By Mario Alexandre · March 27, 2026 · 9 min read
I remember the first time I used ChatGPT. I typed "write me a blog post about productivity" and got back words that sounded okay but said nothing. It took me months of trying things to understand why. The answer changed how I think about AI forever.
If you are new to prompt engineering, this guide will save you those months. I will tell you what prompt engineering is, why most prompts fail, and how to fix it with a simple framework called sinc-LLM.
Prompt engineering means writing instructions for AI models that get you exactly the output you want. It is not magic. It is not hacking. It is not about secret keywords. It is about being specific: you tell the AI exactly what you need instead of hoping it guesses right.
Think of ordering food at a restaurant. "Give me something good" is a bad order. "Grilled salmon, medium, with roasted vegetables, no butter, extra lemon on the side" is a good order. The chef can make both. But only the second one gives you what you want.
The average prompt is 12 words long. The average brief for a human freelancer is 2,000 words long. That gap is where things go wrong. You would never hire a freelancer and say "make me a website" with no details. But that is exactly what most people do with AI.
When the AI gets a vague prompt, it has to guess what you meant. That guessing has a name: hallucination. The AI is not broken. You just gave it too little to work with.
In signal processing, this problem is called aliasing. When you measure a signal with too few data points, the result has errors that were never in the original signal:
This formula is the math behind sinc-LLM, but you do not need to understand it to use the tool. The idea is simple: more detail = less guessing = better output.
I built a framework that splits every prompt into 6 parts. I call them "bands" because they work like frequency bands in a radio signal. Each band carries one type of information. Together, they capture what you really want.
Here are the 6 bands:
Do not let the AI default to "helpful assistant." Tell it what kind of expert to be. Not "be a writer," but "senior tech journalist who writes for Wired, known for explaining hard topics to everyday readers."
Give the AI the background. Example: "I am preparing a presentation for my company's board meeting next Tuesday. The board has 5 non-technical investors. They are deciding whether to increase our AI budget by $2M."
Give it real facts, numbers, and examples. Do not let the AI invent data. Example: "Our AI spending last quarter was $150K. Revenue from AI features: $890K. Customer satisfaction for AI features: 4.2/5."
This is the most important band. Tell the AI what to do AND what not to do. Example: "Maximum 10 slides. No technical jargon. Each slide must have one key number. No pie charts, use bar charts only. Must end with a clear recommendation."
Be specific about structure. Example: "Markdown document with H2 headers for each slide. Each section has: slide title, key message (one sentence), supporting data point, speaker notes (3 bullet points)."
State the action clearly. Not "help me with my presentation," but "create the complete slide deck outline with speaker notes for a 20-minute board presentation on our AI ROI."
Here is what all 6 bands look like together in sinc JSON format:
{
"formula": "x(t) = \u03a3 x(nT) \u00b7 sinc((t - nT) / T)",
"T": "specification-axis",
"fragments": [
{"n": 0, "t": "PERSONA", "x": "Expert data scientist with 10 years ML experience"},
{"n": 1, "t": "CONTEXT", "x": "Building a recommendation engine for an e-commerce platform"},
{"n": 2, "t": "DATA", "x": "Dataset: 2M user interactions, 50K products, sparse matrix"},
{"n": 3, "t": "CONSTRAINTS", "x": "Must use collaborative filtering. Latency under 100ms. No PII in logs. Python 3.11+. Must handle cold-start users with content-based fallback"},
{"n": 4, "t": "FORMAT", "x": "Python module with type hints, docstrings, and pytest tests"},
{"n": 5, "t": "TASK", "x": "Implement the recommendation engine with train/predict/evaluate methods"}
]
}
You can build this structure automatically. Just paste your raw idea into sinc-LLM. The tool fills in all 6 bands for you.
You know the 6-band framework. Here is how to go further:
// Production AI Engineering
sinc-LLM designs, audits, and stabilises production AI infrastructure: from vendor evaluation and cost accountability to incident controls and MCP architecture.
See what we do →