AI engineering glossary · Prompt context engineering
What is prompt engineering?
Prompt engineering: The practice of designing and refining the text sent to a language model so it gives reliable, useful answers without changing the model's weights. It covers wording, examples, structure, and testing variations. It is the cheapest way to improve behaviour before trying retrieval or fine-tuning.
Prompt engineering: an example
A team tries three versions of a resume-screening prompt on 50 sample resumes and keeps the one that matches recruiter decisions most often.
Prompt engineering in Python
A short example you can run (Python 3.11). The output below is what it really prints.
def build_prompt(task, examples, text):
shots = "\n".join(f"Input: {i}\nLabel: {o}" for i, o in examples)
return f"{task}\n\n{shots}\n\nInput: {text}\nLabel:"
prompt = build_prompt(
"Classify each support message as BILLING, BUG or OTHER. Reply with one word.",
[("I was charged twice", "BILLING"), ("The app crashes on login", "BUG")],
"My invoice shows the wrong GST number",
)
print(prompt)Output
Classify each support message as BILLING, BUG or OTHER. Reply with one word. Input: I was charged twice Label: BILLING Input: The app crashes on login Label: BUG Input: My invoice shows the wrong GST number Label:
Related terms
More Prompt context engineering terms
- Prompt optimisation
- Prompt registry
- Prompt regression testing
- Prompt sensitivity
- Prompt template
- Prompt versioning
- Pydantic validation of LLM output
- Quote-first prompting
Where you learn it
Prompt engineering is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.