We are committed to using AI ethically, transparently, and purposefully. Our goal is to help researchers, students, and educators save time without sacrificing trust or accuracy.
How Consensus uses AI
Every AI-generated response starts with a search of real, peer-reviewed scientific literature. This ensures our summaries are always grounded in actual research.
We only use AI after we search the scientific literature.
Every response is grounded in real, citable research papers, not speculative content generated by a model.
Once relevant papers are retrieved, we use AI in two key ways:
To analyze individual papers in depth (e.g. Ask Paper, Study Snapshot)
To synthesize findings across multiple papers (e.g. Pro Analysis, Consensus Meter)
We use two types of AI models in these AI features:
Commercial models (like OpenAI) for general-purpose summarization
Fine-tuned open-source models for domain-specific features, like the Consensus Meter
Generative AI is a powerful tool that can help us reclaim valuable time to focus on what matters most - which is why, at Consensus, we've built in safeguards to ensure it's used responsibly and effectively.
Guardrails
Search before synthesis: Every response starts with a literature search. This ensures all citations are real papers, never hallucinated or invented sources.
Summarization, not speculation: Our AI tools are strictly limited to summarizing content from the papers retrieved. They don’t "fill in the blanks" with outside knowledge.
At our core, we are a search engine, not a chatbot, meaning every source we cite will be a real paper and only one click away
Transparent sourcing and attribution: Every claim is cited, and every citation is clickable. We make it incredibly easy in our interface to inspect, verify, and reference the original source content with one click.
AI "checkers" for relevance: Before summarizing, we use separate models to verify that the source actually contains information relevant to the query. If a paper doesn’t meet our threshold for relevance, it won’t be used in the response. Think of this as a measure to make sure that we “set our models up for success”.
Tight feedback loops: We have an in-product support portal and always encourage users to report any mistakes, allowing us to address and resolve issues promptly. We see every support ticket and try to reply within the day, we also have a dedicated slack channel to solicit further feedback
Consensus is built to enhance, not replace, the research process. Our goal is to provide a faster path to high-quality evidence, while always keeping humans in control.
Limitations
While we are proud of the Consensus product today, there are still plenty of limitations and our features will continually be a work in progress.
We do not have access to ALL research
The Consensus database includes over 220 million peer-reviewed papers. While this represents significant coverage, there is plenty of amazing research that we do have access to. The summary is just a snapshot of some of the relevant research that we have access to, not a fully-comprehensive look into all of the research regarding your question.
Hallucinations can occur
Hallucinations are a common issue in AI systems where the model generates something that is not true. These usually fall into three categories:
Fake sources – the AI cites a paper or article that doesn’t exist.
Wrong facts – the AI generates a confident answer from internal memory that’s simply incorrect with no source.
Misread sources – the AI summarizes a real paper or source, but gets it wrong.
Thanks to how we’ve built Consensus, only the third type is possible, and we work hard to minimize it.
Consensus is not a chatbot. It’s a search engine that uses AI to summarize real scientific papers. Every time you ask a question, we search a database of peer-reviewed research. That means:
Every paper we cite is guaranteed to be real
Every summary is based on actual research, not a model’s guess or internal memory
Still, no AI is perfect. Sometimes a model can misinterpret a paper and summarize it incorrectly. To reduce this risk, we’ve added safeguards like “checker models” that verify a paper’s relevance before summarizing it.
Most importantly, we’ve designed the product to make it easy for you to dive into the source material yourself. The best use of Consensus isn’t just getting a quick summary, it’s using our tools to explore the research in depth. That’s when real understanding happens.
Final Thoughts
Our mission is to make the best science accessible to everyone through AI, but responsible use is essential. While we continuously improve Consensus with more guardrails, we recognize the technology's limitations and are committed to give you transparency every step of the way.
We encourage you to stay engaged with our platform by exploring the source materials, sharing any feedback, and reporting inaccuracies through our support portal. Your feedback helps us improve and make AI-powered research tools more accurate for everyone.
Thank you for being a part of our journey!
If you have questions or need assistance, reach out to our support team at [email protected] or via the Support Chat in the interface. We’re here to help!