はじめに
対話型AIプラットフォーム
チャットボットの概要
自然言語処理(NLP)
ボットの概念と用語
クイックスタートガイド
プラットフォームへのアクセス
ボットビルダーの操作
リリースノート
最新バージョン(英語)
以前のバージョン(英語)
廃止機能(英語)
コンセプト
設計
ストーリーボード
ダイアログタスク
ダイアログタスクとは
ダイアログビルダー
ノードタイプ
インテントノード
ダイアログノード
エンティティノード
フォームノード
確認ノード
ロジックノード
ボットアクションノード
サービスノード
Webhookノード
スクリプトノード
グループノード
エージェント転送ノード
ユーザープロンプト
音声通話プロパティ
イベント ハンドラー
ナレッジグラフ
ナレッジグラフの抽出
ナレッジグラフの構築
ボットにナレッジグラフを追加
グラフの作成
ナレッジグラフの構築
既存のソースからFAQを構築
特性、同義語、停止用語
変数ネームスペースの管理
更新
ノード間の質問と回答の移動
用語の編集と削除
質問と応答の編集
ナレッジグラフの分析
通知タスク
スモールトーク
デジタルスキル
デジタルフォーム
デジタルビュー
デジタルビューとは
パネル
ウィジェット
トレーニング
トレーニングとは
機械学習
機械学習とは
モデル検証
ファンダメンタルミーニング
ナレッジグラフ
示唆
ランキングおよび解決
NLPの詳細設定
NLPのガイドライン
インテリジェンス
インテリジェンスとは
コンテキスト
コンテキストインテント
割り込み
複数インテントの検出
エンティティの変更
デフォルトの会話
センチメント管理
トーン分析
テストとデバッグ
ボットと会話
発話テスト
バッチテスト
会話テスト
デプロイ
チャネル
公開
分析
ボットの分析
NLPメトリクス
会話フロー
Usage Metrics
封じ込め測定
カスタムダッシュボード
カスタムダッシュボードとは
メタタグ
カスタムダッシュボードとウィジェット
ユニバーサルボット
ユニバーサルボットとは
ユニバーサルボットの定義
ユニバーサルボットの作成
ユニバーサルボットのトレーニング
ユニバーサルボットのカスタマイズ
他言語の有効化
ストア
プラントと使用
Overview
Usage Plans
Support Plans
Invoices
管理
ボット認証
複数言語対応ボット
個人を特定できる情報の編集
ボット変数の使用
IVRのシステム連携
一般設定
ボット管理
ハウツー
会話スキルの設計
バンキングボットを作成
バンキングボット – 資金の振り替え
バンキングボット – 残高を更新
ナレッジグラフを構築
スマートアラートの予約方法
デジタルスキルの設計
デジタルフォームの設定方法
デジタルビューの設定方法
データテーブルのデータの追加方法
データテーブルのデータの更新方法
Add Data from Digital Forms
ボットのトレーニング
示唆の使用方法
インテントとエンティティのパターンの使用方法
コンテキスト切り替えの管理方法
ボットのデプロイ
エージェント転送の設定方法
ボット関数の使用方法
コンテンツ変数の使用方法
グローバル変数の使用方法
Web SDK Tutorial(英語)
Widget SDK Tutorial(英語)
ボットの分析
カスタムダッシュボードの作成方法
カスタムタグを使ってフィルタリング
管理
ボット管理者コンソール
ダッシュボード
ユーザーの管理
ユーザーの管理
グループの管理
ロール管理
ボット管理モジュール
登録
ユーザーの招待
招待状の一括送信
ユーザーデータのインポート
Active Directoryからユーザーを同期
セキュリティ/コンプライアンス
シングル サインオンの使用
セキュリティ設定
Billing(日本未対応)
  1. ホーム
  2. Docs
  3. Virtual Assistants
  4. SDKs
  5. Using the BotKit SDK

Using the BotKit SDK

The Kore.ai BotKit SDK is a set of libraries that enable interaction control between users and the assistants you build on Kore.ai XO Platform.

When you build a dialog task using Dialog Editor in XO Platform, you can subscribe to message and webhook events by adding event handlers and controlling the messages and webhook events using the SDK.

This topic describes how the BotKit SDK is integrated with the XO Platform, the SDK events you can use, and download and installation instructions for the BotKit SDK.

While Virtual Assistants can be built to help answer user queries and to perform a transaction for a user, in some cases, we may still need to switch from an interaction with the assistant to a human agent to help the user complete the intent.

For example:

  • A user asks a question or provides a response that the assistant is not designed to answer.
  • A user directly requests to chat with a Live Agent rather than that assistant itself.
  • As a developer, you design a Live Agent transfer based on the dialog flow based on a specific condition. For example, a specific user type, or based on tone analysis of the user, you want the dialog flow to transfer to a Live Agent.

How it Works

You can integrate event handling using the BotKit SDK in your Dialog task by capturing the following event types on the XO Platform.

Messaging

On the Kore.ai XO Platform, a user interacts with your assistant on one of the defined channels . In the following diagram, you can see the user message flow through the Kore.ai XO Platform, the BotKit SDK, and our natural language processing engine.

All messages, both user and assistant responses are sent to the BotKit SDK as message events.

Feedback Survey

When a feedback survey is created for a conversation over a specific channel, a user responds to the virtual assistant for a survey question based on the configured survey type (NPS, CSAT, or Thumbs-up/down). The feedback survey score sent by the user is captured in the system.

