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
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
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Guardrails
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
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
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
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
Data
Overview
Guidelines
Data Table
Table Views
App Definitions
Data as Service
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Installing Botkit in AWS
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer

ADMINISTRATION
Intro to Bots Admin Console
Administration Dashboard
User Management
Managing Your Users
Managing Your Groups
Role Management
Manage Data Tables and Views
Bot Management
Enrollment
Inviting Users
Sending Bulk Invites to Enroll Users
Importing Users and User Data
Synchronizing Users from Active Directory
Security & Compliance
Using Single Sign-On
Two-Factor Authentication for Platform Access
Security Settings
Cloud Connector
Analytics for Bots Admin
Billing
  1. ホーム
  2. Docs
  3. Virtual Assistants
  4. Natural Language
  5. LLM and Generative AI
  6. Co-Pilot Features

Co-Pilot Features

The Co-Pilot features add design-time capabilities to accelerate your bot development process using tailored LLM features. By default, all the features are disabled. To enable the feature, select the model, prompt, and toggle the status to enable it. You can select another supported model for a feature if you have configured multiple models. You can also change the model, its prompts, and its settings.

Steps to enable the feature:

  1. Navigate to Build > Natural Language > Generative AI & LLM > Co-Pilot.
  2. Select the Model and the Prompt from the drop-down list for a feature.
  3. Turn on the Status toggle. The success message is displayed.

Change Settings for a Model

Choose the option below based on the model for which you want to change the settings:

Change Settings for a Pre-built Model

Change Settings for a Pre-built Model

You can change the selected model’s settings if required. In most cases, the default settings work fine.

Follow these steps:

  1. Go to Build > Natural Language > Generative AI & LLM > Co-Pilot or Dynamic Conversation.
  2. Hover over the feature to view the Advance Setting (gear) icon.

  3. Click the Advance Setting. The Advance Settings dialog box is displayed.

    Adjusting the settings allows you to fine-tune the model’s behavior to meet your needs. The default settings work fine for most cases. You can tweak the settings and find the right balance for your use case. A few settings are common in the features, and a few are feature-specific:
    • Model: The selected model for which the settings are displayed.
    • Instructions or Context: Add feature/use case-specific instructions or context to guide the model.
    • Temperature: The setting controls the randomness of the model’s output. A higher temperature, like 0.8 or above, can result in unexpected, creative, and less relevant responses. On the other hand, a lower temperature, like 0.5 or below, makes the output more focused and relevant.
    • Max Tokens: It indicates the total number of tokens used in the API call to the model. It affects the cost and the time taken to receive a response. A token can be as short as one character or as long as one word, depending on the text.
    • Number of Previous User Inputs: Indicates how many previous user messages should be sent to the model as context for rephrasing the response sent through the respective node. For example, 5 means that the previous 5 responses are sent as context.
    • Additional Instructions: Add specific instructions on how prompts should be rephrased. You can create a persona, ask it to rephrase in a particular tone, etc.
    • Similarity Threshold: The Similarity Threshold is applicable for the Answer from Docs feature. This threshold refers to the similarity between the user utterance and the document chunks. The platform shortlists all chunks that are above the threshold and sends these chunks to the LLMs to auto-generate the responses. Define a suitable threshold that works best for your use case. Setting a higher threshold limits the number of chunks and may not generate any result. Setting a lower threshold might qualify too many chunks and might dilute the response.
Change Settings for a Custom Model

Change Settings for a Custom Model

For a custom model, you can only change the post-processor script to adjust the actual response with the expected response.

Follow these steps:

  1. Go to Build > Natural Language > Generative AI & LLM > Co-Pilot.
  2. Hover over the feature to view the Setting (gear) icon.

  3. Click Edit. The Actual Response is displayed.

  4. Click Configure. The Post Processor Script is displayed.

  5. Modify the script and click Save & Test. The Response is displayed.

  6. Click Save.

Model and Feature Support Matrix

The following table displays the Co-Pilot features and the supported models.

(✅ Supported | ❌ Not supported)

Model/Feature Automatic Dialog Generation Conversation Test Case Suggestions Conversation Summary NLP Batch Test Case Suggestions Training Utterance Suggestions
Azure OpenAI – GPT 3.5 Turbo
Azure OpenAI – GPT 4
Azure OpenAI – GPT 4 Turbo
Azure OpenAI – GPT 4o
OpenAI – GPT 3.5 Turbo
OpenAI – GPT 4
OpenAI – GPT 4 Turbo
OpenAI – GPT 4o
Anthropic – Claude Instant
Anthropic – Claude
Custom LLM
Kore.ai XO GPT

 

Note: Azure OpenAI and OpenAI have officially ended support for their GPT-3 model on January 4, 2024. We recommend selecting a higher or alternate model for supported features as soon as possible. Learn more.

Feature Details

Automatic Dialog Generation

This feature auto-generates conversations and dialog flows in the selected language using the VA’s purpose and intent description provided (in English or the selected Non-English Bot Language) during the creation process. The Platform uses LLM and generative AI to create suitable Dialog Tasks for Conversation Design, Logic Building & Training by including the required nodes in the flow. 

You must provide an intent description, and the Platform handles the Conversation Generation for the Dialog Flow.

You can preview the conversation flow, view the Bot Action taken, improvise the intent description, and regenerate the conversation to make it more human-like.

