:root {
  --Foreground-Fg: #251C1D;
  --Foreground-Fg-Dark: #F9F9FB;
  --Foreground-FgSecondary: rgba(37, 28, 29, 0.64);
  --Foreground-FgSecondary-Dark: rgba(249, 249, 251, 0.64);
  --Background-Bg: #2F2E32;
  --article-text: rgba(37, 28, 29, 0.8);;
  --dark-article-text: var(--Foreground-FgSecondary-Dark);
  --Brand-brandPrimary: #8056B0;
  --Background-BgSecondary: #FAF7F6;
  --Background-BgSecondary-Dark: #28272B;
  --Border-border: rgba(136, 99, 101, 0.24);
  --Border-border-Dark: rgba(249, 249, 251, 0.16);
  --Accent-accent4: #CAB0D9;
  --Accents-accent3: #D9BAFC;
  --Accent-accent4-Dark: #A998B8;
}

/* @font-face {
  font-family: MessinaSans;
  src: url(/fonts/MessinaSans_Normal_Upright_Variable_Web.woff2) format("woff2");
  font-weight: 100 900;
  font-style: normal;
  font-stretch: 75% 125%;
  font-variation-settings: "ital" 0;
}

@font-face {
  font-family: MessinaSans;
  src: url(/fonts/MessinaSans_Normal_Italic_Variable_Web.woff2) format("woff2");
  font-weight: 100 900;
  font-style: italic;
  font-stretch: 75% 125%;
  font-variation-settings: "ital" 1;
}
@font-face {
  font-family: Messina Sans Mono;
  font-style: normal;
  font-weight: 400;
  src: url(/fonts/Messina-Sans-Mono-Regular.woff) format("woff");
}
@font-face {
  font-family: Messina Sans Mono;
  font-style: normal;
  font-weight: 700;
  src: url(/fonts/Messina-Sans-Mono-Bold.woff) format("woff");
}
@font-face {
  font-family: Material Icons;
  font-style: normal;
  font-weight: 400;
  src: url(/fonts/MaterialIcons-Regular.eot);
  src: url(/fonts/MaterialIcons-Regular.woff2) format("woff2"),
       url(/fonts/MaterialIcons-Regular.woff) format("woff"),
       url(/fonts/MaterialIcons-Regular.ttf) format("truetype");
} */

h6, body, ul, ol, p {
  /* font-family: MessinaSans, Arial, Sans Serif; */
  /* font-size: 14px; */
}

html {
  font-size: 16px;
  /* font-weight: 500; */

}
html *, html :after, html :before {
  border-color: var(--Border-border); 
}
.dark *,
.dark :after,
.dark :before {
  /* border-color: var(--Border-border-Dark);  */
}

.dark\:border-gray-800\/50:is(.dark *) {
  border-color: var(--Border-border-Dark); 
}
.prose {
  color: var(--article-text)
}
.dark .prose {
  /* color: var(--dark-article-text) */
}
.prose:is(.dark *) {
  color: var(--dark-article-text)
}
.prose p:not(.not-prose *) {
  margin-bottom: 16px;
  /* font-weight: 500; */
}


#content-area :where(h1, h2, h3, h4, h5) {
  font-family: MessinaSans, Helvetica, Arial, sans-serif;
}
#content-area h1 {
  font-size: 28px;
}

/* code, pre, .code, .font-mono {
  font-family: "Messina Sans Mono", monospace;
  font-size: .85rem;
} */
a[href^="https://mintlify.com"] {
  display: none;
}
/* Card */
#content-area .card p {
  font-size: 14px;
}
#content-area .prose :where(h2, h3, h4, h5):note(.card *) {
  margin-top: 24px;
}
#content-area .card svg:min-width(200px){
  margin-bottom: .5rem;
}

#content-area .card:has(div>div > h2:empty):has(div>div p) div:has(svg) {
  margin-bottom: 1.25rem; 
}

