Elicit: The AI Research Assistant For Systematic Reviews

Elicit automates slow parts of academic research: finding papers, extracting data, building literature matrices. Look at what it saves PhDs 20 hours a week.

38 min · Reviewed 2026

Elicit is an AI research assistant built by Ought, designed to automate tedious parts of academic research — finding relevant papers, extracting key findings from them, and building structured literature matrices. It's less about quick answers (like Consensus) and more about doing the actual work of a systematic review. By 2026 it's widely adopted in PhD programs, policy research, and biotech companies, and it charges accordingly.

What it's genuinely good at

Paper finding — surfaces relevant papers beyond what keyword search would catch.
Data extraction — pulls sample sizes, effect sizes, methods, and outcomes into a table.
Summary columns — customize what Elicit extracts from each paper you care about.
Literature matrix — structured output that maps to how reviewers actually work.
Citation analysis — snowball citations to find related work.
Stays grounded — answers are strictly from the papers in your matrix.

What it struggles with

Extraction errors — data extraction misreads tables, especially in scanned PDFs.
Slower than you'd expect — processing 50+ papers takes many minutes per step.
Cost — research-scale use burns through credits on the Plus plan quickly.
Limited to open-access papers for full-text analysis — paywalled papers are abstract-only.
UI is busy — takes real time to learn the workflow.

Pricing (April 2026)

Basic: Free — limited searches, basic summarization.
Plus: $12/month — 12,000 credits/month, full extraction features.
Pro: $42/month — 50,000 credits, priority processing, Notebooks.
Enterprise: Custom — team features, larger usage, institutional billing.

Who should bother: PhD candidates doing literature reviews, policy researchers, biotech companies doing evidence assessments, anyone running systematic reviews. Who shouldn't: casual users (Consensus is simpler), humanities researchers whose papers aren't in the corpus, price-sensitive users. Elicit is the best tool for the narrow but valuable use case of structured academic research automation.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-tool-elicit-creators

What is the main idea of "Elicit: The AI Research Assistant For Systematic Reviews"?
1. Elicit automates slow parts of academic research: finding papers, extracting data, building literature matrices.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Elicit: The AI Research Assistant For Systematic Reviews"?
1. literature review
2. Elicit
3. research automation
4. data extraction
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Paper finding — surfaces relevant papers beyond what keyword search would catch.
4. Treat the AI output as automatically correct
What should a careful learner remember about "The gotcha"?
1. Use "The gotcha" as a reminder to verify the AI output before anyone relies on it.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about Elicit be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about Elicit.
Which action would help you apply "Elicit: The AI Research Assistant For Systematic Reviews" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Data extraction — pulls sample sizes, effect sizes, methods, and outcomes into a table.

← Back to interactive lesson

Tendril · Creators · Tools Literacy