Perplexity Deep Research
Conduct comprehensive AI-powered research with citations
Last updated
Was this helpful?
Conduct comprehensive AI-powered research with citations
Last updated
Was this helpful?
The "Perplexity Deep Research" step allows you to perform in-depth research on any topic using Perplexity's advanced AI research capabilities. This step conducts thorough analysis across multiple sources and provides detailed, cited responses that are helpful for content creation, market research, and competitive analysis.
Configuring the step requires setting the core message and optional advanced parameters:
The "Message" input field contains your research query or question - what you want to conduct deep research on. This should be a clear, specific question or topic you want thoroughly researched.
Examples:
"Compare the top 5 content management systems for enterprise businesses"
"Analyze the competitive landscape for project management software"
To dynamically set the research query referencing an input or output variable, use Liquid syntax: {{ query }} or {{ step_1.output }}
Control the length of the research output. Higher token limits allow for more comprehensive research and detailed analysis.
Specify the time period for information sources. The model will only search for information from the selected time period, ensuring you get the most current data available.
Options include:
Last year
Last month
Last week
Last hour
Limit research to specific domains by entering comma-separated domain names (e.g. techcrunch.com, wired.com, verge.com). This helps focus research on authoritative sources in your industry. This can include a maximum of 3 domains.
Exclude specific domains from research results by entering comma-separated domain names. Useful for filtering out competitors or unreliable sources. This can include a maximum of 3 domains.
View research outputs as they are generated in real-time, rather than waiting for the entire execution to finish. Helpful for monitoring progress on complex research queries.
Return relevant images found during research in the response. These images can be used to enhance content or provide visual context for your research findings.
Return a list of related questions that emerged during the research process. These can help identify additional content opportunities or research angles.
