What is Consensus?
Consensus is an AI-powered academic search engine that helps you find, understand, and synthesize scientific research.
Unlike general AI tools, Consensus searches the scientific literature first and grounds its answers in real research papers. It helps you quickly find relevant studies, review the evidence, and understand what the literature says.
Over 10 million researchers, clinicians, students, and professionals use Consensus to find the best science, faster.
What does Consensus search?
Consensus searches across a database of over 220 million peer-reviewed research papers.
Our paper data comes from trusted sources, including:
Consensus’s own crawl of the scholarly web
Consensus covers all domains and fields of science - from astronomy to sociology to biochemistry! We include papers from most major academic journals, including all of PubMed.
Our research database is updated weekly as we continue expanding coverage and adding newly published research.
Learn more about the Consensus Research Database here.
How does a Consensus search work?
Consensus is designed to find the most relevant papers for your search to ground our AI-generated summaries. Every search goes through three key stages:
Step 1: Cast a wide net
We begin by scanning our entire database of over 220 million papers to find the most relevant results using a hybrid approach:
Semantic search (AI embeddings): Captures the intent behind your search and supports natural language queries.
Keyword search (BM25): A traditional method that anchors results to the exact terms in your query for precise keyword matching.
This means you can search using natural-language questions, keywords, Boolean operators, paper titles, authors, DOIs, and more.
When full text is available, Consensus can search beyond the title and abstract and use information from sections such as the methods, results, and discussion.
Step 2: Refine by quality
Consensus identifies the papers most relevant to your query and considers research-quality signals such as:
Recency of publication
Citation count
Journal impact and reputation
This step ensures your results are highly relevant and backed by high-quality, credible science.
Step 3: Rank the top 20 papers
In this final step, we rank the top 20 papers as accurately as possible. This works similarly to Step 2, but includes two key upgrades:
Relevance is recalculated using a larger, more powerful AI model
This high-precision model is applied only to the top 20 papers to ensure efficiency and accuracy
We continue to factor in recency, citation count, and journal impact, so the final list reflects both relevance and rigor.
If Consensus can't find sufficient relevant evidence, it will tell you rather than filling in the gaps with outside information.
How does Consensus analyze the research?
Once relevant research has been found, Consensus uses AI to read, extract, compare, and synthesize the findings.
Depending on your question and the type of search you're running, Consensus can:
Summarize findings across multiple papers
Compare studies, populations, interventions, or outcomes
Extract details such as methods, sample size, and results
Identify areas of agreement and disagreement
Create tables and other structured outputs
Explore citations and related research
Identify gaps in the literature
For more complex research tasks, Consensus can also plan and carry out multiple research steps, using the appropriate search and analysis tools along the way.
Every AI-generated synthesis includes citations so you can trace claims back to the research used.
Key Features
🤖 Research Agent: Handles complex, multi-step research questions by planning searches, chaining together tools, and applying academic filters.
🔬 Deep Review: Conducts an in-depth synthesis of 50–100 papers to provide a more comprehensive analysis of complex research questions.
📂 My Library: Organize and save papers into custom collections so you can easily revisit and manage your research.
📊 Consensus Meter: Uses AI to analyze and visualize the level of agreement or disagreement in the literature in response to yes-or-no questions.
🔍 Advanced Search Filters: Refine your search using AI-powered filters to surface more relevant and tailored results.
💬 Chat with Full Text: Ask questions across the full text of specific papers, Collections, or your uploaded documents to receive in-depth answers about methods, findings, and more.
🔗 Citation Graph: Explore how research papers are connected through citations to find foundational studies, related research, and papers that build on earlier findings.
How Consensus uses AI responsibly
We are committed to using AI ethically, transparently, and with purpose. Always in service of helping researchers, students, and educators save time without sacrificing trust and accuracy.
Several safeguards are built into the process:
Search comes first. AI generates answers only after relevant research has been retrieved.
Papers are checked for relevance. Research must contain information relevant to your question before it can be included in an analysis.
Answers include citations. You can trace claims back to the papers that support them.
Supporting evidence is available. Citations can surface the passages used to support individual claims when that evidence is available.
Retracted papers are identified and excluded from AI analyses.
Learn more here: Responsible AI & Limitations
Learn more
Ready to start searching? Check out How to Search & Best Practices for guidance on getting the most out of Consensus.
For more detailed product documentation, visit the Consensus Docs: https://docs.consensus.app/
Still have questions? We're happy to help: https://consensus.app/home/contact/