Prompting 101: The Complete Beginner's Guide to AI Prompting
A prompt is an instruction. You write it in plain language, send it to an AI model, and the model generates an output based on what you wrote. That's the whole thing. The gap between a bad output and a great one almost always comes down to the quality of the instruction — not the model.
This guide covers everything you need to start writing prompts that work. No technical background required.
What a Prompt Actually Is
A prompt is everything the AI model receives before it starts generating. That includes your main instruction, any context you provide, and any constraints you set. The model has no memory between sessions, no understanding of what you intended if you didn't say it, and no way to ask follow-up questions — unless you build that into the prompt itself.
This is the core insight that changes how most people approach prompting: the model doesn't know what you mean. It only knows what you wrote. Every detail you leave out is a detail the model will fill in on its own — and it will almost always fill it in wrong for your specific purpose.
The Single Most Important Concept: Specificity
Vague prompts produce generic outputs. The more specific your instruction, the closer the output is to what you actually wanted. This is true for every type of AI model — image generators, video generators, and LLMs all behave this way.
SPECIFIC PROMPT: "RAW photo, 1woman, late 20s, ivory blazer, sitting at a marble cafe table, golden hour light from left window, natural skin texture, Canon EOS R5 85mm f/1.2, Vogue editorial style, 8K"
Same subject. Completely different output quality.
The specific prompt names the camera. Names the lighting. Names the publication reference. Names the lens. Every named element removes one degree of freedom from the model's interpretation — and reduces one variable that could go wrong.
The 3-Part Structure Every Prompt Needs
Most professional prompts follow a simple structure whether the writer knows it or not:
1. Role or Subject
Who or what is the subject of the output? For image prompts: describe the person, object, or scene. For LLMs: define the role the AI should take ("You are a senior brand copywriter for a luxury fashion brand"). The role or subject should be the first thing in the prompt — AI models weight earlier tokens more heavily.
2. Context and Environment
Where is this happening? What's the setting, the mood, the time of day? For image prompts: describe the environment, lighting conditions, and atmosphere. For LLMs: describe the situation, the audience, and any relevant background the model needs to know.
3. Constraints and Format
What do you want the output to look like? For image prompts: camera, lens, color grade, resolution, style references. For LLMs: word count, format (bullets vs prose), tone, things to avoid. Constraints narrow the model's output space and make results more consistent across multiple runs.
Negative Prompts
Most image generation models accept a negative prompt — a list of things you don't want in the output. This is not a trick or an advanced technique. It's a core part of the prompt structure that most beginners skip.
A negative prompt is insurance. It tells the model which failure modes to avoid. Without it, the model may default to outputs that look technically correct but feel wrong — plastic skin, dead eyes, stock photo energy. Adding a negative prompt takes thirty seconds and meaningfully improves output quality.
Why the Same Prompt Gives Different Results Each Time
AI models use randomness as part of the generation process. A setting called the seed controls this randomness — and by default, it changes every run. That's why two runs of the same prompt produce different outputs. If you find a result you like and want to reproduce it, save the seed number and use it again. Most image models display the seed in the output metadata.
The Iterative Workflow
Professional prompt engineers don't write one prompt and expect a perfect output. They write a base prompt, review the output, identify what's wrong, and refine. ChatGPT Image 2.0 makes this particularly straightforward — you can describe changes conversationally ("make her jacket darker, change the background to an interior") and the model adjusts while keeping everything else the same.
For any other model, iteration means updating the prompt text and regenerating. Three to five rounds of refinement is normal for commercial-grade output. First-run perfection is rare and shouldn't be expected.
Where to Go Next
This article covers the foundation. The rest of the site goes deeper into every area: