training data in a Json L file we just need to upload it choose the base model I recommend

using gbt 40 and that's it we can leave everything else as is and click create now open AI will start training

your custom model once it's ready we can go to the playground and try it out so let's try again create a post about SAS and

Entrepreneurship okay let me see I was failing SAS until I finally understood this your team should be remote you should work async taking VC money is your best

bet awesome that sounds exactly like my way of writing love it wait a minute well what was that last line taking VC

money is your best bet no no we can't have that I'm all about bootst startups so we can't have that thing with VC money ah okay got it got it how about

this one I was failing SAS until I finally understood this the easiest way to create a bootstrap sass is using Cloud tools like versel or netfi no no

no absolutely not you sound like me okay but you're saying things I would never say and this is our next problem now we have a fine-

tuned model that has learned to adopt a specific writing style but it's not really that valuable if it doesn't know what our brand is all about it needs to know which core beliefs and opinions to

adopt which common themes can be found in our content which hot takes to drop and which values to align with and this is not exactly something we can find you in our way out of instead we're going to

do exactly what we would do with regular employees we should write a brand brief in plain English this brand brief should provide clear writing guidelines

describe Our Brands in terms of core values content themes and objectives dislikes and opponents Associated products and services and other areas of

our brand write this in a text file notion page a Google doc or whatever you prefer if you've never done this before or you haven't really thought about your personal brand in this way I actually

think it's a great exercise to spend some time writing all of this down but again if you want to save some time you can have chat GPT do this too simply

take all of the training data you used to find through your model in the previous step upload it to chat GPT directly and ask it to create a brand brief given these posts then edit it to

your liking and simply use that for now I've written my brand brief in text file and if we head back over to the playground we can now upload this file Island ask or fine-tuned model to use

this brand brief as a base for creating our posts I have to say this is really good content no one likes a feature creature

how did you come up with that well I guess I learned from the best ah I think you will fit in very well on this team though not going to lie it's a

little bit timec consuming to have to ask you to write every single post can't you work a little a little bit more autonomously I would love to Simon but

I'm just an AI model I can't do anything on my own initiative or make any active decisions all I can do is answer you when you ask me for something so far

we've solved two major shortcomings of the normal chat gbt we fine- tuned a model to write in a specific way and we taught it about our brand to understand

what we're all about it now knows what to say and how to say it but it's still not an AI agent it doesn't do anything on its own and it doesn't make any

decisions to be fair at this stage is still very useful I've been using this exact setup for a long time and it has been tremendously helpful but it's also been very timec consuming chatting with

my fine tuned model refining giving it feedback copy-pasting the results into feed hiive my social media tool and so on so at some point I got this idea what

if I created a small team of AIS and gave them the agency to collaborate with other and push the final results into feed hiive all by themselves we can do better how about an engaging

question we should also use a more consistent tone of voice here's how it would work we want one AI agent to generate topic

ideas we want another agent to create a post from one of these topics we want a third agent to check the quality of the post and give feedback to the second

agent the second agent will use the feedback to refine and improve the post these two agents will go back and forth for a bit until they agree that

the post aligns with the brand uses the right tone of voice and is of high quality then finally push the post to feed High where it shows up under my

drafts let's set this up for this we need a tool called n8n n8n is an automation tool in the same family as sapure and make but just

way way better you can sign up and use NN in the cloud but you can also install it locally or selfhosted which gives you unlimited workflow runs totally free of

charge let's set this up in nadn Click create and then choose credential here you need to add the credentials to the apps you want nadn to

access such as notion Google Docs open Ai and so on you will at the very least need to give nadn access to open AI by adding an API key there are many Guides

Online on how to do this so moving forward I will assume that you have set up credentials for all the apps you need so now that we have that done let's

start cooking we'll start from the smallest task and work back up in the NN dashboard create a new workflow let's call it brand

brief add First Step since this is going to be a subtask we will use when called by another workflow I have my brand brief in notion so let's add a notion

node we want to get all child blocks and add the URL to the notion Page hit test step there we go now because notion

outputs a page in blocks we want to aggregate at the parts we need so let's drag in an aggregate node what we're interested in is the content

Fields there we go we now have a simple list of individual pieces of text so let's add an edit Fields node drag in our content list we want

the final output to be one piece of text so we'll change this to string and after content we'll simply write do join and there we go this workflow is

done let's move on create new call it get content ideas once again

use when called by another workflow now in order to get ideas we first need the brand brief so we'll use a call another workflow

step and we'll choose the brand brief workflow we just created let's rename this to get brand

brief awesome next let's add a simple open AI note called messageer model for this task we can simply choose

