# Perplexity

Add Perplexity to Bolna voice agents so they can pull real-time facts during live calls. Perfect for FAQ bots and info-heavy customer conversations.

At a glance

## How Perplexity fits in the stack

**Best for**

Reasoning, policy handling, tool use, and response generation.

**Use this layer when**

You want to tune quality, cost, latency, or function-calling behavior.

**Connects to**

Transcribed caller input upstream and voice or actions downstream.

## The LLM is the reasoning layer

### The LLM is the reasoning layer

This provider decides how the agent interprets intent, selects next actions, calls tools, and formulates responses. It is the decision engine inside the voice stack.

Telephony Phone Network

→

STT Listener

→

LLM Reasoning

→

TTS Voice

→

Tools Actions

This page focuses on where Perplexity fits in a production voice stack. For full setup steps, credentials, and API details, use the documentation link.

# Overview

Perplexity combines large language models with realtime web search to deliver fact-based, up-to-date responses. With Bolna's Perplexity integration, you can build voice agents that access current information, verify facts, and provide answers grounded in recent web sources.

Perplexity is ideal for scenarios where voice agents need to provide current information about products, services, news, policies, or any domain where information changes frequently and accuracy is critical.

## Features & Use Cases

**Real Time Web Search**

Perplexity searches the web in real-time to provide current, fact-based answers - crucial for information that changes frequently.

**Source Attribution**

Responses include source citations, allowing verification of information and building caller trust.

**Reduced Hallucination**

By grounding responses in actual web sources, Perplexity reduces AI hallucination compared to pure language models.

**Current Information**

Access up-to-date information about products, policies, news, and events without manually updating knowledge bases.

**Factual Accuracy**

Optimised for factual queries where accuracy is more important than creative or conversational responses.

**Use Case: Product Information Hotline**

Build agents that provide current product specifications, availability, and pricing by searching your website and catalog in real-time.

**Use Case: Policy & Compliance Queries**

Handle questions about policies, regulations, or procedures by searching current documentation and official sources.

**Use Case: News & Events Information**

Deploy agents that can answer questions about recent news, events, or announcements by accessing current web information.