IN THIS ARTICLE

This article is an overview of prompting and how to prompt effectively

Contents

Overview

In the CEL Framework, the "E" stands for "Enablers."

There are four key enablers that ensure large language models (LLMs) work as effectively as possible:

1. Prompting
2. Context
3. Data Grounding
4. Governance

This document focuses on the first enabler: Prompting. Here, you'll learn what prompt engineering is, why it matters, and how to craft effective prompts to get the most accurate and useful responses from HallianAI.

What is Prompt Engineering?

Prompt engineering is the technique of crafting prompts in a precise way to guide an LLM (like the ones available within HallianAI) to produce the most accurate and useful responses. The quality of your prompt directly impacts the quality of the AI's output.

Why is Prompt Engineering Important?

• Better Results: A well-crafted prompt leads to more relevant, accurate, and actionable responses.
• Efficiency: Saves time by reducing the need for follow-up questions or corrections.
• Customization: Allows you to tailor responses to your specific needs and context.

Example: Poor vs. High-Quality Prompts

To illustrate the difference, consider the following two prompts: