Prompt Engineering Patterns That Actually Work in Production

import json
from pydantic import BaseModel

class ExtractedEntity(BaseModel):
    name: str
    category: str
    confidence: float

SYSTEM_PROMPT = """Extract entities from the text.
Return ONLY valid JSON matching this schema:
{"name": string, "category": string, "confidence": number 0-1}
Return an array. No explanation, no markdown fences."""

def extract_entities(text: str) -> list[ExtractedEntity]:
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "system", "content": SYSTEM_PROMPT},
            {"role": "user", "content": text},
        ],
        temperature=0.1,
    )
    raw = response.choices[0].message.content.strip()
    # Strip markdown fences if the model adds them anyway
    if raw.startswith("```"):
        raw = raw.split("\n", 1)[1].rsplit("```", 1)[0]
    data = json.loads(raw)
    return [ExtractedEntity(**item) for item in data]

Classify this support ticket. Think step by step:
1. What product area does this relate to?
2. Is this a bug report, feature request, or question?
3. What is the urgency (low/medium/high)?

Then return your answer as JSON: {"area": ..., "type": ..., "urgency": ...}

async def summarize_with_fallback(text: str) -> str:
    try:
        result = await call_llm(text, timeout=5.0)
        return result
    except (TimeoutError, RateLimitError):
        # Fallback: first 200 chars + ellipsis
        return text[:200].rsplit(" ", 1)[0] + "..."
    except json.JSONDecodeError:
        logger.warning("LLM returned unparseable response")
        return "Summary unavailable"

Convert the user message to a database query.

Example: "orders from last week" -> SELECT * FROM orders WHERE created_at > NOW() - INTERVAL '7 days'
Example: "top customers by revenue" -> SELECT customer_id, SUM(amount) as revenue FROM orders GROUP BY customer_id ORDER BY revenue DESC LIMIT 10

User: {user_message}