Elicit Blog

Evaluating Elicit’s Paper Search
Elicit outperformed five other search systems on BioASQ, retrieving more of the papers biomedical experts rely on.
Read more

The Elicit API and MCP: Powering autonomous research engines
The Elicit API and MCP server bring Elicit’s trusted capabilities to your agents and workflows.
Read more

How AI will change Pharma R&D
We've had more than 500 conversations with the top pharma companies and many external advisors. Here's what we believe about the future of R&D.
Read more

Elicit Systematic Review: Now Built for PRISMA 2020
Elicit Systematic Review now supports PRISMA 2020 guidelines, and is reproducible, traceable, and auditable at every step.
Read more

Evaluating Elicit’s Systematic Literature Review Capabilities
Elicit hit 95% search recall, 97% abstract screening, 99% full-text screening, and 96% extraction across 994 Cochrane reviews.
Read more

Planning is unsolved
Models are getting better at long-horizon tasks. So why don't they help much when you're planning clinical development or thinking through a launch?
Read more

What’s going on in AI?
This is an excerpt from Elicit's April 2026 investor update. I take a step back, provide situational awareness, talk about hard-to-verify tasks, ...
Read more

Engineering interviews in the era of agents
Two years ago we published our stance on coding assistants in interviews. A lot has changed…
Read more

Introducing the Elicit API
Search our 138M+ papers and generate Reports using our API.
Read more

The AI Force Multiplier – Orchestrating Integrated Evidence to Drive Biopharma Value
Integrated evidence sooner
AI elevates RWE planning into a corporate strategic mandate
Read more

Science and Culture, Part II: The Arnold-Huxley debate
First public debate on modern science education
The Arnold-Huxley debate on the role of sciences and humanities in education encapsulates some of the best arguments on both sides.
Read more

Elicit Achieves SOC 2
Elicit achieves SOC 2 Type II certification.
Read more

Introducing Keyword Search
Elicit Systematic Reviews now supports keyword search queries over Elicit, PubMed, and ClinicalTrials.gov.
Read more

Looking for Hidden Gems in Scientific Literature
The Promise and Practice of Literature-Based Discovery
Scientific literature is vast and contains within it as yet unnoticed connections. Literature-based discovery is an attempt to bring them to light.
Read more

Introducing Clinical Trials
Clinical Trials are now in Elicit. Search over 545,000 studies on clinicaltrials.gov and instantly summarize them into tables or reports.
Read more

Introducing Elicit Alerts
Other automated alerts don't work: they're noisy and inefficient. Elicit Alerts leverages AI to surface relevant research and reduce wasted time.
Read more

How we evaluated Elicit Systematic Review
Elicit's Systematic Review is our most advanced workflow, delivering human-level accuracy in evidence synthesis at a fraction of the cost and labor.
Read more

How we evaluated Elicit Reports
Elicit Reports provide automated research overviews with higher quality and efficiency than other deep research tools.
Read more

Elicit Raises $22M to Build the Most Trusted AI Platform for Evidence-Backed Decisions
Elicit has raised $22M in Series A to expand beyond academia, building AI infrastructure for evidence-based reasoning across multiple industries.
Read more

Introducing Elicit Reports
Introducing Elicit Reports: fully automated rigorous research overviews, designed for researchers, and built on the principles of systematic reviews.
Read more

Introducing Elicit Systematic Review
Elicit Systematic Review turns months of manual work into minutes, guiding researchers through each step while preserving rigor and accuracy.
Read more

Against RL: The Case for System 2 Learning
Reinforcement learning may boost LLMs today, but it cannot deliver safe, long-term intelligence. We argue for System 2 learning instead.
Read more

Trust at scale: Auto-evaluation for high-stakes LLM accuracy
Elicit develops LLM-based auto-evals to balance scale, trust, and flexibility, ensuring reliable scientific reasoning at superhuman speed.
Read more

Scaling your impact: A polynomial model of career growth
Beyond ladders: a polynomial model of career growth.
Read more

How to Hire AI engineers
Not every AI role needs a PhD in ML. A good AI engineer can bridge full-stack skills with LLM expertise, making AI practical in real products.
Read more

From grep to SPLADE: A Journey Through Semantic Search
Elicit implements SPLADE to leverage semantic search while retaining consistent rigor and accuracy.
Read more

Introducing Notebooks: A New Way to Analyze Papers in Elicit
Elicit introduces Notebooks: a new way to analyze research by unifying search, summaries, and systematic review on a single, living page.
Read more

How We Launch a User-facing Feature Every Week
Elicit has launched a new user-facing feature nearly every week since 2021, making iteration at speed our core practice. We know how to do it well.
Read more

Discovering Alignment Windfalls Reduces AI Risk
An argument for "alignment windfalls": when safer AI systems don’t just reduce risk, but generate immediate value for companies and society.
Read more

Coding Assistants in Technical Interviews: Our Stance
Elicit's nuanced stance on coding assistants in interviews: welcome as tools for testing insight, but not as replacements for genuine reasoning.
Read more

Build a Search Engine, Not a Vector DB
Don’t confuse embeddings with memory. To build effective RAG, start with a search engine, not just a vector database.
Read more

Factored Verification: Detecting and Reducing Hallucinations in Frontier Models Using AI Supervision
We evaluate an automated approach for catching hallucinations in paper abstracts, aiming for consistently more trustworthy results.
Read more

Elicit and AI Safety
Elicit’s two main contributions to AI Safety are strengthening epistemics and pioneering advanced process supervision.
Read more

Elicit's Core Bets: Be Systematic, Transparent, and Unbounded
Many AI assistants promise ease of use. Elicit distinguishes itself by making reasoning systematic, transparent, and unbounded.
Read more

Elicit's Mission Is to Scale Up Good Reasoning
Our mission at Elicit is to scale up good reasoning — because better reasoning leads to better decisions, at every level.
Read more

Elicit Raises $9 Million and Becomes a Public Benefit Corporation
With $9M in new funding, Elicit advances its mission: using language models to make scientific reasoning faster and more reliable.
Read more