Perplexity AI
Web-grounded conversational AI, search, embeddings, and agent APIs powered by Perplexity's Sonar models.
Three ways to use Perplexity AI
Chat with Geni
Ask Geni to pull data, take actions, or answer questions using this integration in a conversation.
Build a workflow
Create automated workflows that trigger on events, run on a schedule, or chain multiple tools together.
Power an app
Use this integration as a data source or action layer behind a dashboard, form, or internal tool.
Supported tools
Actions your AI agents can perform with Perplexity AI.
Create Async Chat Completion
Submit a long-running deep-research chat completion. Returns an ID to poll with Get Async Chat Completion.
Create Chat Completion
Generate a web-grounded chat completion using a Sonar model, with citations, optional structured output, and search filtering.
Create Contextualized Embeddings
Generate context-aware vector embeddings for chunks of a document, improving retrieval quality over independent per-chunk embeddings.
Create Embeddings
Generate vector embeddings for independent texts (queries, sentences, documents) using Perplexity's embedding models.
Execute Agent
Run a multi-step agent with built-in tools (web search, URL fetching, function calling), reasoning, and multi-model fallbacks.
Get Async Chat Completion
Retrieve the status and result of an async chat completion job by ID.
Get started automating Perplexity AI
Ready-to-use workflows
Prompts using Perplexity AI
Auto-diagnose new Linear bug reports with Perplexity research
When a bug is filed in Linear, an agent researches the error online and posts a first-pass diagnostic comment so engineers walk in with a head start.
Auto-research new HubSpot contacts with Perplexity
When a new contact lands in HubSpot, an agent pulls fresh company intel from Perplexity, writes it to the record with sources, and pings Slack for hot leads.
