AI Prompting

The quality of the AI output heavily depends on the prompt input.

Prompting Techniques

There's a variety of ways to talk to GenAI, from simple one-liners to structured multi-step conversations. Below are a few techniques that people tend to start with:

1. Just Ask

(zero-shot prompting)

Type a question, get an answer. Good for simple, straightforward tasks.

Write a thank-you email to a customer who just made their first purchase.

2. Show One Example

(one-shot prompting)

Give AI one example of what you want, then ask it to do more like that.

Here's a product description I like: [example]. Write 3 more like this for these products: [list].

3. Show a Few Examples

(few-shot prompting)

Give AI 3-5 examples. It learns the pattern and produces consistent results.

Here are 5 of my best-performing Instagram captions: [examples]. Write 5 more in the same style about [topic].

4. Give It a Role

(role prompting)

Tell AI who to be. This changes its tone, focus, and expertise.

You are an experienced Chicago restaurant marketing consultant. A new Thai restaurant wants to stand out in Lincoln Park. What would you recommend?

5. Think Step by Step

(chain-of-thought prompting)

Ask AI to show its reasoning. This produces more thoughtful, nuanced answers.

I'm thinking about raising my prices 10%. Walk me through the pros and cons step by step, considering my customer base of budget-conscious families.

6. Have a Conversation

(prompt chaining)

Go back and forth, refining as you go. Start broad, then narrow down.

Start with a broad question, then say "Make it more specific to my business" → "Now shorten it" → "Add a call to action"

Robust Prompting

Those were pretty short prompts. But how long can a prompt actually be? Similar to how a human brain can only hold so much information at once, GenAI has a context window that can only hold so much information at once.

Most leading GenAI tools today can handle between 200,000 and 2,000,000 tokens and one token is roughly 0.75 words. To put that into context (pun intended), the entire Harry Potter series is 1,084,170 words.

Yet most people write prompts that are less than 30 words. That's like owning a Ferrari and never driving it faster than 5 mph.

The problem is that generic AI prompts often yield generic AI outputs. While prompts don't necessarily have to be thousands of words long, providing some detailed context can make a substantial difference when it comes to getting the most out of AI. Below is a simple example of how to provide strong context to AI (and utilize multiple prompting techniques):

Example of a robust AI prompt with detailed context

MCP Connectors

But what if the AI could gather that context automatically? That's the idea behind MCP (Model Context Protocol) Connectors. They connect AI directly to context-rich apps and data sources like a CRM, email, calendar, files, and more. The AI can pull in relevant context without the person having to manually copy and paste it in. But perhaps even more importantly, MCPs allow AI to take action in the real world, not just return responses. Instead of simply drafting an email, the AI can send it. Instead of suggesting a calendar invite, it can create one. MCPs transform AI from a helpful advisor into a capable assistant that actually gets things done.

Disclaimer: This guide is for educational and informational purposes only. It does not constitute professional business, legal, financial, or technical advice. The examples, stories, and prompts are intended to inspire and educate — not to prescribe specific actions. Always use your own judgment and consult qualified professionals for decisions that could have significant consequences for your business.