One of OpenAIs recommendations to simplify complex prompts for ChatGPT is to use “trigger/instruction” pairs.

In this case, a “trigger” is a cause for something to happen, and the “instruction” contains the details of what will happen.

A delimiter is simply a boundary.  They are used to separate individual characters, words, URLs, and all kinds of data.  

As a quick example, here are a few ways I could use delimiters for the numbers 1 - 10:

SPAR is another short, general-purpose framework

It stands for Scenario, Problem, Action, Result

I mentioned in a previous AI Quick Tip post that I used meta-prompting to figure out how to play a game of gin rummy with Perplexity AI.  This post goes into the details.

No, this isn’t about Facebook or any of Zuckerberg’s companies….

Prompt frameworks offer a quick and low-effort way to feed the information that you care about to your AI tool of choice.

CARE is a short, general-purpose framework.  It stands for Context, Action, Result, Example.

I know, I know, it seems backwards.  It doesn’t have to be though and it can help you get past writer’s block, idea block, or whatever block is holding up your progress.

You can give a small amount of context and ask the AI tool to ask you questions about it to gather...

A few posts ago I talked about a simple 4-step prompt framework to get you started.  If that isn’t getting you the results that you are looking for, here is a framework to create prompts with more context.  

Continuing the conversation from the last post, ChatGPT has  plenty of output options for the more technical users.