Workflow · Production
Perplexity Pro Search uses a multi-step AI agent to answer complex queries at scale
The problem
Traditional search engines struggle with complex queries that require connecting information across multiple ideas or extracting detailed information, leaving users to sift through countless results without direct, organized answers.
Workflow diagram · grounded in source
1
User submits query
trigger
“When a user submits a query, the AI creates a plan”
2
AI creates step-by-step plan
ai_action
“the AI creates a plan— a step-by-step guide to answering it”
3
Search queries generated and executed
ai_action
“For each step in the plan, a list of search queries are generated and executed. These steps are executed sequentially, and results from previous steps are passed when executing steps after.”
4
Specialized tools invoked
integration
“Perplexity Pro Search also supports specialized tools such as code interpreters, which allow users to run calculations or analyze files on the fly, as well as mathematics evaluations tools like Wolfram Alpha”
5
Documents grouped and filtered
validation
“These search queries return a list of documents, which are grouped and then filtered down to the most relevant ones”
6
LLM generates final answer
ai_action
“The highly-ranked documents are then passed to an LLM to generate a final answer”
7
Interactive UI shows progress
output
“an interactive UI that shows the plan being executed step-by-step. The team iterated on expandable sections that allow the user to click on individual steps to see more details on a search. They also introduced the ability to hover over …”
Reported outcome
Query search volume for Perplexity Pro Search increased by over 50% in the past few months as more users discovered its ability to answer tricky questions quickly and efficiently.
Reported metrics
Pro Search query volume increaseover 50%
Reported stack
code interpretersWolfram Alpha
Frequently asked questions
What did this team achieve with this AI workflow?
Query search volume for Perplexity Pro Search increased by over 50% in the past few months as more users discovered its ability to answer tricky questions quickly and efficiently.
What tools did this team use?
code interpreters, Wolfram Alpha.
What results were reported?
Pro Search query volume increase: over 50% (source-reported, not independently verified).
How is this workflow AI workflow structured?
User submits query → AI creates step-by-step plan → Search queries generated and executed → Specialized tools invoked → Documents grouped and filtered → LLM generates final answer → Interactive UI shows progress.