AI-assisted search

...site currently in development...

Lib4RI holds institutional subscriptions to Consensus and scite.ai which we recommend as your starting point, since they give all affiliates of Eawag, Empa, PSI and WSL full access without a personal paid plan. General-purpose assistants such as ChatGPT and Claude are useful too, especially when connected to these academic engines.

Consensus and scite.ai

Consensus is an AI-based academic search engine that searches across a large corpus of peer-reviewed literature (drawing on Semantic Scholar) and synthesises what the papers actually report. You can ask a research question in plain language and it returns an evidence-based summary with the underlying references, including an indication of whether the literature broadly agrees or is divided on a point. It is particularly strong for getting a quick, sourced overview of a topic and for understanding the weight of evidence behind a claim.

scite.ai focuses on citations and how publications are received by the research community. For any given paper or claim it shows not just how often something is cited, but whether citing articles support, mention, or contrast it, and where in the citing article the reference appears. This «smart citation» view is valuable for assessing the reliability and standing of a finding. scite.ai also includes the «Scite Assistant», an AI research assistant that answers questions grounded in references, with the ability to specify both, the sources it draws on and the form of its output.

Quick lookup of individual items

When you simply need to find, verify or understand a single article, dataset or other item, both tools work well as a fast first port of call:

• Paste a claim, a sentence, or a question into Consensus to find the specific papers that address it and read a concise synthesis of their findings.
• Drop a title, DOI or claim into scite.ai to pull up a paper together with its smart-citation profile — a quick way to judge whether a result has held up, been contested or been superseded.
• Use the Scite Assistant or Consensus to get a plain-language explanation of an unfamiliar paper or concept before deciding whether it is worth reading in full.

This is the right mode for ad-hoc, low-stakes questions where you want an answer in seconds rather than an exhaustive, documented search.

Topic exploration and systematic search support

For broader work, such as scoping a new project, refining a research question, or preparing the evidence base for a review, these tools can support the early stages of a systematic search (see also our page on systematic literature search):

• Use Consensus to map a topic, identify the main lines of evidence and areas of disagreement, and gather an initial set of key references and terminology.
• Use scite.ai to follow citation networks outward from seminal papers, identify influential and contested work, and spot clusters of supporting or contrasting evidence.
• Use either tool to help extract the underlying concepts, synonyms, and related terms that you will then combine with Boolean operators and truncation into reproducible search strings for databases such as Scopus or Web of Science.

It is important to remember that a genuinely systematic search must be comprehensive, transparent, and protocolled for reproducibility. AI tools are an excellent aide for developing and sharpening the strategy, but the formal search itself should still be conducted and documented in the established databases.

Connecting ChatGPT and Claude to Consensus and scite.ai

General-purpose assistants such as ChatGPT and Claude are helpful for brainstorming, rephrasing search questions, and explaining results in plain language. On their own, however, they can produce plausible-sounding but non-existent references («hallucinations»), so they should not be trusted for factual literature retrieval without grounding.

Both Consensus and scite.ai can be connected to these assistants — for example through Consensus's GPT and connector integrations, or scite.ai's assistant integrations — so that the assistant's answers are grounded in real, retrievable papers rather than its training data alone. When used this way, you get the conversational convenience of ChatGPT or Claude with the evidential backing of our subscribed academic engines. Whenever you rely on a general assistant for literature work, always verify the references against a real database.

Best practice in prompting

A few simple habits can make a significant difference to the quality of AI-assisted search results:

• Be specific. State your topic, population or system, intervention or variable and outcome of interest rather than relying on a single broad keyword. A focused question is more likely to yield focused evidence.
• Use natural-language questions for Consensus and the Scite Assistant — they are designed for them — but keep Boolean search strings for the traditional databases.
• Ask for sources and check them. Request that the tool cite its references, then confirm the papers exist and say what the tool claims. Treat any uncritical claim as a lead to verify, not a conclusion.
• Iterate. Refine your prompt based on the first results — narrow the scope, add synonyms, exclude off-topic areas, or ask the tool to focus on a particular method, period or discipline.
• Mind the limits. Be aware of each tool's coverage and date range, and never rely on a general chatbot alone for factual retrieval.
• Use AI ethically. Keep your own judgement in the loop, respect academic integrity, and remember that the responsibility for what you cite remains yours.

Other AI-assisted search tools

Beyond our subscribed tools, many other AI-assisted discovery tools exist. We do not hold subscriptions to these and they are listed for orientation, not as recommendations; free and paid tiers vary, and the field changes quickly. More comprehensive lists of ai tools could e.g. be found at aitoolshunt.com or A Snapshot of GenAI Tools for Research.

• Connected Papers — visual tool that builds a graph of related papers from a seed reference; free and paid versions.
• Dimensions — research-information platform integrating publications, grants, patents, clinical trials, datasets, and policy documents. All publications and citations including contextual information, and a customized version of ChatGPT (at least a free account is required with OpenAI) are freely available for personal, non-commercial use.
• Elicit — academic search engine for literature review that finds relevant papers, extracts qualitative and quantitative data, and synthesises findings.
• Litmaps — discovery tool that visualises the interconnections among papers.
• OpenAlex — discovery tool that combines both, a Boolean search as well as a semantic AI-powered meaning search.
• Open Knowledge Maps — visual interface that produces a topical knowledge map from your query.
• Perplexity AI — conversational search engine that answers queries using web sources and references them.
• R Discovery — search tool with a natural-language research assistant.
• ResearchRabbit — citation-based discovery and visualisation of related literature and authors, with Zotero integration.
• SciFinder Newton — agentic AI-assistant for SciFinder-n, the discovery platform of the Chemical Abstracts Service (CAS).
• scinapse and Scinapse-style analysers — search engines that support content confirmation through paper analysis.
• Semantic Scholar — AI-powered research and discovery tool with semantic analysis (the data source behind several other tools).
• Scopus AI and Web of Science Research Assistant — generative-AI search layers over Scopus and Web of Science respectively; their trials have ended, but the underlying databases remain available to you via Lib4RI.

If you find a tool you value that is not listed, we would like to hear about it — please get in touch.