How to Train Your AI: Use Examples That Teach, Not Just Tell

May 7, 2025 / By Sean Bailey, Horsesmouth Editor in Chief
Print AAA
Add to My Archive
My Folder

My Notes
Save
AI for Advisors: AI doesn’t read minds—it reads signals. The strongest signal is an example. When you share something real in your prompts—a document, message, or format—the AI starts to deliver results you want.

AI for Advisors newsletter

Quick take:

  • Examples are how you teach the AI to follow your instructions.
  • They help guide structure, eliminate ambiguity, and speed up iteration.
  • Examples also dramatically improve the style and tone of AI outputs.
  • Great examples show the AI what success looks like—especially in complex or personalized tasks.

We’ve explored how strong prompts begin with Role, Task, and Format—and how Context and Questions deepen the conversation. Now we reach the final and most actionable piece of the CQE model: Examples.

If context tells the AI what it’s working on, and questions help it ask for what’s missing, examples show it exactly what good looks like.

Why examples matter

Describing what you want only gets you halfway there. Showing the AI an example—something you’ve written, formatted, or styled—gives it a clear reference.

Instead of: “Write a retirement article for my clients,”

Try: “Use this intro from my Roth IRA piece as a guide. Match the warm tone and conversational style.”

That shift—from vague to specific—can completely transform the output. You’re no longer guessing at the AI’s potential. You’re giving it a map.

Examples in action: Real prompts, real results

Estate planning email prompt

Without an example: “Write an email encouraging clients to review their estate plan.”

The AI replies with something stiff and formal—closer to a law firm memo than a trusted advisor check-in.

With an example: “Use the same tone as this Roth conversion email: ‘Just a quick note to check in—have you thought about how your Roth strategy fits into your long-term plan?’”

Now the email opens warmly, keeps jargon in check, and reflects your actual client voice.

Client onboarding guide prompt

Without an example: “Turn this checklist into a welcome packet for new clients.”

The AI produces a wall of text—technically correct, but overwhelming.

With an example: “Format it like our budgeting guide: clear headers, short bullets, and a welcome message at the top.”

The result is structured, skimmable, and client-ready.

How examples improve AI responses

  • Tone and Voice: The AI mirrors your style—warm, formal, energetic, or empathetic.
  • Structure: Paragraphs, bullets, calls to action (CTAs), headers—it picks up your formatting cues.
  • Relevance: Examples eliminate ambiguity and show the AI how to focus.

Use examples to refine and iterate

When the AI gives you a draft that’s almost—but not quite—what you need, examples create a feedback loop. Instead of starting from scratch, you say: “Let’s try again, but model it on this format.”

That subtle correction helps the AI learn faster—and helps you get better results in less time.

Tackling complex tasks? Bring an example.

The more complex the task, the more valuable the example.

Let’s say you ask: “Write a 600-word article on Roth conversions with a soft CTA, aimed at Gen X professionals.”

Even if your prompt is clear, the AI could go too technical, too long, or too generic.

But include a sample paragraph from a previous article? Now the AI understands your tone, pacing, and audience. The example acts like a model—calibrating its output to match your intent.

Formats that work well as examples

Use examples to guide style and structure, not to plagiarize. Stick to:

  • Your own published materials
  • Edited internal drafts
  • Lightly anonymized samples

If you’re using outside content for inspiration, rewrite it. Show the AI the shape of the thing—not the thing itself.

Think beyond full documents. You can show the AI:

  • A favorite email opening
  • A slide title or layout
  • A headline from your blog
  • A bullet list format
  • A short paragraph that “sounds like you”

Examples don’t need to be long. They need to be clear.

Teach the AI what ‘good’ looks like

Prompting isn’t just about giving commands. It’s about teaching. And examples are your most effective teaching tool.

Your past work. Your best lines. Your formatting. These are what turn a smart language model into a sharp digital assistant—one that understands how you think, write, and connect with clients.

In the end, examples aren’t just helpful. They’re transformative.

AI for Advisors newsletter

Sean Bailey is editor in chief at Horsesmouth, where he has led editorial strategy for over 25 years. He is the co-author of Hack Proof Your Life Now! and has spent over 3,000 hours researching how AI can transform the way financial advisors work. Through his AI-Powered Financial Advisor and AI Marketing for Advisors programs, he helps advisors save time, deliver better client experiences, and market their services with unprecedented speed, quality, and confidence.

IMPORTANT NOTICE
This material is provided exclusively for use by Horsesmouth members and is subject to Horsesmouth Terms & Conditions and applicable copyright laws. Unauthorized use, reproduction or distribution of this material is a violation of federal law and punishable by civil and criminal penalty. This material is furnished “as is” without warranty of any kind. Its accuracy and completeness is not guaranteed and all warranties express or implied are hereby excluded.

© 2025 Horsesmouth, LLC. All Rights Reserved.