Elicit's Research Agent

Elicit's Research Agent is a powerful way to tackle complex research questions that go beyond what academic literature alone can answer. Unlike a Elicit's Reports or Systematic Reviews which are intentionally limited to Elicit's academic, journal, and clinical trial corpus, the Research Agent can pull from a wide range of sources (e.g. publications, public filings, press releases), produce flexible outputs, and let you iterate until you have exactly what you need.

The Research Agent is the right choice when:

• Your question requires sources beyond academic publications — like regulatory filings, press releases, duct labels, etc.

• You need a custom output format, such as a comparison table, competitive landscape, or executive summary

• You want to explore a topic iteratively, following up and refining as you go — rather than running a single structured query

For questions that are well-served by academic or journal literature and a fixed report or systematic review structure, such as PRISMA, the Research Report or Systematic Review workflows are likely a better fit.

The Research Agent includes four templates:

The General template is available on all plans. Competitive, Research, and Clinical Trial templates are available on Elicit's paid plans.

Competitive landscapes — Map out and compare ducts, companies, or therapeutic apaches across the sources most relevant to your analysis.

Research landscapes — Understand the full scope of activity in a field: who's working on what, where the evidence is concentrated, and where the gaps are.

Clinical trial landscapes — Analyze trial designs, endpoints, and outcomes across multiple studies using ClinicalTrials.gov and related sources.

General — Investigate any research question without a predefined structure, using chat to dig deeper as you go.

1. Choose a template and describe your question

Select the research agent and choose a template on the homepage. Then enter your research question or research task in the text box.

You can also attach any relevant documents that you'd like the agent to consider in its answers.

If you'd like quick answers, go ahead and click the green arrow. If you'd like a more in-depth response, click the clock icon to enable extended thinking mode before clicking the green arrow to start the session. Extended thinking is a feature of Elicit's paid plans.

2. Answer clarifying questions

Before the agent begins, it may ask a few questions to make sure it understands your needs — which sources to prioritize, how the output should be structured, and the scope of your question. Taking a moment here leads to much better results.

3. Watch the agent work

The Research Agent breaks your mpt into a systematic plan, then executes it step by step. You can watch which sources it's consulting and how it's building toward your output in real time. You're also free to leave the page and come back later when it's finished. Fast mode should take less than a minute. If you've enabled extended thinking, it might take significantly longer depending on the complexity of your request.

4. Review your output

All claims in the output are grounded in evidence, with citations you can trace back to the source. Unlike other AI tools, the Research Agent doesn't simply search and summarize — it builds a structured gram from your question and executes it reliably. Click on cited sources to learn more about that source.

5. Iterate

This is where the Research Agent really shines. Once you have an initial output, you can:

• Ask follow-up questions about the results

• Request changes or additions to the existing output

• Kick off entirely new analyses based on what you've learned

• Ask the agent to generate different exportable artifacts about the results such as a report, tables, compare/contrasts of different sources, etc. Any artifacts the agent generates will be available in the Artifacts drop down menu.

A research agent session is a workspace for ongoing research, not a single query.

In addition to Elicit's corpus of 138M+ academic papers, the Research Agent can search:

• The broader web

• ClinicalTrials.gov and related clinical databases

• Regulatory documents (e.g., FDA and EMA filings)

• Press releases and company announcements

• duct labels

• Be specific in your prompt. The more context you give upfront — focus area, geography, timeframe, output format — the better the agent can tailor its work. Use declarative language--Give the agent tasks to perform or ask research questions, don't ask the agent for opinions or advice. Note that Elicit is intended to assist with research, data extraction, and analysis only at this time. It is not intended to assist with writing or editing your own content.

• Use the clarifying questions. Don't skip past them. These help the agent scope the task correctly before it spends time searching.

• Iterate freely. If the first output isn't quite right, just ask. The agent can refine, expand, or reframe without starting from scratch.

• Agent sessions do not count as workflows against your workflow limit.

• Agent sessions are subject to a daily limit based on the size, complexity, and frequency of your queries. However, the limit is quite high and most users on an appropriate plan level for their research goals will not encounter it. If you do see the daily limit frequently, consider upgrading to a higher level plan, which includes higher daily limits. Limits reset at 12AM UTC each day. Note: Use of Extended Thinking Mode will cause you to hit the limit more quickly.

The Research Agent will not provide support on how to use Elicit. It is designed only for research. For help using Elicit, please contact support at help@elicit.com.