Arc Search vs Embase AI
Arc Search
arc.netEmbase AI
elsevier.comSide by side
| Figure | Arc Search | Embase AI |
|---|---|---|
| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| iOS | Yes | Yes |
| Android | Yes | Yes |
| Plans published | 1 | 1 |
| Spec score · AI Search Engines | 8.1 (#9) | 7.6 (#18) |
| Privacy | The maker says Browse for Me sends the command bar content and search result content to OpenAI to generate summaries. | Elsevier says Embase AI does not allow information to be stored in the LLM or used for training purposes. |
| Support | Arc Search users can contact the team from the app settings or submit a support ticket through the help page. | Elsevier’s Embase resources page links to an Embase Support Center and an Embase AI use cases and prompt guide. |
Plans
In their own words
Arc Search
Arc Search is a free browser centered on Browse for Me, which searches multiple pages and produces an answer on a custom webpage. Its built-in blocker is described as stopping ads, trackers, pop-ups, and cookie banners. Other features include reader mode, incognito mode, website translation, and voice search. Inactive tabs are archived automatically, with help documentation listing intervals from 12 hours to 30 days. Browse for Me is the default search option; alternatives include Google, Bing, DuckDuckGo, Ecosia, Perplexity, and Kagi. Arc Sync can share desktop Spaces, pinned tabs, and Today tabs with Arc Search on iOS, but is unavailable on Android, and tabs created in Arc Search do not sync back to desktop. The maker says Browse for Me sends command-bar and search-result content to OpenAI to generate summaries. Arc Search supports iOS 16 or later and Android 10 or later. The maker also says Sync sidebar data uses end-to-end encryption, but the product is not currently SOC 2 or ISO 27001 certified and does not offer account MFA.
Embase AI
Embase AI is Elsevier’s natural-language search tool for biomedical literature. It searches Embase, which the product page says contains 47 million records, and summarizes findings from the 30 most relevant peer-reviewed articles. Users can filter by publication year, publication type and study type, or extend searches to preprints, conference abstracts, ClinicalTrials.gov studies, and articles in press or in process. Summaries link to relevant articles, with references ranked through term-based retrieval and then neural semantic ranking. Users can inspect the AI-generated Embase query, refine it by opening results in Embase, or copy the query text. Follow-up questions and session export support continued searching and record keeping. Elsevier says information is not stored in the LLM or used for training. It presents the product for biomedical research, including users in pharma, medtech, universities and libraries. Embase AI is paid, has a three-day trial, and lists no price; prospective customers can request a demo. It is available on Android, iOS, macOS, web and Windows.