Basics6 min read
What Is Prompt Engineering? A Practical Guide With Examples
Prompt engineering is the skill of writing inputs that get reliable results from AI models. Learn the parts of a good prompt, with before-and-after examples.
Fundamentals
Prompt engineering fundamentals: clear instructions that work
Prompt engineering fundamentals are the basics that decide most results: say exactly what you want, give the model the context it cannot guess, set constraints such as length, audience and format, and describe what a good answer looks like. Most weak outputs come from a vague task, not from a weak model.
Coming soon onApp StoreComing soon onGoogle Play
Structured outputIntermediate
Your app parses the model’s JSON, but sometimes the reply starts with “Sure! Here is the JSON:”. What is the most robust fix?
AAdd “please” to the prompt
BUse structured-output mode with a schema, then validate
CLower the temperature to 0
DStrip the first line of every reply
Sample question · Fundamentals
A prompt says “Summarize this report.” The summaries keep coming back too long and too general. What is the best first fix?
- AAdd “be concise” at the end
- BState the reader, the purpose and a length, e.g. “5 bullets for a CFO deciding on budget”
- CSwitch to a larger model
- DAsk the model to try again
Show the answer and why
B. State the reader, the purpose and a length, e.g. “5 bullets for a CFO deciding on budget” “Be concise” is still vague. Naming who reads the summary, what they need it for and how long it should be gives the model something concrete to aim at.
What the questions test
- Spotting the missing piece of context in a prompt
- Turning a vague request into a specific instruction
- Choosing constraints: length, audience, tone, format
- Positive instructions vs. long lists of “don’t”
What you’ll learn
- How to write instructions a model can follow literally
- Which context to include and which to leave out
- How to set length, audience and format without guesswork
- How to iterate on a prompt instead of rewriting it from scratch
How to practice it in TokIQ
- 1. Open Fundamentals. Pick it from the topic list on the Quiz tab. It is included in the free plan.
- 2. Answer one question at a time. You see right away whether you were correct.
- 3. Tap Why? Read the short explanation and answer three follow-up questions on the same idea.
- 4. Watch your accuracy. The Progress tab shows how Fundamentals compares with your other topics.
Fundamentals: common questions
What are the basic elements of a good prompt?
A clear task, the context the model needs, constraints (length, audience, tone, format) and, when it helps, an example of the output you want. Put the most important instruction where it cannot be missed.
Do I need to know how to code to learn prompt fundamentals?
No. The fundamentals are about writing clear instructions. TokIQ’s Fundamentals questions use everyday tasks like summaries, emails and analysis.
Further reading
Basics4 min read
How to Write Better ChatGPT Prompts: A Before-and-After Checklist
A practical checklist for writing better ChatGPT prompts, with before-and-after examples. The same habits work for Claude, Gemini and other AI assistants.
Basics5 min read
11 Common Prompt Engineering Mistakes and How to Fix Them
The prompt engineering mistakes that cause most bad AI output, from missing context to conflicting rules and untested changes, each with a concrete fix.
More topics
Practice fundamentals a few questions a day.
Short quizzes on real prompting decisions, with an explanation for every answer. Free to start on iPhone and Android.
Coming soon onApp StoreComing soon onGoogle Play