An AI research analyst that reads the papers, not just the abstracts

What a literature scan actually costs you

A proper scoping review eats a week before you've written a word. You query Google Scholar, Semantic Scholar, and PubMed separately, dedupe the overlap by hand, open forty PDFs, and realize half are paywalled or off-topic by the third paragraph. By the time you've built the reference list, the question you started with has drifted.

The agent runs the searches across the databases you name, opens the full text it can reach, and reads past the abstract — the methods, the sample size, the limitations the authors buried in the discussion. It writes a brief that states what the literature actually agrees on, where the findings conflict, and which claim rests on a single underpowered study. Every sentence carries a citation back to the source it came from.

It works the way you'd want a careful RA to work:

• Searches multiple sources for one question, then merges and dedupes the hits instead of handing you three separate lists
• Opens JS-heavy journal pages and preprint servers, not just whatever the snippet showed
• Pulls structured data straight from an API — OpenAlex, Crossref, a dataset endpoint — when a search box won't do
• Tracks every source in a Google Sheet with DOI, year, and the finding it supports, so the bibliography builds itself
• Flags where two papers contradict each other rather than averaging them into mush

It does not invent a DOI or a quote — if it can't reach the full text, it says so and tells you what it had to work from. That is the difference between a tool you check once and one you stop trusting.

Related pages in this workflow

These pages cover the adjacent jobs buyers usually compare before choosing an AI agent.

• AI Brand Monitoring Analyst — Reads the whole thread, not the headline: it checks the sites you watch each morning and briefs you on what actually changed overnight.
• AI Research Analyst — Hand it a question and a deadline, get a brief that shows its work — figures, links, and the page each number came from.
• AI Research Agent — Hours of digging, back in minutes: it reads the full sources and hands you a structured report with every claim cited.
• AI Market Research Agent — A cited competitive briefing in your inbox on the cadence you set — competitors watched, trends tracked, a source behind every line.
• AI Tutor — Snap a worksheet or paste an assignment: it teaches step-by-step in the student’s language, remembers what they know, and keeps them on schedule.
• AI Language Tutor — A tutor that remembers what you’ve learned: spaced-repetition drills, grammar in your own language, and a nudge the day you’d otherwise skip.
• AI Competitive Intelligence Analyst — The whole market, read for you: it watches competitor pricing, changelogs, and job boards and drops a cited brief the moment something moves.
• AI Data Analyst Agent — A data team without the headcount: point it at a CSV or Sheet and ask in plain language — it cleans, charts, and answers, with full undo.

Frequently asked questions

Which databases can it search?

Anything reachable on the open web — Google Scholar, Semantic Scholar, PubMed, arXiv, bioRxiv, SSRN — plus any source with a public REST API like OpenAlex or Crossref. For an API behind a key, you give it the key once and it authenticates on every call.

Can it get past paywalls?

No, and it won't pretend to. It reads open-access full text, preprints, and abstracts. When the full paper is paywalled it tells you it worked from the abstract and metadata so you know exactly what's behind each claim.

Will it make up citations?

It's built not to. Every reference traces to a page it actually opened, with the link in the brief. If it can't verify a DOI or a quote, it flags the gap instead of filling it. You can spot-check any line against its source.

Can it keep watching a topic over time?

Yes. Tell it to re-run a search every week or month and it will, emailing you only when a new paper changes the synthesis — not a digest of everything it re-read. The reference sheet updates with each run.

What format does the brief come in?

A synthesized write-up with inline citations in chat or email, a linked reference list, and a Google Sheet of every source with DOI and year. It can also generate a formatted DOCX or a PDF report if you need something to circulate.

How much does it cost?

$49/month or $490/year — cancel anytime. Setup runs about four minutes — name the agent, tell it which databases you lean on, and ask your first question. It's in public beta.

AI research analysts by field

One research agent that searches, reads, and cites — pointed at the sources and questions your field cares about.

• AI Research Analyst (hub) — Hand it a question and a deadline, get a brief that shows its work — figures, links, and the page each number came from.
• AI Brand Monitoring Analyst — Reads the whole thread, not the headline: it checks the sites you watch each morning and briefs you on what actually changed overnight.
• AI Competitive Intelligence Analyst — The whole market, read for you: it watches competitor pricing, changelogs, and job boards and drops a cited brief the moment something moves.
• AI Data Analyst Agent — A data team without the headcount: point it at a CSV or Sheet and ask in plain language — it cleans, charts, and answers, with full undo.
• AI Due Diligence Analyst — Hand it a company name, get a brief you can trust: founders, funding, and litigation flags, each with a citation behind it.
• AI Equity Research Analyst — Hand it a ticker, get a cited brief — built from the 10-K, the latest call, and live multiples, every claim linked to its source.
• AI Grant Research Analyst — Finds the grants you actually qualify for: it reads the RFP, checks your eligibility, and hands you a sourced one-pager with the ask and deadline.
• AI Healthcare Research Analyst — Ask a clinical question, get an answer you can defend: a structured brief where every claim links to the paper, trial, or guideline.
• AI Junior Consultant — Brief to deliverable in a single session: it runs the research, organizes the findings, and builds the deck and the client-ready PDF.
• AI Legal Research Analyst — A memo where every claim has a link you can check: it searches the open web and reads the actual opinions and filings.
• AI Market Research Agent — A cited competitive briefing in your inbox on the cadence you set — competitors watched, trends tracked, a source behind every line.
• AI Market Sizing Analyst — TAM/SAM/SOM that shows its work — top-down and bottom-up, every figure traced back to the source it came from.
• AI News Briefing Agent — One briefing every morning, built around your world: your industry, your tickers, your topics — scanned, summarized, and waiting in your inbox.
• AI Policy Research Analyst — It reads the actual bill, not the press release — a sourced brief with section citations, agency dates, and the dissenting view.
• AI Procurement Research Analyst — A sourcing request, back as a cited supplier brief: shortlisted vendors, pricing signals, and lead times, with a source behind each.
• AI Real Estate Market Analyst — A neighborhood read in one sourced doc — comps, days-on-market, price per square foot, inventory trends — instead of twelve open tabs.
• AI Research Agent — Hours of digging, back in minutes: it reads the full sources and hands you a structured report with every claim cited.