Literature review is where research begins — and where most of the wasted weeks live. Searching five databases with five interfaces, deduplicating exports, and stitching quotes into a document that goes stale the moment it's finished. Here is how the same work runs in Neutropic.
One question, every database
Ask a research question in plain language and the agent fans out across PubMed, Crossref, OpenAlex, and Semantic Scholar in parallel — plus Scopus, Web of Science, and KCI when your institution's access is connected. Results are deduplicated across sources, and the search strategy itself is recorded so your methods section can report exactly what was searched, and when.
Every sentence accountable
The output is not a pile of abstracts but a synthesized review in which every sentence carries an inline citation to a real source. Click a sentence and a source panel shows exactly which studies support it — with the quoted passage and why it was cited. Sentences no source supports are flagged visibly, not smoothed over.
- Claims attributed to a named study cite the original paper, not a later mention of it.
- Secondary citations are marked as such when the original couldn't be retrieved.
- A source table breaks down the evidence by database, venue tier, and year.
The field as a structure
Beyond the report, the agent maps the literature: theories, constructs, methods, and findings, and how they relate. Contradictory results cluster together instead of hiding pages apart, and unstudied combinations surface as gaps — the raw material for your next hypothesis.
Always current, never stale
A review in Neutropic is a living artifact. Re-run it next quarter and new publications flow into the same structure, with changes highlighted — so the review you wrote for the grant application is still accurate when the reviewers read it.
The goal isn't to read less. It's to spend your reading on the papers that matter, with the bookkeeping already done.
