01.
The frozen protocol
Inclusion criteria, exclusion criteria and search strings, locked before the search runs. No moving goalposts.
The audit grade AI research workspace
Stop searching.Start reading.
One question in. Searches, interviews, data and a finished manuscript out, every step on the record.
240M+ works · Question to manuscript · Every decision logged
The name is the method: six sentences from question to literature base.
The record
Not a chat transcript. A record you can defend.
SixSentences_ documents the search the way a methods chapter would. The protocol is frozen before the first query runs, every screening decision carries a written reason, and the final numbers reconcile. If a reviewer asks why paper 41 is out, the answer is one click away.
app.sixsentences.com
A REAL FINISHED SEARCH: 457 FOUND · 420 SCREENED · 30 INCLUDED
02.
The decision ledger
Every include and every exclude with its reason attached. Not a sample. All of them.
03.
The report
PRISMA style flow counts and citations, exported as RIS, BibTeX, CSL JSON or pushed straight to Zotero.
Between searches
A research assistant that shows its work.
Most days you are not running a review. You are checking a claim, chasing a reference, or reading. SixSentences_ keeps working between the big searches.
01 · grounded
Answers that show sources
The assistant quotes what it cites, cites what exists, and says so when it finds nothing. Every claim links back to a real paper.
02 · library
A living library
Retrieved full texts stay in your workspace. Read them in place, search inside them, and ask questions across everything you collected.
03 · pipeline
API and webhooks
Everything the interface can do, your scripts can do too. Start searches, pull results, and wire the record into your own pipeline.
The workspace
Your questions, your rules.
The morning after a search: your library on the left, the paper you are reading on the right, and a conversation in between that quotes its sources.
app.sixsentences.com
01 · model
Choose your model
Every question can run on the model you trust, or on auto, which picks the cheapest one that does the job. You decide which provider sees your text.
02 · tactic
Choose your tactic
A grounded quick answer in seconds, a deep screen over full texts, or the whole systematic method overnight. You set depth, criteria and scope per run.
03 · privacy
Privacy is the house rule
Your protocols, decisions and library stay in your workspace and serve no other purpose. Delete a chat, a search or the whole account any time, and it is gone.
Manuscript Studio
Write the manuscript where the evidence lives.
A structured authoring room with the search wired in: import Word or start from your own template, navigate a live outline, let the assistant propose edits, connect your own sources and research data, and compile the PDF as you write.
app.sixsentences.com
THE SEARCH FROM ABOVE, WRITTEN UP: ITS 30 INCLUDES ARE THE BIBLIOGRAPHY
01 · cite
A bibliography with receipts
references.bib combines the include set of your searches with your own PDFs, BibTeX and RIS. Every source receives a real key before the assistant can cite it.
02 · edit
Edits arrive as proposals
Ask for a rewrite and you get a diff: exact find and replace, applied only when you accept it. Highlight a passage in the PDF and discuss exactly that passage.
03 · results
Your data joins the argument
Import CSV, JSON or Excel with provenance and missingness intact. Ask the assistant to use exact values, or turn them into a deterministic chart for the paper.
Interview Studio
Your interviewer, on call around the clock.
Qualitative interviews used to be the bottleneck: recruiting, scheduling, transcribing, coding. Now you design a study once, pilot it by talking to your own interviewer, then share a link. Participants have a real conversation by voice or in writing, and every session returns as evidence you can defend. Uploaded recordings go through the same transcription and verified analysis.
app.sixsentences.com
A REAL STUDY: THE DESIGNER CHAT ON THE LEFT, THE VERSIONED GUIDE IT WROTE ON THE RIGHT
app.sixsentences.com
THE CONVERSATION ITSELF, CAPTURED LIVE: DISCLOSED AS AN AI, CAPTIONED, INSIDE THE TIME BUDGET
01 · design
Design the study in conversation
Describe what you want to learn and the study designer drafts the guide, tunes the interviewer and writes the consent text. Run it guided along your topics, or iterative: one opening question, and every follow up grows out of what the person actually said.
02 · talk
A voice that listens first
Participants open a link, read what the study is about, and give timestamped consent before a single word is recorded. The interviewer always introduces itself as an AI, speaks or types in your study language, and stays inside the minutes you budgeted.
