# 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](/content/blog/evaluating-elicit-paper-search/index.html)

**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](/content/blog/the-elicit-api-and-mcp-powering-autonomous-research-engines/index.html)

**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](/content/blog/ai-pharma-rd/index.html)

**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](/content/blog/systematic-review-for-prisma-2020/index.html)

**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](/content/blog/evaluating-elicit-slr/index.html)

**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](/content/blog/planning-is-unsolved/index.html)

**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](/content/blog/situational-awareness-april-2026/index.html)

**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](/content/blog/engineering-interviews-in-the-era-of-agents/index.html)

**Introducing the Elicit API**  
Search our 138M+ papers and generate Reports using our API.  
[Read more](/content/blog/elicit-api/index.html)

**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](/content/blog/ai-evidence-biopharma/index.html)

**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](/content/blog/science-and-culture-part-2/index.html)

**Elicit Achieves SOC 2**  
Elicit achieves SOC 2 Type II certification.  
[Read more](/content/blog/elicit-achieves-soc-2/index.html)

**Introducing Keyword Search**  
Elicit Systematic Reviews now supports keyword search queries over Elicit, PubMed, and ClinicalTrials.gov.  
[Read more](/content/blog/introducing-keyword-search/index.html)

**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](/content/blog/literature-based-discovery/index.html)

**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](/content/blog/clinical-trials/index.html)

**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](/content/blog/introducing-elicit-alerts/index.html)

**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](/content/blog/how-we-evaluated-elicit-systematic-review/index.html)

**How we evaluated Elicit Reports**  
Elicit Reports provide automated research overviews with higher quality and efficiency than other deep research tools.  
[Read more](/content/blog/elicit-reports-eval/index.html)

**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](/content/blog/series-a/index.html)

**Introducing Elicit Reports**  
Introducing Elicit Reports: fully automated rigorous research overviews, designed for researchers, and built on the principles of systematic reviews.  
[Read more](/content/blog/introducing-elicit-reports/index.html)

**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](/content/blog/systematic-review/index.html)

**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](/content/blog/system-2-learning/index.html)

**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](/content/blog/auto-evaluation/index.html)

**Scaling your impact: A polynomial model of career growth**  
Beyond ladders: a polynomial model of career growth.  
[Read more](/content/blog/career-growth/index.html)

**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](/content/blog/how-to-hire-ai-engineers/index.html)

**From grep to SPLADE: A Journey Through Semantic Search**  
Elicit implements SPLADE to leverage semantic search while retaining consistent rigor and accuracy.  
[Read more](/content/blog/semantic-search/index.html)

**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](/content/blog/notebooks/index.html)

**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](/content/blog/launching-a-feature-every-week/index.html)

**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](/content/blog/alignment-windfalls/index.html)

**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](/content/blog/coding-assistants-and-interviews/index.html)

**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](/content/blog/search-vs-vector-db/index.html)

**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](/content/blog/factored-verification-detecting-and-reducing-hallucinations-in-frontier-models-using-ai-supervision/index.html)

**Elicit and AI Safety**  
Elicit’s two main contributions to AI Safety are strengthening epistemics and pioneering advanced process supervision.  
[Read more](/content/blog/ai-safety/index.html)

**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](/content/blog/core-bets/index.html)

**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](/content/blog/mission/index.html)

**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](/content/blog/elicit-raises-9-million-and-becomes-a-public-benefit-corporation/index.html)