.dark #content-area .card:has(div>div > h2:empty) div:has(svg) svg path {
  fill: #ac6df3 !important;
}
.dark #content-area .card:has(div>div > h2:empty) div:has(svg) svg g[clip-path="url(#clip0_396_970)"] g {
  mask: unset !important;
}

/* page layout */
@media (min-width: 1220px) {
  #table-of-contents.xl\:flex {
      display: flex;
  }
  #table-of-contents.xl\:hidden {
    display: none;
  }
}

@media (min-width: 1024px) {

  #content-area.lg\:pl-\[23\.7rem\] {
    padding-left: 22rem;
  }

  #navbar .lg\:px-12 {
    padding-left: 2rem;
  }
}
#navbar .px-12 {
  padding-left: 2rem;
}
#table-of-contents.pl-10 {
  padding-left: 1rem;
}

#table-of-contents.w-\[19rem\] {
  width: 14rem;
}

#table-of-contents .w-\[16\.5rem\] {
  width: 14rem;
}
#content-container .gap-12 {
  gap: 1rem;
}

.max-w-8xl {
  max-width: 86rem;
}

/* Remove gap top of content */
#content-area> div.relative {
  margin-top: 1rem;
}

#content-area >header >div.prose {
  margin-top: unset;
  
}

#content-area >header >div.prose p {
  font-size: 18px;
  color: rgb(var(--gray-900));
}
.dark #content-area >header >div.prose p {
  font-size: 18px;
  color: rgb(var(--gray-200));
}

/* sidebar color */
.bg-gray-950\/\[0\.03\] {
  background-color: unset;
}

.dark .bg-gray-950\/\[0\.03\] {
  background-color: unset;
}

/* Border */
#navbar-transition,
table,
#content-area >div.prose >div>div.not-prose .border {
  border-color: var(--Border-border);
}

.dark #navbar-transition,
.dark table,
.dark #content-area >div.prose >div>div.not-prose .border {
  border-color: var(--Border-border-Dark);
}

/* Links */

.prose a {

}

/* Code */

.prose a:has(>code) {
  /* border-bottom-width: 0px; */
  /* color: var(--Brand-brandPrimary)  */
}

.prose a:has(>code):hover {
  /* border-bottom-width: 2px; */
}

.prose a[href^="/apis"]:after {
  content: "API";
  font-size: .65rem;
  font-weight: 400;
  padding-left: 3px;
  padding-right: 3px;
  padding-top: 1px;
  padding-bottom: 1px;
  margin-left: 3px;
  color: var(--Background-BgSecondary);
  background-color: var(--Brand-brandPrimary);
  /* border: 1px solid var(--Border-border); */
  border-radius: 3px;
  vertical-align: middle;
}

.dark .prose a[href^="/apis"]:after {
  /* background-color: var(--Background-Bg-Dark); */
  /* color: var(--Foreground-Fg-Dark); */
}
  

.prose :not(pre)>code {
  background-color: unset;
  border-color: var(--Accent-accent4);
  line-height: 18px;
  /* font-weight: 500; */
  /* font-size: .95rem; */
}

.prose strong:not(pre)>code {
  font-weight: 700;
}
.dark .prose :not(pre)>code {
  border-color: var(--Accent-accent4-Dark);
}
:not(pre)>code:is(.dark *) {
  --tw-brightness: unset;
}
.prose :has(> code){
  white-space: pre-wrap;
}

code .token.string {
  color: var(--Accents-accent3)
}
/* Navbar */
#sidebar a[href="/"] {
  position: relative;
  display: inline-flex;
  align-items: center;
}

#sidebar a[href="/"]:after {
  content: "Docs";
  position: static;
  margin-left: 0.5em;
  font-size: 18px;
}

#navbar a {
  font-size: 14px;
  font-weight: 600;
  color: var(--Foreground-FgSecondary);
}