GPT 40 Mini in the text field give the model a prompt that describes what it's supposed to do we'll tell it to create 10 topic suggestions that aligns with the

provided brand brief we'll tell it to use a Json output format like this and we'll provide the brand brief from the step

before enable output content as Json let's try it out that's perfect and also here let's add an edit note and let's map this over

to a simple list called suggestions like that let's move on to the next workflow we call this get content

feedback it's similar to the workflow we just did so let's set up the execute workflow trigger and the get brand brief notes just like before this workflow is a

little different since it will take some incoming data namely the post to give feedback on so let's double click on the first node click set mock data then add

some data like this perfect and also here we want a node from open AI that messages a

model and also here we can choose gbt 4 mini this time we want to give the AI some rules to follow so let's change this first message to the type

system the role of this AI is to give feedback and ensure the quality of a post is good so we will simply give it some criteria to follow of course you should adjust this

to fit your specific brand the most important part here is to have the model give a score between Z and one and show it in the Json format we want to use for the

output let's make sure to include the brand brief and this time we want to add another message with the role

user and this will simply be the query from the first step also here we want to Output as Json and let's test

it perfect and yeah since this is just a mock input I'd expect the score to be pretty low here so that seems to work finally also here let's make sure to simplify the output a

bit there we go now we got everything we need let's put the whole thing together I'll show you how to do this but if you want to download and import all of these

workflows directly into your own nadn I will share access to these files with members of Founders dech I'll tell you more about this towards the end of the video create a new workflow let's let's

call it content creator for now the first step will be on chat message but we'll change that in a bit the next node will be an AI

[Music] agent now we need to give this AI agent three things a model memory and tools

for the model we'll use open AI [Music] and because we linked our open AI account we have access to the fine-tuned

model we created earlier for the memory let's just use window buffer now we need to give this agent some tools these tools are going to be

the workflows we already created so let's pick NAD and workflow let's give the tool a name get brand

brief let's describe and pick the workflow from the list we'll add the feedback tool in the very same

way there we go awesome now let's double click the AI agent we need to give this agent a description of its main

objective so we'll use system message and we'll give it a description similar to this a quick explanation of how we want it to

work how to use the tools we provided and which final output we expect now let's hit chat and try it out all right and we can see that the

models start collaborating going back and forth and there we go look at that really cool at this point the basic AI agent

functionality is pretty much done the agent has access to a fine tun model it has access to the tools it needs to access the brand brief and get feedback and because it's an agent it figures out

when and how to use these tools correctly given its task description this right here is an actual AI agent let's finish up since we want the output

of this AI agent to be passed onto another tool in my case feed hiive We'll add an HTTP request node here in feed hiive under automation we can

create a new trigger I'll call this AI content and pre-select a few social

accounts I'll grab the URL from here and add it to nadn we don't have images in this workflow so I'll remove the media url's

part and for the text I'll grab the output from the AI agent agent and simply add it here now every time the agent finishes a post it'll add it

directly to feed hiive where I can schedule it to go out and instead of this chat message input let's use the content idea task we

created we'll replace this with trigger manually We'll add a call another workflow node choose get content ideas from the

list there we go now let's add a split out node drag in the suggestions from the idea step now let's add a loop to Loop over

each item awesome now for each of the suggestions that was generated we'll trigger the AI agent flow but because the AI agent expects an AI chat input we

just need to add a temporary step here so once again edit fields this time let's use Json and we want an object that looks like

this for the session ID we use an inbuilt variable called item index the action should just be send message and the chat input will be the

suggestion we got from the idea generation step perfect we can feed this directly into the AI agent and after each Lube is done we

need to make sure to go all the way back to continue with the next item which is the next idea now all we have to do is Click test workflow and see the whole thing in

action the AI agents will start working and a bit of back and forth and finally off to feed five where the post will appear under

drafts highquality posts that are on brand using the right topics and using the right style of riding fully automated isn't that just

awesome also in case you didn't know feed hiive which is the social media management tool I used here is one of the sad products my team and I run and if you think all of this looked way too overwhelming and complex feed hiive

actually has a lightweight version of this exact flow built-in you can write your posts ask feed's AI to give it a grade and it will give you feedback and

suggest changes to make your post better to it's not using a fine-tuned model trained on your specific content so it's not as good as a custom setup like the one we built here but it's pretty solid

and a very userfriendly experience you can get lifetime access to feed hiive as well as three other tools my team and I run for a single onetime purchase they

all come with apis and automation they're all AI agent compatible go to founder stack. proo to check it out I'll

founder stack. proo to check it out I'll leave a link in the description now I know I ran through some of this pretty fast but I have put the full workflows together for you to easily import into

your own NN account and a step-by-step tutorial on how to set this up in an ocean dock if you are a Founder stack member you can go and access this right away I

have left the link in the description below all you have to do is enter the email you used to buy founder stack and you'll get access to this immediately if you want a more slow paced technical

introduction to n8n just Search Here on YouTube there are many excellent videos from creators showing you how to build all kinds of cool automation with these agents now I picked one example for this

video which is content creation but through this I'm using similar workflows for a whole range of different tasks I hope you got inspired thanks for watching

Loading...

Loading video analysis...