03 · evidence
Every quote is checked
Each conversation lands as a transcript with speakers and timestamps, plus an analysis whose quotes are verified verbatim against that transcript. Unlocatable quotes are flagged, never presented as evidence, and each interview closes with testable hypotheses for the next one.
The Workspace
The search grew into the whole study.
Literature is where research starts, not where it ends. Around the search sit the rooms a study actually needs, and they share one memory: your sources, your data, your interviews and your manuscript reference each other instead of living in five tools. Everything keeps the same house rule: every claim carries its evidence, in German or English.
app.sixsentences.com
THE VISUAL LAB: ONE BRIEF PER FIGURE, ANY FIELD, PAPER READY
interviews
Interviews
Upload recordings or let the AI interviewer run the conversation. Speaker attributed transcripts, quotes verified verbatim, hypotheses for the next session.
surveys
Surveys
Design questionnaires in conversation, share protected links, and watch responses arrive live. Results publish straight into your research data.
data hub
Data Hub
Version pinned datasets with honest profiles. Deterministic analyses up to a full meta analysis with forest and funnel plots, and exact charts that never estimate.
visual lab
Visual Lab
Publication figures with a real visual review pass. Hand it a whiteboard photo or a rough sketch and it redraws the figure professionally, keeping every label.
projects
Projects and records
One workspace per study: question, study map, claims with linked evidence, risk of bias, submission checklist and a reproducibility manifest at the end.
library
Library
Every full text in one place, readable next to the chat. Even a phone photo of a lecturer's PDF becomes a transcribed, quotable source.
review
Sharing and review
Publish a search as a public record, or share a manuscript as a password protected review link. Reviewer comments land in your editor live, anchored to the passage.
automation
API and agents
API keys, webhooks and an MCP server, so your own tools and agents can search, read records and pull bibliographies from the same audited workspace.
Sources & exports
Searched in full, exported in yours.
Every search sweeps the major catalogs in one pass: more than 240 million scholarly works spanning PubMed, Crossref, arXiv and DOAJ, unified in one open index. Grey literature joins in from the open web, and full texts are retrieved wherever they are openly available.
Visit openalex.orgOpenAlex
OpenAlex
PubMed
Crossref
arXiv
DOAJ
DOI
Zotero
BibTeX
RIS
CSL JSON
JSON API
webhooks
Pricing
Start free. Scale when the reviews do.
Each step unlocks a coherent research layer, from a free core workspace through discovery, the complete solo system and team collaboration. One calm meter shows the monthly capacity left; usage follows the work actually performed.
Free
$0/month
Understand papers, organize your work and complete a real basic review.
- PDF chat, notes, projects and library
- Basic systematic search and screening
- Interviews, surveys and figures on the starter meter
- 100 MB storage · up to 20 PDFs
- Up to 150 works per run
- Starter monthly capacity
Scout
$9/month
For focused projects that need stronger discovery, imports and research tooling.
- Everything in Free
- Live, semantic and citation discovery
- Boolean search, Zotero and database imports
- Document imports and Visual Lab starter
- Interview transcription, surveys and photo sources
- 1 GB storage · up to 250 PDFs
Popular
Scholar
$29/month
The complete solo research system, from discovery to a finished manuscript.
- Everything in Scout
- Full text, deep screening and web sources
- Complete Manuscript Studio and Visual Lab
- AI-led interviews, Data Hub and meta analysis
- Evidence extraction, API and living reviews
- 10 GB storage · up to 2,500 PDFs
Cohort
$99/month
For labs and reading groups that share one workspace and one record.
- Everything in Scholar
- Shared workspace for up to 10 researchers
- Pooled team capacity and reviewer coordination
- 25 GB storage · up to 10,000 PDFs
- Up to 30,000 works per run
Extra capacity
Ran dry before the month did? Buy a one-time pack inside the workspace: Boost adds 15% for $9, Surge 50% for $25, Reserve 120% for $49. Packs are spent only after your monthly capacity, never expire, and are deliberately premium: if you reach for them every month, the next plan is the better deal.
FAQ
Fair questions, straight answers.
The things researchers ask before they trust a tool with their methods chapter. If you need more, write to us and a person answers.
Early access
Six sentences away.Be first in line.
We are onboarding researchers in small waves. Leave your email and we will wake you when it is your turn.
Already have access? Sign in