.dark #navbar a {
  color: var(--dark-article-text);
}

#navbar > div > div > div.hidden a:not([class*="group-hover"]) {
  color: var(--Foreground-Fg)
}
.dark #navbar > div > div > div.hidden a:not([class*=group-hover]) {
  color: var(--Foreground-Fg-Dark)
}
#navbar > div > div > div.hidden a:not([class*="group-hover"]) >div {
  height: 3px;
}
/*Table of contents */

#table-of-contents a {
  /* font-size: 14px; */
  /* font-weight: 600; */
  /* color: var(--Foreground-Fg) */
}

#table-of-contents svg {
  /* display: none; */
}
#table-of-contents ul >li:not([style*="margin-left"]) a  {
  /* font-weight: 500; */
}
#table-of-contents ul >li[style*="margin-left"]  a {
  /* font-weight: 500; */
}
#table-of-contents>div>div>span {
  /* margin-left: 5px; */
  /* text-transform: uppercase; */
  /* font-size: 16px;  */
  /* font-weight: 700; */
  /* color: var(--Foreground-FgSecondary); */
}

.dark #table-of-contents>div>div>span {
  color: var(--dark-article-text)
}
/* Tables */

#content-area .prose :where(table ){
  border-width: 1px;
  border-radius: 4px;
}

#content-area .prose :where(thead th:first-child, tbody tr td:first-child) {
  padding-left: 12px;
}

#content-area prose :where(thead th:last-child, tbody tr td:last-child){
  padding-right: 12px;
}
#content-area .prose :where(thead th) {
  padding-top: 12px;
  width: 1%; /* this somehow fixes table width issues when coloring the header */
}

#content-area .prose :where(ul) {
  margin-top: 0px;
  /* margin-bottom: 0px; */
}

#content-area .prose :where(thead) {
  background-color: var(--Background-BgSecondary);
}

.dark #content-area .prose :where(thead) {
  background-color: var(--Background-BgSecondary-Dark);
}

#content-area .prose table td{
  font-size: 1rem;
}

/* unordered lists */
#content-area  .prose :where(ul:not(.not-prose) > li):before{
  background-color: unset;
  content: "▪";
  top: unset;
  font-size: 16px;
  padding-left: 8px;
  padding-right: 8px;
}

/* ordered lists */
#content-area  .prose :where(ol) {
  list-style-type: none;
  counter-reset: item;
  padding-left: 0;
}

#content-area .prose :where(ol > li) {
  counter-increment: item;
  position: relative;
  padding-left: 28px; /* Adjust based on your counter size and desired spacing */
  margin-bottom: 10px;
}

#content-area .prose :where(ol > li)::before {
  content: counter(item);
  position: absolute;
  left: 0;
  top: 5px;
  background: var(--Brand-brandPrimary);
  border-radius: 4px;
  color: white;
  width: 18px;
  height: 18px;
  display: flex;
  align-items: center;
  justify-content: center;
  font-size: 12px;
  line-height: 1;
  font-weight: 700;
}



.dark #content-area  .prose :where(ol >li)::before {
  /* color: var(--Background-Bg) */
}

/* .prose :where(ol > li) > * {
  margin-top: 0;
  margin-bottom: 0;
} */

/* Hide the automatically generated marker */
#content-area  .prose :where(ol > li)::marker {
  display: none !important;
}

/* Accordian in dark mode */
.dark #content-area  div[role=listitem] {
  background-color: unset;
}
#content-area  div[role=listitem] button p{
  font-weight: 700;
}
/* Navigation sidebar */

.dark #navigation-items * {
  color: var(--Foreground-Fg-Dark)
}

#navigation-items a * {
  /* font-weight: 500; */
}

#navigation-items h5 {
  font-weight: 700;
  font-size: 14px;
}

/* Tabs */
#content-area .prose ul>li>button{
  font-size: 1rem;
  font-weight: 700;
}


/* API Ref */

.border-gray-100 {
  border-color: var(--Border-border)
}
.py-6 {
  padding-top: 1rem;
  padding-bottom: 1rem;
}
.mt-4 {
  margin-top: .5rem;
}
.py-6 >.font-mono .text-primary {
  font-size: .95rem;
}
.mt-4 .prose:last-child p:last-child{
  margin-bottom: 0;
}
.prose-sm {
  font-size: .9rem;
}