All the feedback survey messages exchanged between the user and the assistant are sent to the BotKit SDK as message events.

Webhooks

Your BotKit SDK receives webhook events whenever the natural language processor enters the SDK Webhook node in an XO Platform dialog task flow. In the following sequence diagram, flow for a user sending a message via a channel until the user response is shown.

For webhook events, you should add a Webhook node in the dialog task flow whenever there is a need for server-side validation, execution of business logic, or a backend server call is required. Business logic and the response is sent on the same on_webhook event. The response is an HTTP status code 202. To send response data to the XO Platform from the SDK, call the sdk.sendWebhookResponse() event.

Webhook events are received by the SDK when the Kore.ai NL Engine processes a Webhook node in a dialog task flow. The Kore.ai NLP engine processes each node, and then transitions to the next node based on the conditions defined. When a Webhook node is processed, a webhook call is executed and the XO Platform sends the on_webhook event to the SDK. The following sequence diagram shows the message flow with a webhook.

Agent Transfer

In the following sequence diagram, the XO Platform responds to user input directly, until the Agent Transfer condition is matched. When matched, the XO Platform connects to your BotKit SDK implementation, and then initializes the chat, for example, getting the current conversation. The BotKit SDK integrates the user and agent conversation until the Live Agent session is closed. When switching to a Live Agent, the current dialog task ends.

To set up an Agent Transfer in your dialog conversation flow, you will need to:

  1. Create an app on the XO Platform under Build > Integrations > BotKit section.
    Note: RS256 and RS512 JWT signing algorithms are not supported for Custom BotKit or Botkit.
  2. Define the Callback URL and generate Client ID and Client Secret, and enable OnAgentTransferNode.
  3. Identify the steps and define the transition conditions to meet to transfer to an agent.
  4. Add the Agent Transfer node in the dialog flow as shown in the following illustration

For more information, see BotKit SDK Tutorial – Agent Transfer.

Using the BotKit SDK

The Kore.ai BotKit SDK is a set of libraries that enable interaction control between users and the assistants you build on Kore.ai XO Platform.

When you build a dialog task using Dialog Editor in XO Platform, you can subscribe to message and webhook events by adding event handlers and controlling the messages and webhook events using the SDK.

This topic describes how the BotKit SDK is integrated with the XO Platform, the SDK events you can use, and download and installation instructions for the BotKit SDK.

While Virtual Assistants can be built to help answer user queries and to perform a transaction for a user, in some cases, we may still need to switch from an interaction with the assistant to a human agent to help the user complete the intent.

For example:

  • A user asks a question or provides a response that the assistant is not designed to answer.
  • A user directly requests to chat with a Live Agent rather than that assistant itself.
  • As a developer, you design a Live Agent transfer based on the dialog flow based on a specific condition. For example, a specific user type, or based on tone analysis of the user, you want the dialog flow to transfer to a Live Agent.

How it Works

You can integrate event handling using the BotKit SDK in your Dialog task by capturing the following event types on the XO Platform.

Messaging

On the Kore.ai XO Platform, a user interacts with your assistant on one of the defined channels . In the following diagram, you can see the user message flow through the Kore.ai XO Platform, the BotKit SDK, and our natural language processing engine.

All messages, both user and assistant responses are sent to the BotKit SDK as message events.

Feedback Survey

When a feedback survey is created for a conversation over a specific channel, a user responds to the virtual assistant for a survey question based on the configured survey type (NPS, CSAT, or Thumbs-up/down). The feedback survey score sent by the user is captured in the system.

All the feedback survey messages exchanged between the user and the assistant are sent to the BotKit SDK as message events.

Webhooks

Your BotKit SDK receives webhook events whenever the natural language processor enters the SDK Webhook node in an XO Platform dialog task flow. In the following sequence diagram, flow for a user sending a message via a channel until the user response is shown.

For webhook events, you should add a Webhook node in the dialog task flow whenever there is a need for server-side validation, execution of business logic, or a backend server call is required. Business logic and the response is sent on the same on_webhook event. The response is an HTTP status code 202. To send response data to the XO Platform from the SDK, call the sdk.sendWebhookResponse() event.

Webhook events are received by the SDK when the Kore.ai NL Engine processes a Webhook node in a dialog task flow. The Kore.ai NLP engine processes each node, and then transitions to the next node based on the conditions defined. When a Webhook node is processed, a webhook call is executed and the XO Platform sends the on_webhook event to the SDK. The following sequence diagram shows the message flow with a webhook.

Agent Transfer

In the following sequence diagram, the XO Platform responds to user input directly, until the Agent Transfer condition is matched. When matched, the XO Platform connects to your BotKit SDK implementation, and then initializes the chat, for example, getting the current conversation. The BotKit SDK integrates the user and agent conversation until the Live Agent session is closed. When switching to a Live Agent, the current dialog task ends.

To set up an Agent Transfer in your dialog conversation flow, you will need to:

  1. Create an app on the XO Platform under Build > Integrations > BotKit section.
    Note: RS256 and RS512 JWT signing algorithms are not supported for Custom BotKit or Botkit.
  2. Define the Callback URL and generate Client ID and Client Secret, and enable OnAgentTransferNode.
  3. Identify the steps and define the transition conditions to meet to transfer to an agent.
  4. Add the Agent Transfer node in the dialog flow as shown in the following illustration

For more information, see BotKit SDK Tutorial – Agent Transfer.

メニュー