Elicit Research Agent
Elicit Research Agent is a standalone vertical AI agent from Elicit. A research agent that turns a question into a plan, searches papers, trials and regulatory documents, and returns a cited report. Nearfi's Agent Index rates its autonomy 4/5 (multi-step on its own): after clarifying questions it plans and runs a whole research programme on its own and hands back a cited report; it is not 5 because it runs only when asked, and is not 3 because the user does not approve each step. Status: beta; 0 incident(s) logged.
By Elicit · launched 2025-12-09 · last checked 2026-11-04
Why 4: after clarifying questions it plans and runs a whole research programme on its own and hands back a cited report; it is not 5 because it runs only when asked, and is not 3 because the user does not approve each step.
What it does. Elicit says its Research Agent breaks a prompt into a structured plan, asks clarifying questions, then runs it across papers and the wider web, including clinical-trial databases, regulatory documents and product labels. Output can be a comparison table or narrative summary. Pro and above add a systematic-review workflow that screens up to 5,000 papers.
Where it falls short. Elicit calls the workflows a beta and its claims of evidence-grounded output come from the company; the launch post gives no accuracy figures. Third-party reviewers disagree on its suitability for formal systematic reviews, so outputs need checking against the sources.
What it can do
Incidents
- None logged.
Closest fiction
Devs — A machine that reads the whole record to answer one question.
Related research agents
- ChatGPT deep research OpenAI · autonomy 4/5
- Gemini Deep Research Google · autonomy 4/5
- Perplexity Deep Research Perplexity · autonomy 4/5
History
- 2026-11-04 Added to the index.
Sources
- New in Elicit: Research Agents Elicit, 2025-12-09
- Elicit pricing Elicit
← All agents in the index · Autonomy is rated on what the product does today, on a 1–5 scale. Every fact links to a source.