Create research with sources you can verify1
Generate citation-backed narrative reviews for fast synthesis, or run a systematic review workflow that supports PRISMA 2020 reporting — with AI assistance and human decision control.
1. Every claim links back to the paper it came from — open any citation and read the passage yourself.
A source-linked draft in ~15 minutes·Median 40 references per review·Narrative & systematic workflows
A generated review, every claim linked to its source.
Two paths for research synthesis
Fast when you need a narrative brief. Controlled when you need a systematic review. Both built for health and clinical evidence work, with the source behind every claim one click away.
Narrative Literature Review
~15 minutes
Median time to a source-linked first draft
Systematic Review Copilot
Weeks to months
A review project, every decision on the record
Evidence you can inspect
The reason to trust a synthesis is never that it sounds authoritative. It is that you can follow any sentence back to the paper it came from. Here is that path, end to end.
The search returns papers, not recollections
A question runs against academic databases, the PDFs you uploaded, and your Zotero or Mendeley library. What comes back is a ranked set of real records with real identifiers — the draft is written from those, and only those.
Each claim is written against its own sources
Sentences are drafted from the passages retrieved for that section, and carry the citation for the paper they came from. Citations are checked against the retrieved set as the draft is built; ones that don't resolve are removed rather than left to look plausible.
Any citation opens to the paper behind it
Click an inline citation and you get the title, authors, year, and abstract, with a link straight to the source (Fig. 2). This is the part that matters: you are not asked to trust the synthesis, you are given the means to check it.
Then you can question the evidence directly
Ask across the papers you retrieved — compare statistical approaches, surface disagreements, check what a study actually measured — without leaving the review or pasting anything into a separate chat window.
What opens is the source record itself — title, authors, year, and a link to the original — not the model's restatement of it.
What the record shows
INRA helps researchers save time without giving up the ability to check the work — every figure below is measured across completed reviews on the platform.
- Median time to a source-linked draft
- ~15 minMedian time to a source-linked draft
- Median references per completed review
- 40Median references per completed review
- Reviews completed on INRA
- 10,000+Reviews completed on INRA
“This is a great tool I was surprised how easy it was to use.”
“Writing my dissertation was overwhelming INRA did a good job of helping me organize my thoughts and find relevant studies.”
“The linked citations gave me a ton of confidence in the research and made it so much easier to write my paper.”
Researchers at
One plan, both workflows
Unlimited narrative literature reviews and full access to SLR Copilot. Cancel anytime.
Annual billing works out to six months free.
Professional
$10/month, billed yearly
For researchers who need ongoing access.
- Unlimited narrative literature reviews
- Full SLR Copilot access
- Priority email support
- Word, PDF, LaTeX, and review-data export
Cancel anytime.
Teams & Institutions
$7.50/seat/month, billed yearly
Minimum three seats.
- Everything in Professional, per seat, plus:
- Discounted pricing for multiple seats
- Centralised user management and billing
- Dedicated onboarding and support options
Everything you need to know
Common questions about how reviews are generated, how citations are checked, and how INRA fits the rest of your workflow.
INRA is an AI-powered research platform for source-backed literature reviews and systematic review workflows. For narrative literature reviews, describe your research question and INRA searches across academic databases spanning 220M+ papers, retrieves and ranks the most relevant evidence, organizes it, drafts thematic sections, and attaches validated citations you can inspect. For systematic reviews, SLR Copilot gives your team a structured, human-in-the-loop workflow for protocol setup, citation import, screening, full-text review, extraction, risk of bias, and exports that support PRISMA 2020 reporting.
SLR Copilot guides systematic reviews through a workflow aligned to PRISMA 2020 reporting: setup, citation import and deduplication, title and abstract screening, full-text review, data extraction, risk-of-bias assessment, and export. AI assists with screening suggestions, extraction support, and workflow organization, but reviewer decisions stay under human control. Teams can use dual screening, conflict resolution, full-text PDF workflows, extraction templates, risk-of-bias tools, PRISMA diagrams, and review data exports.
Unlike general-purpose AI tools, INRA only cites papers it has retrieved and analyzed. Every citation links back to the source paper with traceability, and citation-backed answers are grounded in the papers from your research session. This keeps the evidence inspectable and helps prevent fabricated references.
Yes. INRA integrates with your existing research workflow. You can upload your own PDF papers or import your Zotero library. For narrative reviews, INRA can analyze your papers alongside discoveries from academic databases. For SLR Copilot, you can import citation files, search supported databases, resolve IDs, deduplicate records, and manage review-scoped decisions.
INRA searches multiple academic databases in parallel, including PubMed Central for biomedical and medical research, Semantic Scholar for broad academic coverage, arXiv for preprints, Google Scholar, and Unpaywall for open-access full text. This multi-database approach helps broaden source coverage for both narrative reviews and systematic review workflows.
Yes. INRA includes an AI research agent that lets you chat with your compiled research. Ask questions like 'What are the main controversies?' or 'Compare these methodologies' and get citation-backed answers. Responses are grounded in papers from your research session, so you can inspect the sources behind the answer.
INRA is purpose-built for academic research. The key difference is that INRA combines retrieval, source inspection, citation-backed synthesis, and structured review workflows. General chat tools can answer from broad model knowledge and may invent references. INRA grounds outputs in retrieved papers, supports academic database search, generates organized narrative review drafts, and provides SLR Copilot for systematic review workflows that support PRISMA 2020 reporting.
For narrative reviews, INRA supports exports such as Microsoft Word, PDF, and LaTeX/BibTeX for academic writing workflows. For SLR Copilot, exports include PRISMA 2020 flow diagrams and structured review data such as citation, screening, extraction, and reference-manager outputs.
No. INRA is designed to fit around existing research habits. You can continue using tools like Zotero, upload PDFs directly, use database search, and export into writing or review-management formats. INRA handles repetitive work such as retrieval, organization, citation-backed synthesis, and structured workflow tracking while you focus on expert review and interpretation.
Yes. INRA supports multi-language output including Arabic, French, Spanish, German, Chinese, and more. Select your target language before generating a review and the final report will be written in that language. Retrieval stays English-first to maximize source coverage across academic databases, so you get the broadest possible evidence base regardless of output language.
Yes. All research data is encrypted. We never share your research content, questions, or papers with third parties. Your uploaded PDFs and generated reviews are stored securely and only accessible to you.
Build your next review workflow
Start with a citation-backed narrative review, or open SLR Copilot to run a systematic review with your team, on the record.