- Home
- AI Search Engines
- PropensityAI
PropensityAI
Berlin, Germany
What it is
PropensityAI combines retrieval and reasoning to answer questions across the web, documents, and media with concise inline citations. It links important claims to sources, can signal uncertainty, and may 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, while video search locates scenes and spoken content with time-range citations. Users can query research PDFs and citations and compare methods, results, and limitations. The maker describes connectors for shared drives, wikis, ticketing systems, and internal documents. Starter is free, requires no sign-up, and allows up to 16 sources per answer and one file per query. Local packages include 30B Science & Logic and 30B Software Engineering for €8,000.00 once each, plus 130B General Intelligence for €20,000.00 once. Team and Enterprise plans add shared controls, connectors, governance, and deployment options. Enterprise supports on-premises or VPC use, including air-gapped infrastructure.
For and against
For
- Provides inline citations for search answers
- Analyzes images, audio, video, and PDFs
- Starter plan needs no sign-up
- Supports on-premises, VPC, and air-gapped deployments
- Private queries and uploads are not used for training
Against
- Starter allows one file per query
- Starter may throttle at peak
- Local packages start at €8,000.00 once
The verdict
PropensityAI brings cited retrieval and reasoning to varied sources, with media analysis and research comparison tools. Its free entry plan is limited, while local and enterprise options target organizations with larger deployment and governance needs.
Who it suits
PropensityAI suits people researching across mixed media, PDFs, and internal knowledge sources. Teams needing connectors, access controls, or local deployment can consider its Team and Enterprise offerings.
Plans and prices
Starter
Up to 16 sources per answer · 1 file per query · Standard + Reasoning models (best-effort; may throttle at peak) · Basic citations
Read 8 Oct 2026 · propensityai.com
30B Science & Logic
Dedicated hardware and LLM included · Tailored for R&D and analytical teams · Open-weight model with commercial-use license
Read 8 Oct 2026 · propensityai.com
30B Software Engineering
Dedicated hardware plus model · Code generation and debugging · Open-weight model with commercial-use license
Read 8 Oct 2026 · propensityai.com
130B General Intelligence
Pre-configured hardware and LLM bundle · Open-weight model with commercial-use license · Secure local deployment
Read 8 Oct 2026 · propensityai.com
Enterprise
Up to 40 sources per answer · Up to 10 files per query · On-prem / VPC · Advanced governance
Read 8 Oct 2026 · propensityai.com
Team
Up to 30 sources per answer · Up to 10 files per query · Shared docs and connectors · Access control
Read 8 Oct 2026 · propensityai.com
On the record
- Audio and video
- Audio analysis can transcribe, diarize, summarize, and extract tasks; video search can find scenes and spoken content with time-range citations.propensityai.com · read 8 Oct 2026
- Company location
- The site says PropensityAI ships from Berlin, Germany; its privacy policy names FetchCFD UG (haftungsbeschränkt) as the responsible party and gives a Berlin address.propensityai.com · read 8 Oct 2026
- Deployment
- Enterprise supports on-premises or VPC deployment, and the maker offers local LLM systems that can run inside a customer's infrastructure, including air-gapped deployments.propensityai.com · read 8 Oct 2026
- Grounded answers
- It links key claims to sources and can flag uncertainty or refuse when it lacks supporting evidence.propensityai.com · read 8 Oct 2026
- Image analysis
- Image features include OCR, captioning, visual question answering, and structured extraction.propensityai.com · read 8 Oct 2026
- Integrations
- The maker describes typical internal knowledge-base connectors for shared drives, wikis, ticketing systems, and internal documents.propensityai.com · read 8 Oct 2026
- Intended users
- The Team plan is described for teams using shared documents and connectors, while Enterprise is described for secure deployments, VPC, and governance.propensityai.com · read 8 Oct 2026
- Local package terms
- The maker says local LLM packages are one-time purchases with no per-token usage fees.propensityai.com · read 8 Oct 2026
- Privacy
- The site says private queries and uploaded files are not used to train foundation models; Team and Enterprise plans also list no model training on user data.propensityai.com · read 8 Oct 2026
- Research papers
- Users can ask questions across PDFs and citations and compare methods, results, and limitations.propensityai.com · read 8 Oct 2026
- Security
- The site lists a SOC2-ready roadmap and SSO, and says Enterprise includes advanced governance and dedicated support.propensityai.com · read 8 Oct 2026
- What it does
- PropensityAI combines retrieval and reasoning to provide concise, cited search results across the web, documents, and media.propensityai.com · read 8 Oct 2026
