> ## Documentation Index
> Fetch the complete documentation index at: https://dialnexa.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Perplexity AI

> Connect DialNexa calls to Perplexity AI for ticket, conversation, customer issue, SLA risk, product feedback item, or support escalation workflows.

Perplexity AI provides conversational AI models for generating human-like text responses.

<Note>
  Use Perplexity AI with DialNexa when a caller needs help, escalation, callback, product triage, or a status update that support teams must own.
</Note>

## Where Perplexity AI fits in a DialNexa workflow

Perplexity AI should receive DialNexa output when the conversation affects a ticket, conversation, customer issue, SLA risk, product feedback item, or support escalation. The handoff should explain what the caller asked for, what DialNexa learned, which record or object is affected, and who owns the next step.

<CardGroup cols={2}>
  <Card title="Escalate VIP or angry callers" icon="check-circle">
    Flag sentiment, account value, SLA risk, repeat contact, and cancellation language.
  </Card>

  <Card title="Capture product feedback" icon="check-circle">
    Separate bugs, feature requests, usability confusion, and missing documentation.
  </Card>

  <Card title="Close the loop" icon="check-circle">
    Trigger callbacks, status updates, or support replies with the exact promise made during the call.
  </Card>

  <Card title="Avoid repeat questions" icon="check-circle">
    Send the questions DialNexa already asked so agents do not restart discovery.
  </Card>
</CardGroup>

## What DialNexa should capture for Perplexity AI

* Customer name, account, email, phone, plan, support ID, ticket ID, and owner
* Issue summary, product area, urgency, sentiment, SLA risk, and expected resolution
* Tags such as bug, refund, cancellation risk, VIP, repeat contact, angry customer, or callback needed
* Transcript link, recording link, DialNexa call ID, CRM link, order link, and conversation link
* Duplicate ticket check, escalation owner, due date, and customer-visible next step

## High-value Perplexity AI workflows

<AccordionGroup>
  <Accordion title="Repeated issue should become product feedback">
    DialNexa should write the symptom, expected behavior, actual behavior, affected area, business impact, and evidence links into Perplexity AI. A teammate should be able to triage the issue without replaying the call.
  </Accordion>

  <Accordion title="Angry caller needs manager review">
    For this scenario, DialNexa should treat Perplexity AI as an escalation destination. Send the impact, urgency, affected customer or object, owner, and transcript link so the right team can act before the issue gets colder.
  </Accordion>

  <Accordion title="Customer calls about an unresolved ticket">
    For this workflow, DialNexa should send Perplexity AI a concise, action-ready handoff: matched caller, affected record, reason for the update, urgency, owner, next step, and links to call evidence.
  </Accordion>

  <Accordion title="VIP caller needs urgent escalation">
    For this scenario, DialNexa should treat Perplexity AI as an escalation destination. Send the impact, urgency, affected customer or object, owner, and transcript link so the right team can act before the issue gets colder.
  </Accordion>

  <Accordion title="DialNexa detects cancellation language">
    For this workflow, DialNexa should send Perplexity AI a concise, action-ready handoff: matched caller, affected record, reason for the update, urgency, owner, next step, and links to call evidence.
  </Accordion>

  <Accordion title="Caller reports a product bug">
    DialNexa should write the symptom, expected behavior, actual behavior, affected area, business impact, and evidence links into Perplexity AI. A teammate should be able to triage the issue without replaying the call.
  </Accordion>

  <Accordion title="Support needs a callback task after no answer">
    DialNexa should capture the preferred time, timezone, owner, promise made, and contact channel before updating Perplexity AI. The receiving team should see exactly why the follow-up exists and what the caller expects next.
  </Accordion>

  <Accordion title="Use create chat completion">
    Use create chat completion only when DialNexa has a matched caller, a clear destination object, and enough call context to justify opening a new support record. If the caller is unclear, route to review instead of creating noise.
  </Accordion>

  <Accordion title="Use get async chat completion">
    Use get async chat completion before answering, routing, or creating follow-up. DialNexa should verify the lookup result against the caller and send low-confidence matches to a human queue.
  </Accordion>
</AccordionGroup>

## Workflows that pair Perplexity AI with other integrations

* [Perplexity AI](/integrations/perplexityai) + [Stripe](/integrations/stripe): Stripe for billing or refund context.
* [Perplexity AI](/integrations/perplexityai) + [Shopify](/integrations/shopify): Shopify for ecommerce order context.
* [Perplexity AI](/integrations/perplexityai) + [Intercom](/integrations/intercom): Intercom for conversation history.
* [Perplexity AI](/integrations/perplexityai) + [Google Sheets](/integrations/googlesheets): Google Sheets for reviewing unresolved callbacks.
* [Perplexity AI](/integrations/perplexityai) + [Gmail](/integrations/gmail): Gmail for customer-facing follow-up.
* [Perplexity AI](/integrations/perplexityai) + [HubSpot](/integrations/hubspot): HubSpot for account value and renewal context.
* [Perplexity AI](/integrations/perplexityai) + [Slack](/integrations/slack): Slack for urgent support escalation.
* [Perplexity AI](/integrations/perplexityai) + [Jira](/integrations/jira): Jira for product bugs from calls.

## Implementation notes

* Use the DialNexa call ID as the idempotency key before running Perplexity AI actions.
* Write a short operational summary into Perplexity AI and link to the full transcript or recording for audit.
* Map required fields before launch: destination object, owner, status, urgency, next step, and record URL.
* Create review paths for low-confidence matches, sensitive requests, high-value customers, and actions that change money, access, legal terms, or customer commitments.

## FAQs

<AccordionGroup>
  <Accordion title="Should every support call create a ticket?">
    No. Create or update a ticket when the caller needs follow-up, SLA tracking, evidence, escalation, or customer-visible ownership.
  </Accordion>

  <Accordion title="What makes a support handoff useful?">
    Issue, affected product, customer expectation, what DialNexa already checked, urgency, owner, next step, and transcript link.
  </Accordion>

  <Accordion title="When should a call become a product bug?">
    When the caller provides reproducible behavior, expected result, actual result, affected product area, and business impact.
  </Accordion>

  <Accordion title="How should angry customers be routed?">
    Tag sentiment, repeat contact, account value, cancellation language, and SLA risk, then notify the escalation owner.
  </Accordion>

  <Accordion title="How do callbacks get tracked?">
    Create a callback task with phone number, preferred time, timezone, owner, attempt count, and the reason for the callback.
  </Accordion>

  <Accordion title="How are duplicate tickets avoided?">
    Search open tickets and recent conversations by customer, phone, email, and issue category before creating anything new.
  </Accordion>
</AccordionGroup>