Prompt frameworks
Seventeen named patterns for turning rough prompts into structured super-prompts. Pick by task and complexity, or browse them all.
Simple
Action · Purpose · Execution
A three-part framework that adds a "why" between the request and the output spec. Good for tasks where intent shapes the answer.
Context · Action · Result · Example
A clean, example-led prompt framework. Useful when you want the LLM to model a specific voice or pattern.
Role · Action · Context · Explanation
A clean four-part prompt framework, well-suited for short structured tasks like summaries and rewrites.
Role · Task · Format
The simplest reliable prompt-engineering framework. Define the role, the task, and the format and most LLMs do the rest.
Task · Action · Goal
A tight three-part prompt framework that forces clarity on what to do, how to do it, and what success looks like.
Standard
Comprehend · Identify · Report · Cut · List · Evaluate · Summarise
Lewis Lin's seven-step product design framework, restructured as a prompt. Ideal for feature design, scoping, and product decisions.
Context · Objective · Actions · Scenario · Task
A five-part framework that splits "the situation" from "the constraints" and gives the LLM an ordered path through both. Best for strategic memos and decision support.
Context · Role · Action · Format · Target
A five-part framework that adds an explicit audience to the standard role + action + format structure. Useful when "who reads it" really matters.
Context · Request · Explanation · Outcome
A four-part framework for generating structured ideas, strategies, and problem-solving approaches. Anchors the request to the reasoning behind it and the outcome it must enable.
Capacity & Role · Insight · Statement · Personality · Experiment
A five-part framework for nuanced LLM prompts that handle persona, context, task, voice, and variation in one shot.
Problem · Action · Information · Next Steps
A four-part framework for tackling challenges and driving solutions through structured inquiry. Moves from the problem to a focused output to a clear follow-through.
Persona · Audience · Result · Tone · Style
A five-part framework purpose-built for brand-led writing. Surfaces the voice, the reader, the deliverable, and the textures around them.
Role · Input · Steps · Execution
A four-part framework for guided instructions, tutorials, and learning flows. Sets the persona, the material, an ordered process, and how to deliver it.
Role · Objective · Scenario · Expected Solution · Steps
A five-part framework for decision-making, scenario analysis, and structured problem solving. Frames the goal, the situation, the kind of answer wanted, and the path to it.
Advanced
Chain-of-Thought
A reasoning framework that forces explicit step-by-step thinking before the answer. Improves accuracy on maths, logic, and multi-step problems.
Character · Request · Examples · Adjustments · Type · Extras
A six-part framework for creative, highly tailored content. Built for storytelling, marketing, and social copy where voice and constraints both matter.
Few-Shot Examples
A three-part pattern that shows the LLM 2–4 input-output examples and asks it to match the pattern on a new input. Best for stylistic tasks where the pattern is hard to describe.
Reasoning + Acting
A four-part agentic pattern that forces the LLM to alternate between reasoning and concrete evidence-gathering steps. Best for research and multi-step decisions.
Self-Consistency
A three-part framework that asks the LLM to reason through a problem multiple ways and commit to the most consistent conclusion. Improves robustness on judgement calls.
The TID House Framework — Role · Context · Brief · Quality Bar
The This Is Digital house framework. Four parts — Role, Context, Brief, Quality Bar — and a built-in explicit failure-mode floor.