Cognitive Blueprints: Advanced Prompt Templates

Intermediate · 1–2 hour read · Some AI chat experience helps

Good prompts do not command. They architect the path the reasoning takes.

This document offers a library of "cognitive blueprints": structured, multi-step prompts designed to guide AI through complex research tasks. They demonstrate patterns that support the interpretive orchestration framework, but they are starting points rather than scripts. Your research questions, disciplinary norms, and analytical goals should shape different prompts. Learn the structures and principles here, then adapt them to develop your own prompting intuition.

Part A: example prompts (Start here)

These three examples show what structured prompts can look like. Study the patterns. Notice what makes them work. Then experiment with building your own.

1. Theory synthesis prompt

Why this works: Clear structure, specific tasks, asks for integration.

2. Grey literature integration

Why this works: Acknowledges different source types, asks for critical evaluation.

3. Thematic analysis for qualitative studies

Why this works: Method-aware, looks for patterns and differences.

Part B: the IMO framework

Understanding the IMO structure

The International Mathematical Olympiad (IMO) paper referenced in the Case Study shows how AI can think systematically:

1. Hypothesis: Form an initial understanding.
2. Verification: Test the hypothesis against evidence.
3. Refinement: Improve based on what you found.
4. Iteration: Repeat until you reach a solid synthesis.

IMO template for systematic reviews

This template shows one way to reinterpret the IMO framework for research. You'll likely adapt it significantly based on your specific research questions and field.

Part C: prompt structure template

The ROLE/CONTEXT/TASK/FORMAT/CONSTRAINTS framework

Many effective prompts for complex research tasks use a structure like this. We've found this pattern helpful, though you might discover other structures that work better for your needs:

# ROLE
Define the AI's expertise and perspective

# CONTEXT
Provide necessary background information

# TASK
Specify the exact analytical work required

# FORMAT
Describe the expected output structure

# CONSTRAINTS
Set boundaries and quality criteria

# EXAMPLES (optional)
Show desired output format

Applied example

# ROLE
You are an expert in organizational theory and systematic review methodology.

# CONTEXT
I have 45 papers on organizational scaling. I need to identify common themes.

# TASK
Analyze these papers and extract 5-7 recurring themes about scaling challenges.

# FORMAT
For each theme, provide:
1. Theme name
2. Description (2-3 sentences)
3. Supporting papers (list authors + year)

# CONSTRAINTS
- Focus on themes mentioned in at least 3 papers
- Avoid generic statements
- Cite specific claims from papers
- Identify areas of disagreement

# EXAMPLES
Theme: Coordination Complexity
Description: As organizations scale, coordination costs increase non-linearly...
Supporting papers: DeSantola & Gulati (2017), Shepherd & Patzelt (2022)...

Part D: your prompt workspace

Use these templates as inspiration to develop and refine your own cognitive blueprints for research tasks. Adapt them freely to match your research context.

Template: initial synthesis prompt

# My Synthesis Prompt

## My Chosen Method: [Describe the methodological approach you're adapting]

## My IMO-Inspired Prompt:

[Paste your developed cognitive blueprint here]

## Notes on My Approach:
- Why I chose this method:
- How I adapted the IMO structure:
- What I expect this to reveal:

Template: refined prompt (After feedback)

# Refined Prompt

## What I Learned:
-
-
-

## My Improved Prompt:

[Updated version here]

## Changes Made and Why:
-
-
-

Template: agentic workflow design

For multi-agent workflows, decompose your research task into specialized roles:

# My Agentic Workflow Design

## Agent 1: Discovery Agent
Role: Extract structured information from research papers
Prompt: "Read these papers and extract: (1) research questions, (2) methodology type, (3) key findings, (4) sample size. Output as structured markdown table."

## Agent 2: Analysis Agent
Role: Evaluate methodology quality and identify limitations
Prompt: "For each paper, assess: (1) validity threats, (2) sample representativeness, (3) measurement issues, (4) generalizability limits. Rate confidence: high/medium/low."

## Agent 3: Synthesis Agent
Role: Identify patterns and synthesize across papers
Prompt: "Compare findings across papers. What patterns emerge? Where do studies contradict? What gaps exist? Organize by theme."

## Agent 4: Critique Agent
Role: Verify outputs and flag issues
Prompt: "Review all extracted data. Flag: (1) missing information, (2) inconsistencies across agents, (3) potential misinterpretations. Verify citations match original papers."

Part E: organizing your work

Creating your prompt folder

1. Create a personal folder in your workspace for organizing prompts (e.g., my-research/prompts/).
2. Save versions of your prompts as synthesis-v1.md, synthesis-v2.md, etc.
3. Keep a collection of your favorite prompts for future research.
4. Copy your best prompts to Cherry Studio for use in your AI workspace.

Prompt development tips

• Start simple: Basic structure first, then add complexity as needed
• Test iteratively: Try your prompt on 2-3 papers, then refine based on what you learn
• Document what doesn't work: Note failures and why. They're valuable data.
• Version your experiments: Keep track of what you've tried
• Share with peers: Learn from each other's approaches and adaptations

Why this approach works

Rather than memorizing templates, this approach helps you build prompts that:

• Match your specific research needs and questions
• Integrate methodological concepts you're learning
• Evolve through experimentation and feedback
• Scale to agentic systems when needed

Your prompt library grows with you as your research thinking deepens. What works for others might not work for you, and that's exactly as it should be.

Enhance your practice

Related Resources:

• Building Prompts (Session 2)
• Agentic Applications (Session 4)