Structured Output (JSON & Tables) — Hugging Face (open-source)

Hugging Face (open-source)Fundamentals From a course

When you need output your app or spreadsheet can actually use, explicitly request a schema.

The prompt

System: Respond only with valid JSON matching this schema: {"summary": string, "sentiment": "positive"|"neutral"|"negative", "keywords": string[]}. User: [paste customer feedback]

What to replace

Swap these placeholders for your own details before running the prompt:

[paste customer feedback]your own value

Pro tip: Always show the exact JSON schema in the prompt itself — models follow explicit key names far more reliably than vague descriptions.

How to use this prompt

Copy the prompt using the button above.
Replace [paste customer feedback] with your own details — the more specific you are, the better the output.
Paste it into Hugging Face (open-source) and run it.
If the answer feels generic, add constraints: audience, length, tone, and what to avoid. That single change fixes most weak output.

Learn the technique

Structured Output (JSON & Tables)

Module 2 — Core Techniques · Prompt Engineering Fundamentals

Related prompts

ChatGPT

The 5-Part Prompt Framework — ChatGPT

Every strong prompt combines five parts: Role (who the AI should act as), Context (background info it needs), Task (the specific ask), Format (how you want the output structured), and Constraints (length, tone, things to avoid).

Claude

The 5-Part Prompt Framework — Claude

ChatGPT

Zero-Shot vs Few-Shot Prompting — ChatGPT

Zero-shot means asking directly with no examples.

Grok

Zero-Shot vs Few-Shot Prompting — Grok

Zero-shot means asking directly with no examples.

ChatGPT

Chain-of-Thought Prompting — ChatGPT

Asking a model to "think step by step" before answering measurably improves accuracy on reasoning, math, and multi-step logic tasks because it forces the model to externalize intermediate steps instead of jumping to a guess..

Claude

Chain-of-Thought Prompting — Claude