← All prompts 👥 // prompt framework

Expert Panel Prompting

Ask the AI to simulate a panel of experts with different viewpoints. Forces balanced, multi-perspective analysis.

Best for: Important decisions and strategy stress-testing ClaudeChatGPT

The template

Copy this template and fill in the [BRACKETS] with your specifics.

Respond as a panel of 3 experts: Expert 1: [ROLE — e.g. sceptical CFO] Expert 2: [ROLE — e.g. optimistic product manager] Expert 3: [ROLE — e.g. pragmatic engineer] Each gives their distinct view on: [YOUR QUESTION OR DECISION] End with: Panel Synthesis — what would all three agree on?

Other frameworks

🎯

RCTF Framework

Role + Context + Task + Format. The foundation of every good prompt.

🧠

Chain of Thought

Force the model to think step by step before giving an answer.

📋

Few-Shot Prompting

Give 2-3 examples of input → output before your actual request.

📌

XML Tags (Claude-specific)

Claude processes XML tags with higher accuracy. Use tags to separate concerns.

✅

Self-Consistency Check

Ask the AI to verify its own output before delivering it.

🚫

Negative Prompting

Explicitly state what NOT to do — often more effective than positive instructions.

🎯

RGB — Role, Goal, Format

Define the AI role, state the goal, specify the output format. Covers 80% of everyday prompting needs in under 30 seconds.

🔬

CRISPE Framework

Capacity, Role, Insight, Statement, Personality, Experiment — for nuanced expert-level responses.

⭐

STAR Prompting

Structure your prompt like a behavioural interview answer. Forces specificity about context, need, and desired outcome.

🧅

PEEL — Point, Evidence, Explain, Link

Makes AI give structured analytical responses: state a point, support with evidence, explain reasoning, link back to question.

🚧

Constraint Prompting

Tell AI what NOT to do and what hard limits to respect. Constraints fix most quality problems faster than adding more context.

🏛️

Socratic Prompting

Instead of asking for an answer, ask AI to ask you questions that reveal gaps in your thinking before giving advice.

⚓

Output Anchoring

Give the AI an example of your ideal output before making the request. It mirrors structure, tone, and depth of your anchor.

🔄

Iterative Refinement Protocol

Three-pass system: generate, self-critique, refine. The AI critiques its own output then improves it. Dramatically better results.

🎭

Persona Injection

Describe a persona in detail: beliefs, communication style, vocabulary, what they avoid. AI embodies that persona consistently.

🧩

Task Decomposition Prompting

Ask AI to break complex tasks into steps, confirm the plan with you, then execute step-by-step. Prevents errors on long tasks.

🪜

Prompt Ladder

A prompting methodology: start 1-sentence prompt, layer in role, context, format, constraints until quality is right.