Leina 
Wanta 
Inspect web search results
Retrieve ranked raw results without model synthesis.
/oo Perplexity: Search Perplexity for [query] and summarize the returned sources, titles, and URLs while noting unanswered questions.
Connect Perplexity to Your AI Agent
Ask your AI assistant to work with Perplexity: research Web Results and Generate Search-Grounded Answers.
4 tools API key
Try a Perplexity Task
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
oo Skill Perplexity
Generate a grounded response
Call a Sonar model with explicit messages and search settings.
/oo Perplexity: Use Perplexity model [model ID] with web search enabled to answer [question], then preserve citations returned with the answer.
Start Working with Perplexity
-
Install OOMOL
Set up oo CLI and the oo Skill in your agent.
Install OOMOL → -
Connect Perplexity
Connect using your Perplexity API Key.
Connect Perplexity → -
Give Your Agent a Task
Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →
Choose Your Agent
- An account with access to the Perplexity resources used in your task.
Perplexity Tools
Perplexity exposes raw web search and Sonar model responses as separate operations for your AI assistant.
Inspect web search results
Retrieve ranked raw results without model synthesis.
Generate a grounded response
Call a Sonar model with explicit messages and search settings.
4 tools
List Models
List the models currently available from Perplexity.
perplexity.list_models Search
Search the web and return ranked raw results from Perplexity without LLM synthesis.
perplexity.search Create Chat Completion
Create a Perplexity Sonar chat completion grounded by web search when enabled.
perplexity.create_chat_completion Create Embeddings
Generate vector embeddings for one or more input strings with Perplexity.
perplexity.create_embeddings No matching tools.
Frequently Asked Questions
Does search already generate an answer?
search returns ranked raw results without LLM synthesis; create_chat_completion is the response-generation action.
Can I query available models?
list_models returns the currently available Perplexity models.
Are embeddings a web search?
create_embeddings turns input strings into vectors and is separate from search.