Consensus vs PropensityAI

Consensus is an AI workspace and academic search engine for scientific research, available on web, Android, iOS, and as an extension. It searches more than 220 million peer-reviewed papers, with the database updated weekly, and offers filters for publication date, access, citations, journal rank, study design, population, sample size, and other paper details. Its Research Agent plans multi-step searches, uses tools such as citation crawling and DOI lookup, and returns citation-backed answers. Consensus says citations in its AI summaries correspond to exact paper quotes, with the relevant section identified and PDF text highlighted when available. Medical Mode searches a selected collection of about 8 million papers and 50,000 clinical guidelines from the top 1,000 medical journals. Users can import Zotero libraries and export CSV or RIS files for reference managers. Consensus also works in ChatGPT, Claude, and Microsoft 365 Copilot; API and MCP calls share a monthly allowance. The Free Tier costs nothing. Pro is $20 a month, or $144/year billed annually; Deep is $65 a month, or $540/year billed annually.

PropensityAI combines retrieval and reasoning to answer questions across web pages, documents, and media with concise inline citations. It links claims to sources, flags uncertainty, and can decline when evidence is insufficient. Image analysis includes OCR, captioning, visual question answering, and structured extraction. Audio tools transcribe, identify speakers, summarize, and extract tasks. Video search locates scenes and spoken content with time-range citations. Users can query research PDFs and citations, then compare methods, results, and limitations. The maker describes connectors for shared drives, wikis, ticketing systems, and internal documents. Starter costs nothing, needs no sign-up, and allows up to 16 sources and one file per query. Local packages cost €8,000 as a one-time purchase for 30B Science & Logic or 30B Software Engineering, and €20,000, paid once for 130B General Intelligence. Team and Enterprise plans add shared connectors, controls, analytics, on-premises or VPC deployment, governance, and support. Enterprise can run local systems inside customer infrastructure, including air-gapped environments. The site says private queries and uploads are not used to train foundation models.