shot examples
technique judged 99% likely a named technique or architecture
See how it has spread across media tiers
Mentions over time
Table view
| Week | Articles | Sources |
|---|---|---|
| 2021-W22 | 1 | 1 |
| 2024-W18 | 1 | 1 |
| 2024-W26 | 1 | 1 |
| 2025-W31 | 1 | 1 |
| 2026-W03 | 1 | 1 |
| 2026-W09 | 1 | 1 |
| 2026-W11 | 7 | 1 |
| 2026-W40 | 3 | 1 |
| 2026-W41 | 1 | 1 |
In their words
Your response:""" ## Part 4: Prompt Optimization ### Automated Prompt Optimization python prompting/optimization.py from dataclasses import dataclass from typing import List, Callable import asyncio @dataclass class PromptCandidate: prompt: str score: float = 0.0 metadata: dict = None class PromptOptimizer: def init ( self, llm, evaluator: Callable[[str, str], float], # (prompt, expected) -> score
If it survives careful prompting and few-shot examples, then consider fine-tuning.
Our first fixes were in the prompt and in code: A system prompt with facts, rules and few-shot examples: 1,333 tokens.
Forty lines of "respond only with JSON", "do not include any other text", "if you are unsure, output UNKNOWN", plus three few-shot examples I'd been carrying between projects like a lucky coin.
Format consistency: If your production system needs structured output (JSON, a specific text format), include that structure in your few-shot examples.
The “Do I Even Need Fine-Tuning?” Checklist Section titled “The “Do I Even Need Fine-Tuning?” Checklist” Before investing in fine-tuning, try these approaches first (in order): - Better prompting — Few-shot examples in the system prompt often achieve 80% of fine-tuning quality - System prompt optimization — Iterate on instructions, format examples, and constraints - RAG — If the problem is knowled
This page assumes you already understand prompt engineering fundamentals — system prompts, few-shot examples, and basic Chain-of-Thought.
The discipline is maturing, not shrinking — moving from informal trial-and-error toward systematic techniques with measurable outcomes: few-shot examples, chain-of-thought, structured output, evaluation-driven prompt iteration.