How to get the most out of your AI model

How do you prevent your AI assistant wasting tokens by generating something you'll probably won't use? Much like when you're sat in front of a computer deciding what to concentrate your time on, AI assistants need to be told up front what they need to be focusing on.

After having launched my own blog and an equipment management web app as a realistic practice project I will tell you how to get the most out of your AI assistant.

It all boils down to defining exactly what the AI assistant should do. By doing this the AI is laser focused on the task at hand and you'll no longer have to worry about token burn rate. But what does a spec actually look like?

I have posted a set of spec files for a MERN-based project on my GitHub account (link can be found above next to my avatar picture).

Feel free to edit it for your own projects and if you would like to, post a link to an update in the comments section below.

Bearing in mind I used this format before I heard of agent skills. The downside is you'll have to change the spec files everytime you wish to build something.

I've also gotten into the habit of getting the AI model I'm working with to generate a set of specs in case I wish to regenerate the source code with certain changes (for example if a client decides to go with an alternative CSS framework), I usually include this with the project so that I don't lose context.

If you're looking for something more generic that can work across multiple projects then this GitHub repo might be something to test:

https://github.com/addyosmani/agent-skills