Prompting
How you ask determines what you get back. The techniques worth knowing by name.
Prompt Engineering
Prompt engineering is the skill of crafting effective instructions for AI models to get optimal results. It involves understanding how AI models interpret language, structuring requests clearly, and iterating on prompts to improve output quality. It's a critical skill for any AI-native organization.
Why it matters
The difference between a mediocre AI result and an exceptional one often comes down to how you ask. A well-crafted prompt can be the difference between a vague summary and a precise analysis, between buggy code and a working application.
Prompt engineering isn't just for technical users. Anyone who interacts with AI tools — from executives using ChatGPT to developers using Claude Code — benefits from understanding how to communicate effectively with AI systems.
Core principles
Be specific. "Analyze our Q4 sales data and identify the top 3 underperforming product categories with specific recommendations for each" will always outperform "look at our sales data."
Provide context. AI models perform significantly better when they understand the situation. Include relevant background, constraints, and goals in your prompts.
Iterate. Prompt engineering is a conversation, not a one-shot command. Review the output, refine your instructions, and build on previous results.
Structure your requests. Break complex tasks into clear steps. Use formatting (bullet points, numbered lists, headers) to organize multi-part prompts.
Organizational impact
Organizations where prompt engineering skills are widespread see dramatically better results from their AI tools. It's one of the most underrated capabilities for AI-native teams — and one of the easiest to develop through practice.
System Prompt
A system prompt is a set of instructions given to an AI model before a conversation begins, typically invisible to the end user, that shapes how the model behaves throughout the interaction. System prompts define the model's persona, its constraints, its areas of focus, and its default behaviors. They're used to build AI products — a customer support chatbot has a system prompt that tells it to only answer questions about the company's products.
For organizations building custom AI tools, the system prompt is one of the most powerful levers for controlling output quality and consistency.
Zero-Shot Prompting
Zero-shot prompting is asking an AI model to perform a task without providing any examples of how to do it — just a description of what you want. Most everyday AI use is zero-shot: "Summarize this document" or "Write a proposal for this client." Zero-shot works well for tasks the model has encountered frequently in training. It works less well for novel tasks, specialized formats, or outputs that require a specific structure the model hasn't been explicitly shown.
Few-Shot Prompting
Few-shot prompting is providing an AI model with a small number of examples of the desired input-output pattern before asking it to perform the task on new input. Instead of just saying "classify this email as urgent or not urgent," you show it two or three examples of classified emails, then ask it to classify a new one. Few-shot prompting typically improves output quality significantly for tasks that require a specific format, style, or classification logic that isn't obvious from description alone.
It's one of the most practical techniques for improving AI output without any technical setup.
Chain-of-Thought Prompting
Chain-of-thought prompting is asking an AI model to show its reasoning step by step before giving a final answer. Instead of "What's the answer to X?" you ask "Think through this step by step and then give me your answer." Chain-of-thought improves accuracy on complex reasoning tasks — math problems, logical analysis, multi-step decisions — because it forces the model to work through the problem rather than jumping to a potentially wrong answer. The instruction "think step by step" or "let's reason through this" at the end of a prompt often produces noticeably better outputs on complex tasks.