Extract lead details during chatbot conversations

When a new lead is captured in chat via Cassidy, automatically run the conversation text through Perplexity to classify intent and extract key contact metadata.

Try:

See all Cassidy + Perplexity integrations or talk to a human

Trusted by teams already building on Knit·

4.9/5 on G2·

Google for Startups Accelerator

How Knit builds this workflow

The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.

Cassidy Explore Cassidy →

Triggers

New conversation started

Fires when a new chat or conversation begins in Cassidy.

Lead captured in chat

Fires when Cassidy captures a lead during a conversation.

Conversation handed off

Fires when Cassidy escalates a conversation to a human.

Actions

Send a message

Sends a message to a user through Cassidy.

Generate an answer

Asks Cassidy a question against its knowledge base and returns the answer.

Summarize a conversation

Uses Cassidy to summarize a chat transcript.

Create a ticket from a chat

Opens a support ticket from an Cassidy conversation.

Perplexity Explore Perplexity →

Triggers

New completion generated

Fires when Perplexity generates a response to a prompt.

Model run failed

Fires when a request to Perplexity errors or times out.

Fine-tune job completed

Fires when a fine-tuning job in Perplexity finishes.

Actions

Generate a completion

Sends a prompt to Perplexity and returns the model's response.

Summarize text

Uses Perplexity to summarize a block of text.

Classify or extract data

Uses Perplexity to classify or extract structured data from text.

Send custom completions back to chat visitors When a conversation starts in Cassidy, generate a completion in Perplexity and send a tailored message directly back to the visitor. See details

Alert support agents when model fine-tuning completes When a fine-tune job completes in Perplexity, automatically send a message through Cassidy to notify AI administrators that the updated model is ready. See details

See all Cassidy + Perplexity integrations → · Browse the full workflow library →

Enterprise-grade security

Visit our Security Center Review the DPA

FAQ

Common questions

Can Knit build “Extract lead details during chatbot conversations” between Cassidy and Perplexity?

Yes — describe it in the box above and Knit's Integrations Agent researches Cassidy and Perplexity's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.

How long does it take to build?

Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.

How does connecting Cassidy to Perplexity expand chatbot capabilities?

Connecting Cassidy to Perplexity allows your chatbot to tap into advanced AI models for deeper context, sentiment classification, and sophisticated text generation beyond standard scripted responses.

Can Cassidy notify operators if a backend model process encounters an issue in Perplexity?

Yes, when a model run fails in Perplexity, you can send an automated message or alert through Cassidy to notify system administrators.