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.

Active and passive prompting

A passive prompt hands the task over. Phrases such as "assess credibility", "integrate appropriately" or "avoid generic statements" let the AI choose the method, the criteria and what each judgment word means, and the output comes back fluent whatever it chose. By the mirror effect, a vague prompt is vague thinking made visible.

An active prompt keeps the judgment with you. It:

• states the question, and your own current account, before the AI reads anything
• names the method the work should follow
• defines every judgment word, or marks it as yours to supply
• requires a locator (a page, a section or a quote) for each claim
• splits the work into steps, with a stop for your review
• asks for the cases that disconfirm your account

The templates on this page use square brackets for simple slots such as [topic]. A bracket that begins with insert:, as in [insert: your credibility criteria], marks what only you can supply. Every template ends with the same guard line:

If anything in [insert: …] is still unfilled, stop and ask me before starting.

When an output still reads as generic, run the Output Mirror on it, and look in the Failure Museum for the exhibit it resembles.

"Active prompting" is also the name of a published chain-of-thought technique (Diao and colleagues, 2023) that picks the questions a model is least certain about for human annotation. This page uses the words in a plainer sense.

Part A: example prompts (Start here)

These three examples show what active prompts can look like for literature work in general. Each one marks the judgment calls it leaves to you. Study the pattern, then fill the placeholders from your own project.

1. Theory synthesis prompt

What it asks of you: your question, your account before reading, and what a contradiction means in your field. The integrating framework at the end is yours to build.

2. Grey literature integration

What it asks of you: your own credibility criteria, stated before the AI applies any, and the decision about how much each perspective should weigh.

3. Thematic analysis for qualitative studies

What it asks of you: the synthesis approach, the themes you expected, and what counts as divergence. Naming the themes that survive stays with you.

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.

In research, the hypothesis worth testing is usually yours rather than the model's: write it down first, and ask the verification step to quote its evidence.

IMO template for systematic reviews

The review version of this template now lives with the case study, on Review Prompt Templates.

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

The same structure, filled in as an active prompt. Slots in plain brackets describe your material; the [insert: …] slots are the judgments the prompt cannot make for you.

# ROLE
You are assisting a researcher in [field] who is identifying themes
in the literature on [topic]. The conclusions are the researcher's.

# CONTEXT
I have [number] papers on [topic], listed with IDs in [file].
My question: [insert: the question the themes must answer]
My current account: [insert: the themes I expect, in two or three sentences]

# TASK
Step 1: quote every passage that bears on my question, with paper ID
and page. Stop for my review.
Step 2, after I reply: group the passages into candidate themes.

# FORMAT
For each theme:
1. Theme name
2. Description (2-3 sentences) in the papers' terms
3. Supporting passages: paper ID, page, quote
4. Papers that contradict or complicate it

# CONSTRAINTS
- A theme needs support from at least [insert: your threshold] papers
- By "generic" I mean [insert: for example, a statement true of any
  organization]; flag such themes rather than dropping them
- List disagreements before agreements
- If a paper is silent on a theme, say so; do not infer

# EXAMPLES
[insert: one theme written the way you want it, from your own reading]

If anything in [insert: …] is still unfilled, stop and ask me before starting.

Part D: your prompt workspace

The worksheets for a first and a refined synthesis prompt, and the template for an agentic workflow, now live with the systematic-review course: the initial prompt worksheet, the refined prompt worksheet and the agentic workflow design. Outside a review the habit is the same: keep your own account beside each version of a prompt, and note where the output diverged from it.

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:

• Review Prompt Templates
• Building Prompts (Session 2)
• Agentic Applications (Session 4)