Common Prompt Mistakes

Why Mistakes Matter

Most poor model outputs are not the model's fault — they are the prompt's fault. When a model produces a vague, irrelevant, too-long, or incorrectly formatted response, it is almost always because the prompt gave it permission to. The model fills gaps with defaults. Gaps in the prompt become problems in the output.

The Core Insight

Understanding the common failure patterns lets you write prompts that leave fewer gaps — and produce fewer surprises.

Mistake 1: Too Vague

The most common mistake. The task instruction does not specify what exactly to produce, so the model guesses.

Too vague

"Tell me about databases."

Relational or NoSQL? History or use cases? Beginner or expert? The model must guess all of these and will pick the statistical average of everything.

Fix: add specificity

"Explain the difference between relational and NoSQL databases in 3 bullet points for someone who has never used a database."

Topic, angle, format, length, and audience all specified. No guessing required.

Mistake 2: Too Broad

The scope is wider than can be covered usefully in one response. The model produces a shallow survey of many topics rather than a useful explanation of any of them.

Too broad

"Explain everything about machine learning."

Machine learning is a vast field. The response will be a thin overview — not enough depth to be actionable on any specific topic.

Fix: narrow the scope

"Explain supervised learning in 2 paragraphs: what it is and one real-world example."

Specific topic, specific length, specific structure. If broad coverage is needed, split into multiple targeted prompts.

Mistake 3: Missing Context

The model does not know the situation it is responding into — who the audience is, what the purpose is, or what the reader already knows.

Missing context

"Write an introduction to our product."

What product? Who is the audience? What tone? What platform? The model invents answers to all of these.

Fix: provide the background

"Write a 2-sentence introduction to Zeruno, an AI-powered coding education platform, for the homepage. Audience: adult beginners to programming."

Product, platform, audience, length, and purpose all specified.

Mistake 4: Conflicting Instructions

What Happens

The prompt contains instructions that contradict each other, and the model must choose which to honor — unpredictably.

"Explain this in detail, but keep it to one sentence." — detail and one sentence are incompatible; the model satisfies one and violates the other

"Be creative and original, but follow this exact template exactly." — creativity and exact template adherence are contradictory

Fix: review your prompt for contradictions before sending; if two constraints conflict, decide which is higher priority and remove the other

Mistake 5: Assuming the Model Knows Your Goal

Assumes too much

"Fix this code."

Fix what specifically? Return only the code or explain the changes? Preserve the original style or improve it? The model makes these decisions without your input.

Fix: state the goal explicitly

"Fix the bug in this Python function that causes it to fail when the input list is empty. Return only the corrected function with no explanation."

Bug described. Output specified. Format specified. No ambiguous tradeoffs.

Mistake 6: No Format Instruction

The Default Is Always Prose

Without a format instruction, the model defaults to flowing paragraphs. If you needed a list, a table, JSON, or a code block, you did not get it — and the model had no reason to think you wanted one. Always add a format instruction when you need anything other than prose paragraphs.

Summary

Key Takeaways
  • Most poor outputs are prompt failures — gaps in the prompt become defaults in the output
  • Too vague: add specificity — topic, angle, audience, length, format
  • Too broad: narrow the scope; split large requests into multiple targeted prompts
  • Missing context: provide the audience, purpose, platform, and background the model cannot infer
  • Conflicting instructions: review for contradictions before sending; keep only the higher-priority constraint
  • Assuming goal knowledge: state your purpose and specify the exact output you need
  • No format instruction: always specify format when you need anything other than prose

Need Help?

Ask the AI if you need help identifying mistakes in a prompt you have written, understanding a specific failure pattern, or knowing the right fix for a particular type of bad output you are seeing.