.group.flex.font-mono {
  /* flex-wrap: wrap; */
  gap: 0rem;
}

/* API ref puts description as the page description which we want to appear as normal content */
main:has(#navbar > div > div > div.hidden a[href^="/apis"]:not([class*="group-hover"])) {
  & #content-area >header >div.prose {
    margin-top: 1rem;
  }
  & #content-area >header >div.prose.text-lg {
    font-size: 1rem;
  }
  & #content-area >header >div.prose p {
    font-size: 1rem;
  }
}

/* Header anchor */
#content-area :where(h1, h2, h3, h4, h5) .absolute > a {
  margin-left: -1.75rem;
}

/* List of steps */
.dark\:text-gray-200:is(.dark *) {
  color: rgb(var(--gray-200));
}

ASAPP Docs

Documentation

API Reference

Book a Demo

Support

AI Console

Get suggestions for the next agent message in the conversation. 

There are several times when this should be called:
- when an agent joins the conversation,
- after a message is sent by either the customer or the agent,
- and as the agent is typing in the composer (to enable completing the agent's in-progress message).

Optionally, add a message to the conversation.


Generate suggestions

Recommended message for the agent to autopilot send.

Delay before the message is sent to the customer, during which a preview of the message is shown to the agent and they can choose to cancel it

Text of the message with placeholders for metadata instead of the values filled in

Delay before showing the preview and starting the countdown to send the message

Represents a single message within a conversation.

Hello, I would like to upgrade my internet plan to GOLD.

Information about the participant who sent the message.

The time when the message was sent. Include the timezone, otherwise UTC will be assumed.

Represents a participant in the conversation.

The unique identifier for the participant in your external system. This should be consistent across all interactions for the same individual.

The role of the participant in the conversation.

A participant role, usually the customer or an agent for human participants. System participant is also allowed but keep in mind
that this role won't be considered a participant in a conversation, just a message sender.


Completion of the phrase the agent is currently typing, to be displayed inline in the composer

Phrase completion text for the agent (this may be empty if the model does not have a confident prediction for how to complete the message)

Suggestion text with placeholders for metadata instead of the values filled in

A suggestions request with an optional message to add to the conversation

API ID & API Secret

Home

Welcome to ASAPP

Getting Started

Setup ASAPP

Manage Users

Learn how to view, search, and export audit logs to track changes in AI Console.

Audit Logs

Learn how to get started using ASAPPs APIs

Developer Quickstart

Learn how ASAPP returns Errors in the API

Error Handling

Learn about API rate limits recommended retry logic.

Rate Limits

API Rate Limits and Retry Logic

Use GenerativeAgent to resolve customer issues safely and accurately with AI-powered conversations.

Overview

GenerativeAgent

Discover how GenerativeAgent functions to resolve customer issues.

How It Works

How GenerativeAgent Works

Human in the Loop

Go Live

Use Messaging Platform to connect your brand to customers via messaging channels.

Messaging Platform

Use AutoSummary to extract insights and data from your conversations

AutoSummary

Learn how to get started with AutoSummary

See examples on how AutoSummary can be used

Example Use Cases

Learn how to extract insights and summarizations in batch with AutoSummary

Batch

Generate Insights in Batch

Learn how to use the AutoSummary Salesforce plugin.

