This is a preview. We're curious what you'll build with it, and we'd love to hear what you'd want to see before we fully launch.
Check out some API examples for inspiration: github.com/elicit/api-...
This is a preview. We're curious what you'll build with it, and we'd love to hear what you'd want to see before we fully launch.
Check out some API examples for inspiration: github.com/elicit/api-...
Getting started:
1) Create an API key at elicit.com/settings
2) Give Claude or ChatGPT your question + the docs.
3) Run the script it writes or copy a code snippet from the docs and swap in your key.
Within a minute, get your first results from the Elicit API.
Build on top of Elicit. Now you can build research dashboards or combine Elicit evidence with your own datasets.
Integrate Elicit into your workflow. Call the API from Claude or ChatGPT to get real citations while writing a paper, or build a Slack bot that pulls evidence into team discussions. We built one internally to settle debates with data instead of anecdotes.
Run research at scale. Got 30 compounds to check or 20 hypotheses to test? Write a short script and get structured results for all of them instead of running each one manually.
The Elicit API is now available in preview for Pro and Teams users. You can search 138M+ papers and generate Research Reports from your code, scripts, or AI tools.
Get your API key at elicit.com/settings and check out docs.elicit.com
Available now for Pro, Team, and Enterprise users.
Full documentation: support.elicit.com/en/articles...
Combined with full-text screening, Elicit now supports the core PRISMA workflow from search through extraction.
We built this for researchers who need defensible methodology, not just faster answers.
bsky.app/profile/eli...
The output matters as much as the search.
Elicit generates your PRISMA flow diagram with paper counts per source, and our Methods section includes exact query strings and databases. Your search strategy is documented the moment you run it.
Browser-style research interface showing multiple query tabs and a large keyword search box with a complex PubMed Boolean query about statins, type 2 diabetes, mortality and cardiovascular disease.
Elicit Systematic Reviews now lets you run multiple strategies simultaneously in separate tabs. Test query variations side by side, combine semantic and keyword approaches, and search against a variety of corpora
Rigorous systematic reviews require layered search strategies. You need broad semantic discovery to catch conceptually related work, precise Boolean strings for exact terminology, and targeted registry searches for things like clinical trials.
Elicit Systematic Reviews now let you combine multiple search strategies!
You can explore results from AI-based search, keyword-based search, and combine results across many search strategies to ensure comprehensiveness.
Try it at elicit.com!
These two Systematic Review features are now live for Pro, Teams, and Enterprise users at elicit.com
After you search, screen, and extract data from the papers in your Systematic Review, you can generate a report to give you an overview of the research.
Now, Elicit can use 80 papers (double the previous limit of 40) to generate that report, giving you a more comprehensive look into your research.
Papers that fail any strict criteria will appear at the bottom of the screening results page with a label showing they were excluded based on strict criteria. You can still decide to manually include them if needed.
This gives you full control over your inclusion logic in Elicit.
Traditional systematic reviews have strict inclusion/exclusion criteria, where any paper has to meet all criteria to be screened in.
Now, you can enable strict criteria within Elicit to achieve the same results and automatically screen out papers failing to meet a strict criterion.
We’ve made two updates to make Systematic Reviews in Elicit more rigorous and defensible:
Strict screening criteria - Mark criteria as 'strict' to exclude papers that fail to meet them.
80-paper Systematic Review reports - The report at the end of your Systematic Review can use 2x the papers.
Full-text screening will be rolling out later today for Pro, Teams, and Enterprise at elicit.com
Just days ago we released figure extraction from full texts. This latest release continues our relentless work to make your research as systematic and comprehensive as possible, without sacrificing speed or convenience.
bsky.app/profile/eli...
Researchers spend countless hours tracking down PDFs for their reviews.
Our browser extension has been speeding that process up for months, and it now integrates seamlessly with full-text screening. You can also quickly upload PDFs to your review now.
bsky.app/profile/eli...
Abstracts don't contain all the information needed when judging whether to include a paper in your review.
Right now, you only find this out after spending time digging up each paper and reading it yourself.
Elicit's full-text screening catches this at scale, saving you time and letting you focus.
New in Elicit: full-text screening in systematic literature reviews.
You can now apply screening criteria against papers' full texts, not just the abstracts, ensuring that you don’t miss anything in your research.
Get full texts automatically with our Chrome extension, then screen them in seconds.
Figures are currently available to users on the Elicit Team & Enterprise plans. Try it at elicit.com
Elicit was the first AI research tool to analyze data in tables, which we launched two years ago. We’re excited to now be the first to systematically apply frontier multimodal reasoning to help scientists.
Many researchers review the figures first before diving deeper into the paper. You can now do that more seamlessly in Elicit’s paper reader.
When you create a systematic review, Elicit will extract data from figures of up to 1,000 papers.
When you run an Elicit Report, you can see which figures are used to support claims in the report.
Figures contain critical information not always described in the text of papers. Many researchers can determine the quality or relevance of a paper just by skimming the figures.
Elicit now understands figures!
Elicit is the first AI tool that can systematically parse, interpret, and extract data from figures across thousands of papers. That includes Kaplan-Meier curves, heatmaps, reaction schemes, and microscopy images.
We're launching keyword search in Elicit Systematic Reviews
1. Elicit will automatically turn your research question into a keyword query
2. You can keyword search over Elicit, PubMed, and Clinical Trials(.gov)
3. You can view and edit your query until it's robust
Thread 🧵