Some dumb researchers still read papers one by one. Stanford PhD...
Louis Gleeson@aigleeson
103 views
Mar 15, 2026
~3 min read
Advertisement
1
Some dumb researchers still read papers one by one.
Stanford PhD students just use Claude.
Here are 9 prompts that turn 40+ papers into structured literature reviews, knowledge maps, and research gaps in minutes:
Stanford PhD students just use Claude.
Here are 9 prompts that turn 40+ papers into structured literature reviews, knowledge maps, and research gaps in minutes:
2
PROMPT 1 - The Intake Protocol
Use this when you first upload your papers:
"I'm going to share [X] papers on [topic].
Before I ask anything, do this:
1. List every paper by author + year + core claim in one sentence
2. Group them into clusters of shared assumptions
3. Flag any paper that contradicts another
Don't summarize. Map the landscape."
Use this when you first upload your papers:
"I'm going to share [X] papers on [topic].
Before I ask anything, do this:
1. List every paper by author + year + core claim in one sentence
2. Group them into clusters of shared assumptions
3. Flag any paper that contradicts another
Don't summarize. Map the landscape."
3
PROMPT 2 - The Contradiction Finder
Most researchers miss this. This prompt doesn't:
"Across all papers uploaded, identify every point where two
or more authors directly contradict each other.
For each contradiction:
- State both positions
- Name the papers
- Explain WHY they likely disagree (methodology, dataset, era)
Format as a table."
Most researchers miss this. This prompt doesn't:
"Across all papers uploaded, identify every point where two
or more authors directly contradict each other.
For each contradiction:
- State both positions
- Name the papers
- Explain WHY they likely disagree (methodology, dataset, era)
Format as a table."
4
PROMPT 3 - The Citation Chain
"Pick the 3 most-cited concepts across these papers.
For each concept:
- Who introduced it first?
- Who challenged it?
- Who refined it?
- What's the current consensus (if any)?
Show me the intellectual lineage like a family tree."
This one alone saves 6 hours of backward citation digging.
"Pick the 3 most-cited concepts across these papers.
For each concept:
- Who introduced it first?
- Who challenged it?
- Who refined it?
- What's the current consensus (if any)?
Show me the intellectual lineage like a family tree."
This one alone saves 6 hours of backward citation digging.
5
PROMPT 4 - The Gap Scanner
This is where it gets scary good:
"Based on all uploaded papers, identify the 5 research
questions that NOBODY has fully answered yet.
For each gap:
- Why does it exist? (too hard, too niche, overlooked?)
- Which existing paper came closest to answering it?
- What methodology would be needed to close it?"
This is where it gets scary good:
"Based on all uploaded papers, identify the 5 research
questions that NOBODY has fully answered yet.
For each gap:
- Why does it exist? (too hard, too niche, overlooked?)
- Which existing paper came closest to answering it?
- What methodology would be needed to close it?"
6
PROMPT 5 - The Methodology Audit
"Compare the research methodologies used across all papers.
Group by: surveys, experiments, simulations, meta-analyses,
case studies.
Then flag:
- Which methodology dominates this field and why?
- Which methodology is underused?
- Which paper's methodology is weakest and why?"
"Compare the research methodologies used across all papers.
Group by: surveys, experiments, simulations, meta-analyses,
case studies.
Then flag:
- Which methodology dominates this field and why?
- Which methodology is underused?
- Which paper's methodology is weakest and why?"
7
PROMPT 6 - The Master Synthesis
Once you've run the above prompts, hit this one:
"You now have a full picture of this literature.
Write a synthesis that does NOT summarize individual papers.
Instead:
- State what the field collectively believes
- State what remains contested
- State what's been proven beyond reasonable doubt
- End with the single most important unanswered question
Max 400 words. No filler."
Once you've run the above prompts, hit this one:
"You now have a full picture of this literature.
Write a synthesis that does NOT summarize individual papers.
Instead:
- State what the field collectively believes
- State what remains contested
- State what's been proven beyond reasonable doubt
- End with the single most important unanswered question
Max 400 words. No filler."
8
PROMPT 7 - The Assumption Killer
"List every assumption that the MAJORITY of these papers share
but never explicitly test or justify.
For each assumption:
- State it clearly
- Name 1-2 papers that rely on it most
- Explain what would happen to the field if the assumption
turned out to be wrong"
This is how paradigm-shifting papers get written.
"List every assumption that the MAJORITY of these papers share
but never explicitly test or justify.
For each assumption:
- State it clearly
- Name 1-2 papers that rely on it most
- Explain what would happen to the field if the assumption
turned out to be wrong"
This is how paradigm-shifting papers get written.
9
PROMPT 8 - The Knowledge Map Builder
"Create a structured knowledge map of this entire literature.
Format:
- Central claim the field orbits around
- 3-5 supporting pillars (well-established sub-claims)
- 2-3 contested zones (active debates)
- 1-2 frontier questions (nobody's solved yet)
- 3 papers a newcomer MUST read first and why
Output as a clean outline, not prose."
Print this. Pin it above your desk.
"Create a structured knowledge map of this entire literature.
Format:
- Central claim the field orbits around
- 3-5 supporting pillars (well-established sub-claims)
- 2-3 contested zones (active debates)
- 1-2 frontier questions (nobody's solved yet)
- 3 papers a newcomer MUST read first and why
Output as a clean outline, not prose."
Print this. Pin it above your desk.
10
PROMPT 9 - The "So What" Test
Run this last. Every time.
"Pretend I have to explain this entire body of research to a
smart non-expert in 5 minutes.
Give me:
1. The one-sentence version of what this field has proven
2. The one honest admission of what it still doesn't know
3. The single real-world implication that matters most
No jargon. No hedging. No academic throat-clearing."
Run this last. Every time.
"Pretend I have to explain this entire body of research to a
smart non-expert in 5 minutes.
Give me:
1. The one-sentence version of what this field has proven
2. The one honest admission of what it still doesn't know
3. The single real-world implication that matters most
No jargon. No hedging. No academic throat-clearing."
11
These 9 prompts turn Claude into a research co-pilot that:
→ Maps 50+ papers in under 30 minutes
→ Finds contradictions you'd miss in 10 hours of reading
→ Surfaces research gaps worth publishing on
→ Builds a knowledge structure you actually remember
Bookmark this thread.
If you found this useful, repost tweet 1 so other researchers see it.
Follow me for more prompts that do the work your PhD advisor never showed you.
→ Maps 50+ papers in under 30 minutes
→ Finds contradictions you'd miss in 10 hours of reading
→ Surfaces research gaps worth publishing on
→ Builds a knowledge structure you actually remember
Bookmark this thread.
If you found this useful, repost tweet 1 so other researchers see it.
Follow me for more prompts that do the work your PhD advisor never showed you.