Salesforce plugin

Deploying AutoSummary for Salesforce

Learn how to self-host AutoSummary & AutoTranscribe

Self-hosted

AutoTranscribe & AutoSummary Self-Hosted

Transcribe your audio with best in class accuracy

AutoTranscribe

Integrate AutoTranscribe into your SIPREC system using ASAPP Media Gateway

SIPREC Connector

Deploy AutoTranscribe into SIPREC via Media Gateway

Twillio Connector

Deploying AutoTranscribe for Twilio

Use AutoTranscribe in your Amazon Connect solution

Amazon Connector

Deploying AutoTranscribe for Amazon Connect

Use AutoTranscribe in your Genesys Audiohook application

Genesys AudioHook Connector

Deploying AutoTranscribe for Genesys AudioHook

Use a websocket URL to send audio media to AutoTranscribe

Direct Websocket

AutoTranscribe via Direct Websocket

Learn more about the use of AutoTranscribe and its features

Product Guide

AutoTranscribe Product Guide

AutoCompose

AutoCompose API

Deploying AutoCompose API

Use AutoCompose on your LivePerson application.

LivePerson Connector

Deploying AutoCompose for LivePerson

Use AutoCompose on Salesforce Lightning Experience.

Salesforce Connector

Deploying AutoCompose for Salesforce

Learn how to use the AutoCompose tooling UI

Tooling Guide

AutoCompose Tooling Guide

Learn more about the features and insights of AutoCompose

AutoCompose Product Guide

Reporting and Insights

Learn how to use File Exporter to retrieve data from ASAPP.

File Exporter

Retrieving Data via S3

Learn how to send metadata via Metadata Ingestion API.

Metadata Ingestion API

Security

Use External IP Blocking to block IP addresses from accessing your data.

External IP Blocking

Learn how to securely handle Customer Information.

Warning about CustomerInfo and Sensitive Data

Retrieves a list of conversation resources that match the specified criteria.

You must provide at least one search criterion in the query parameters.


List conversations

Creates a new conversation or updates an existing one based on the provided `externalId`.

Use this endpoint when:
- Starting a new conversation
- Updating conversation details (e.g., reassigning to a different agent)

If the `externalId` is not found, a new conversation will be created. Otherwise, the existing conversation will be updated.


Create or update a conversation

Retrieves the details of a specific conversation using its `conversationId`.

This endpoint returns detailed information about the conversation, including participants and metadata.


Retrieve a conversation

Lists all messages within a conversation.

This messages are returned in chronological order. 


List messages

Creates a message object, adding it to an existing conversation.

Use this endpoint to record each new message in the conversation.


Create a message

Retrieve the details of a message from a conversation.


Retrieve a message

This creates multiple message objects at once, adding them to an existing conversation.

Use this endpoint when you need to add several messages at once, such as when importing historical conversation data.


Create multiple messages

List messages with an externalId

Stores customer-specific authentication credentials for use in integrated flows.

- Can be called at any point during a conversation
- Commonly used at the start of a conversation or after mid-conversation authentication
- May trigger additional actions, such as GenerativeAgent API signals to customer webhooks

<Note>This API only accepts the customer-specific auth credentials; the customer is responsible for handling 
the specific authentication mechanism.</Note>


Authenticate a user in a conversation

Call this API to trigger GenerativeAgent to analyze and respond to a conversation.

This API should be called after a customer sends a message while not speaking with a live agent. The Bot replies will not be returned on this request; they will be delivered asynchronously via the webhook callback.

This API also adds an optional **message** field to create a message for a given conversation before triggering the bot replies. The message object is the exact same message used in the conversations API /message endpoint


Analyze conversation

This API creates a generative agent event streaming URL to start a streaming connection (SSE).

This API should be called when the client boots-up to request a streaming_url, before it calls endpoints whose responses are delivered asynchronously (and most likely before calling any other endpoint).

Provide the streamId to reconnect to a previous stream.


Create stream URL

This API provides the current state of the generative agent for a given conversation.


Get GenerativeAgent state

Retrieves the primary intent of a conversation, represented by both an intent code and a human-readable intent name. If no intent is detected, "NO_INTENT" is returned.

This endpoint requires:
1. Intent support to be explicitly enabled for your account.
2. A valid conversationId, which is an ASAPP-generated identifier created when using the ASAPP /conversations endpoint.

Use this endpoint to gain insights into the main purpose or topic of a conversation.


Get conversation intent

Generates a concise, human-readable summary of a conversation.

