# Prompting for Engineers: Structured Outputs Over Clever Wording

> Treat a prompt like an API contract: clear instructions, examples, a strict output schema and validation — so LLM output can safely feed a pipeline.

- Source: https://akshaythakare.com/notes/generative-ai/structured-outputs-and-prompting
- Topic: Generative AI
- Level: beginner
- Reading time: 3 min
- Tags: llm, prompting, structured-output, genai
- Updated: 2026-10-11

## The engineering view of a prompt

In production, an LLM call is a function: inputs go in, output must be parseable and correct often enough to automate. Clever phrasing matters less than a clear contract.

A reliable prompt has four parts:

1. **Role and task** — what the model is doing and for whom.
2. **Context** — the data it needs, clearly delimited.
3. **Rules** — constraints, including what to do when information is missing.
4. **Output format** — exactly what to return.

```text
You extract fields from support emails.
Return JSON matching the schema. If a field is not stated in the email, use null — do not guess.

<email>
{email_text}
</email>
```

## Ask for structure, then enforce it

Most model APIs can constrain output to a JSON schema (often called structured outputs, JSON mode or tool calling). Define the schema in code and validate the result:

```python
from pydantic import BaseModel, ValidationError

class Ticket(BaseModel):
    customer_email: str | None
    product: str | None
    severity: str  # "low" | "medium" | "high"

raw = call_llm(prompt, response_schema=Ticket.model_json_schema())
try:
    ticket = Ticket.model_validate_json(raw)
except ValidationError:
    ticket = None   # retry once with the error message, then route to a human
```

> **Tip: Validation is not optional**
>
> Even with schema-constrained output, values can be wrong. Validate types and ranges in code, and check critical fields against your own systems.

## Few-shot examples beat long explanations

Two or three input–output examples covering edge cases (missing fields, ambiguous wording) usually improve consistency more than paragraphs of instructions.

## Make it testable

- Keep prompts in version control next to the code that uses them.
- Build a small evaluation set of real inputs with expected outputs.
- Re-run it whenever you change the prompt, model or temperature.

## Settings that matter

- **Temperature**: low (0–0.3) for extraction and classification; higher only for creative text.
- **Max output tokens**: set it, so a runaway response cannot blow up cost or latency.
- **Model choice**: use the smallest model that passes your evaluation set.