Prompting Basics: How to Get More Reliable Answers from AI (with Templates)

The short answer

A prompt is everything you give a large language model: instructions, material, examples and format requirements. The model can only predict the next token from the context you provide (see What Is a Large Language Model?), so the clearer the prompt, the more reliable the answer. The official guides from OpenAI, Anthropic and Google agree closely: be clear, give examples, give structure, and define what “good” looks like.

Step 1: instructions, roles and context

Picture the model as a brilliant new colleague who knows nothing about your situation (Anthropic's guide uses the same image). A complete prompt usually has four parts:

Practical tips:

• Separate instructions from material. Wrap the content to process in headings, triple quotes or XML tags (for example <policy>…</policy>) so the model is less likely to treat sentences in it as instructions.
• Long documents first, question last. Anthropic's docs recommend placing long documents at the top of the prompt and the query at the end.
• Add a role, but don't rely on it. “You are a senior financial analyst” adjusts tone and depth; the specific task and material still decide quality.
• Use the system prompt for rules that stay the same, and the user message for each specific task.

Step 2: few-shot examples

Instead of describing the style you want at length, show 2–5 examples. The GPT-3 paper showed that a model can perform tasks it was never specifically trained for just from a few examples in the prompt — “in-context learning” (Brown et al., 2020).

Classify user feedback as: feature request / bug / praise.

Feedback: The export button does nothing when I click it → bug
Feedback: Please let me filter by date → feature request
Feedback: Your support agent was so patient, thanks! → praise

Feedback: The mobile app shows a blank screen after login →

Make examples cover different cases (including edge cases) and match the exact output format you want. Avoid near-identical examples, or the model learns only the surface pattern.

Step 3: let the model think step by step

For maths, logic or multi-step problems, asking the model to write out its reasoning before the answer improves accuracy noticeably. This is chain-of-thought prompting (Wei et al., 2022). Even adding “Let's think step by step” helps (Kojima et al., 2022). Going further, have the model solve the problem several times and take the most common answer — self-consistency (Wang et al., 2022).

Two caveats:

• Reasoning models (which “think” before answering) already do this internally. OpenAI's guide likens a reasoning model to a senior co-worker who can be given a goal and trusted with the details, while GPT models need more explicit instructions.
• A written-out chain of reasoning is not guaranteed to be correct; still check the final answer.

Step 4: structured output (JSON)

If a program will consume the result, ask for a fixed format such as JSON.

1. Prefer the platform feature. OpenAI's Structured Outputs, for example, makes the output conform to a JSON Schema you supply (OpenAI docs).
2. Without such a feature, list the field names and types with a full example, and say “output JSON only, no extra text”.
3. Always validate in code. If parsing fails or fields are missing, retry or raise an error rather than using it as is.

{"category": "bug", "product_area": "login", "urgency": "high", "summary": "Blank screen after mobile login"}

Step 5: iterate on prompts like code

Prompts are rarely right the first time. A dependable loop:

1. Collect 5–20 real test questions (including hard and edge cases) and write down what a good answer looks like.
2. After every prompt change, run the same set and compare results.
3. Split complex tasks into steps (extract, then analyse, then write), one prompt each — easier to control than one giant prompt.

For evaluating model outputs systematically, see How to Evaluate LLMs.

When prompting is not enough

Prompting can only draw on what the model already can do; it cannot add what the model doesn't know:

Also, when processing external content — web pages, emails, documents — it may contain text like “ignore previous instructions”. That is prompt injection, and prompting alone cannot defend against it.

Try it yourself

1. Pick a task you repeat every week, write it as a goal + context + format + constraints template, test it on 5 real cases, and revise it three times, noting what went wrong each time.
2. Work through Anthropic's interactive prompt-engineering tutorial.
3. Compare the OpenAI prompting guide, Gemini prompting strategies and the Prompt Engineering Guide and note what they agree on.