Pt 1: Building an AI Native Company | CoinFN

There’s a number of buzz and chatter about constructing AI firms however little or no know-how on how to take action. I assumed I’d define on this article what we’re doing for our new product line (following on from my final put up round sunsetting our analytics product). Let’s start! Regardless that you suppose you might know the place that is going, you in all probability received’t, so be certain that to learn by!

Most individuals get too caught up with “prompt engineering”. That’s leaping the gun when desirous about issues within the AI world. Context comes first. Nonetheless, when constructing programs it’s a must to be systematic and considerate about:

• The place the context lives lives

• How a lot is required for the duty

• What processes will permit it to be transferred

  

I wish to write this collection from the angle of what you need to do assuming you’re beginning a brand new firm/product so for any enterprise a very powerful context is the enterprise context itself!

You should use any framework you’d like however I discovered downloading one thing like this Enterprise Mannequin canvas that has staple items any enterprise ought to attempt to reply.

The explanation why you employ that is to be able to import it into FigJam to collaborate with one other staff member to jam on this collaboratively. Right here’s the above canvas crammed out but in addition the brainstorming that occurs round it.

So now that you’ve all this context crammed out and hopefully nicely thought out, you possibly can screenshot/save the crammed out canvas into ChatGPT with a easy immediate like:

Extract all the data from this canvas. Construction it in markdown withe every field being a title and be sure that all of the playing cards are extracted out in additional full sentences.

The output of it will then principally provide you with a considerably lengthy textual content output which is your uncooked context.

Now that is the place most individuals get it mistaken, they go away this context in ChatGPT or preserve including to it in that single chat. That is how context dies. As a substitute we’re going to do one thing completely different.

What’s the choice you might be asking? Properly the reply is git repositories! For these of you that don’t come from a software program engineering background, git is a protocol that permit software program engineers to collaborate on software program by permitting you to handle modifications, conflicts and many others. I received’t clarify extra right here since you possibly can simply ChatGPT to grasp the remaining.

Carrying on, you principally create a brand new git repo on one thing like Github after which obtain Windsurf and join your repo. My selection round Windsurf will probably be obvious later.

Now, you open up Windsurf, you’re taking the output of your ChatGPT from the enterprise mannequin canvas and append the next immediate

Create a brand new folder referred to as “business-canvas” within the root of this undertaking after which create a brand new file for every of the headings within the textual content above. Guarantee the entire information for every heading are structured as markdown and observe kebab-case formatting.

This can now create a bunch of information in your repository that has all of your information in a folder. Given these are going to be type of sparse, you’ll need to undergo every of them toe guarantee they’re right and issues haven’t obtained misplaced in translation.

Okay now that you simply’ve achieved all of the arduous work of making and saving your context in software program native protocols it may be manipulated identical to you manipulate code! So for instance, I’ve prompted the next within the chat window to the correct

what do you consider the client relationships and the way they’re served? lets brainstorm some concepts and as soon as i like your concepts you possibly can replace the file

As soon as I’m proud of the output I can then replace this file. I can proceed to rinse and repeat this course of frequently to create new information, merge contexts and many others.

The place this will get actually highly effective is now that from an engineering perspective, you possibly can add this repo/folder to codebase by this selection.

What this then lets you do is let your AI code editor write code with the entire enterprise context baked immediately in! No have to re-explain what your corporation is, what it does and many others. It’s all pre-baked. Nonetheless it’s a must to commit as an organisation to utilizing this repo for all of your context. When you use Notion to retailer this context it is going to be misplaced. You should use MCPs however Notion’s APIs suck and doesn’t have good model management. Since you enterprise context turns into code-ified it means you possibly can commit any updates to your pondering by git commits which can be auto generated.

So after the above immediate I can go to my supply management pane and it figures out what modified and lets me commit it in a single shot.

This has the additional benefit of having the ability to see how the pondering across the enterprise context has modified over time (identical to a codebase).

Your context repo may also function a invaluable place for engineers to doc any technical assumptions that the enterprise staff would wish to know or that the advertising and marketing/gross sales staff would wish entry to. The secret’s that it is advisable create a shared tradition round committing to code-first context (no Google Docs or Notion)!

I might stick with it right here however I feel this ought to be adequate for the primary a part of this collection. What I wished to exhibit on this put up is how one can can construct, rework and remix context throughout completely different mediums/platforms in ways in which performs to every platform’s power. Realizing the correct instrument for the correct job is important when being in AI land and having a very good grasp on the instruments at your disposal is simply as essential. In case you have by no means used git or Windsurf earlier than this put up, I recommend you in all probability change that ASAP.

One key realisation I’ve had by all this AI transition is you want a 100% AI-native tradition. When you don’t have full buy-in and have those who discover these items of their free time you’re going to battle to create new highly effective programs like this. The battle is actual and I’ve discovered when conducting hiring interviews this can be a new standards that’s remarkably arduous to rent for too. Utilizing code editors, studying git and many others can really feel deeply uncomfortable and plenty of should suppose “this AI thing is a fad” or “why would i use something that gets things wrong 60% of the time”. These folks will resist these newer working methodologies.

There’s a wholly new option to construct firms and the reward for having the ability to execute on it’s broad open. I hope this helps you advance in your journey.