Elicit vs PropensityAI

Elicit is an AI research assistant for researchers gathering and assessing evidence. Its Research Agent draws on scientific databases, academic journals, public data sources, uploaded documents, a corpus of 138 million academic papers, and the wider web. A session can use up to 20 uploaded resources, including PDF, DOCX, XLSX, PPTX, and JPG files. Elicit offers Research Agent sessions, Research Reports, and Systematic Reviews, and supports AI-generated claims with sentence-level citations to underlying sources. It can find up to 1,000 relevant papers and analyze up to 20,000 data points at once. Research Reports export as PDF or Word, tables as CSV or Excel, and references as RIS or BIB. Elicit runs on the web and provides an API, but API access requires Pro or above. Its MCP server connects to Claude Desktop, Claude Code, and other compatible clients using OAuth 2.0. Basic is free with limited usage for Research Agent and Research Reports; Plus costs $11 a month. Pro is $39 a month and Scale is $89 a month. Elicit states that it has achieved SOC 2 Type II compliance.

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.