Provide an agentExternalId if you want to get the summary for a single agent's involvment with a conversation.


Get free text summary

Create a feedback event with the full and updated summary. Each event is associated with a specific summary id. 

The event must contain the final summary, in the form of text.


Provide feedback.

Generates a concise, human-readable summary of a conversation.

Provide an agentExternalId if you want to get the summary for a single agent's involvment with a conversation.

You can use the id from ASAPP's system (conversationId or IssueId) or your own id (externalConversationId).


Create free text summary

Creates and returns set of structured data about a conversation that is already known to ASAPP.

You can use the id from ASAPP's system (conversationId or IssueId) or your own id (externalConversationId).

Provide an agentExternalId if you want to get the structured data for a single agent's involvment with a conversation.


Create structured data

Get [websocket streaming URL](/autotranscribe/deploying-autotranscribe-via-websocket) to transcribe audio in real time. This websocket is used to send audio to ASAPP's transcription service and receive transcription results.


Get streaming URL

Get an evaluation of a text to verify if it contains profanity, obscenity or other unwanted words. This service should be called before sending a message to prevent the agent from sending profanities in the chat.


Evaluate profanity

Get spelling correction for a message as it is being typed, if there is a misspelling. Only the current word
will be corrected, once it's fully typed (so it is recommended to call this endpoint after space characters).


Check for spelling mistakes

Create a MessageSent analytics event describing the agent's usage of AutoCompose augmentation features
while composing a message


Create a MessageSent analytics event

To improve the performance of ASAPP suggestions, provide information about the actions performed by the agent while composing a message by creating `message-analytic-events`.

These analytic events indicate which AutoCompose functionality was used or not. This information along with the conversation itself is used to optimize our models, resulting in better results for the agents.

We track the following types of message analytic events:
- suggestion-1-inserted: The agent selected the first of the `suggestions` from a `Suggestion` API response.
- suggestion-2-inserted: The agent selected the second of the `suggestions` from a `Suggestion` API response.
- suggestion-3-inserted: The agent selected the third of the `suggestions` from a `Suggestion` API response.
- phrase-completion-accepted: The agent selected the `phraseCompletion` from a `Suggestion` API response.
- spellcheck-applied: A correction provided in a `SpellcheckCorrection` API response was applied automatically.
- spellcheck-undone: A correction provided in a `SpellcheckCorrection` API response was undone by clicking the undo button.
- custom-response-drawer-inserted: The agent inserted one of their custom responses from the custom response drawer.
- custom-panel-inserted: The agent inserted a response from their custom response list in the custom response panel.
- global-panel-inserted: The agent inserted a response from the global response list in the global response panel.

Some of the event types have a corresponding event object to provide details.

Create a message analytic event

Get settings for AutoCompose clients, such as whether any features should not be used.
It may be desirable to disable some features in high-latency scenarios.


Get settings for AutoCompose clients

Get autopilot greetings

Update autopilot greetings

Get autopilot greetings status for an agent

Get autopilot greetings status

Update autopilot greetings status for an agent

Update autopilot greetings status

List feeds

List feed versions

Lists feed formats for a company feed/version/


List feed formats

Lists dates for a company feed/version/format


List feed dates

Lists intervals for a company feed/version/format/date


List feed intervals

Lists files for a company feed/version/format/date/interval


List feed files

Retrieves a feed file URL for a company feed/version/format/date/interval/file


Retrieve a feed file

Add an agent metadata

Add multiple agent metadata items; submit items in a batch in one request


Add multiple agent metadata

Add metadata attributes of one issue/conversation


Add a conversation metadata

Add multiple issue/conversation metadata items; submit items in a batch in one request


Add multiple conversation metadata

Add a customer metadata

Add multiple customer metadata items; submit items in a batch in one request


Add multiple customer metadata

The API Health check endpoint enables you to check the operational status of our API platform.


ASAPP APIs

Generate suggestions

Authorizations

Path Parameters

Body

Response