The nodes and the flow for the Business Logic are automatically built for your conversation, and you only need to configure the flow transition.

The Platform auto-defines the Entities, Prompts, Error Prompts, Bot Action nodes, Service Tasks, Request Definition, Connection Rules, and other parameters.

Usage

Once you enable this feature:

  1. The Platform triggers the flow when you launch a task for the first time.
  2. The Platform presents the intent description and an option to generate conversation.
  3. You can preview the generated conversation, edit the description, and regenerate it.
  4. The Platform sends the updated description to Generative AI in the background to get the new conversation.
  5. Once you’re satisfied with the conversation, generate a dialog task.

If this feature is disabled, you will not have the option to auto-generate a dialog flow when first launching a Dialog Task.

Note: The Platform uses the configured API Key to authorize and generate the suggestions from OpenAI.

Learn more.

Conversation Test Cases Suggestions

This feature provides a regression tool or a Playbook that creates a conversation test suite for each intent (new and old) in English or Non-English Bot language to evaluate the impact of the change on the conversation execution.

You can view input/utterance suggestions at every conversation step simulating the various input types and scenarios. This feature helps check if the task/intent is robust enough to handle random user utterances.

This feature also helps you predict and simulate the end user’s behavior and check if the VA can execute all the defined flows by generating user responses and presenting any digressions from the specified intent.

Usage

  1. You can create a test suite by recording a live conversation with a VA by initiating the interaction or letting the VA initiate it.
  2. An icon displays to indicate the user input suggestions from Generative AI.
  3. The Platform triggers OpenAI or Anthropic Claude-1 based on your model selection to generate suggestions for user input where expected in English or a Non-English Bot Language.
  4. The Platform shares the following information with OpenAI/Anthropic to generate suggestions
  • Randomly picked intents from the VA (Dialog, FAQ),
  • Conversation flow,
  • Current Intent, if any,
  • Current node type:
    • For an entity node, the system sends the following:
      • Entity name,
      • Entity type,
      • Sample entity values. 
    • Types of user input scenarios:
      • Entities,
      • Without entities,
      • Different entity combinations in the user input,
      • Digression to another intent,
      • Trigger error scenarios.
  • You can regenerate suggestions if required.
  • You can accept the suggestions shown or type custom input at every step.
  • Create a Test Suite after stopping the recording and validating the model.

If the feature is disabled, the Platform doesn’t display the Generative AI suggestions icon and the suggestions themselves. Learn more.

Conversation Summary

This feature generates concise, natural language summaries of interactions between the virtual assistant, users, and human agents. It distills the key intents, entities, decisions, and outcomes into an easy-to-read synopsis. Companies can leverage conversation summarization to boost agent productivity, ensure process compliance, and create better contextual recommendations – without having to read lengthy transaction histories. It is pre-integrated with Kore.ai’s Contact Center platform. It is also extensible to third-party applications via API integration.

Note: For existing bots, by default, the feature is enabled with the Kore.ai XO GPT Model. For new bots, the feature is disabled.
This feature is broadly implemented in two scenarios discussed below:

Scenario 1

In a contact center environment, the customer interacting with a VA may request to transfer to a live agent. During agent handoff, the agent must have the necessary context information and interaction history to assist the customers efficiently. The system generates the conversation transcript and interaction summary and routes it to the agent for better understanding.

An example of the usage: When Conversation Summary is enabled and the conversation is transferred to an agent in SmartAssist, the Conversation Summary is displayed on the Agent Console, as shown in the screenshot below.

Conversation Summary Generated by XO GPT

Usage

The Conversation Summary public API fetches the summary of the entire conversation included in the transcript. LLM and Generative AI are leveraged to provide a concise and informative conversation summary from the transcript.

Scenario 2

When closing a conversation request, contact centers require an agent to summarize the customer interaction and context in their closing notes to confirm that the issue has been resolved effectively. Closing notes help document the interactions, provide context for future interactions, support quality assurance efforts, and serve as references to deliver effective customer service.

Usage 

The system uses the Conversation Summary public API to fetch the details of the entire conversation between the customer and the VA or agent. The API uses an open-source LLM to summarize conversations using a large number of sample conversation transcripts.

NLP Batch Test Cases Suggestions

This feature lets you generate test cases based on the NLU Language selected, and add them to the test suite with minimum or no errors. You can give instructions in English or any Non-English bot language you’ve selected. Additionally, in case of a Multilingual NLU, the system generates utterances in the language prompted by the user. For instance, if your instructions are in Hindi, the utterances are generated in Hindi.

Usage

  1. When creating a New Test Suite, select Add Manually or Upload Test Cases File to add test cases. 
  2. Add Manually creates an empty test suite where you can generate test cases and do the following:
  • Select a Dialog Task.
  • Based on the intent context, the Generative AI generates test cases you can review and add to or remove from the Test Suite.
  1. When you click Generate Test Cases, the Platform sends Generative AI (OpenAI or Anthropic Claude-1 model based on your selection) the following information to generate test cases:
  • Intent
  • Entities
  • Probable entity value
  • Different scenarios to simulate end-user utterances,
  • Random training utterances and test cases that are generated to avoid duplicate test cases from Generative AI.

If this feature is disabled, you will not have the option to generate test cases during batch testing. Learn more.

Training Utterance Suggestions

This feature generates a list of suggested training utterances and NER annotations based on the selected NLU language for each intent description and Dialog Flow, eliminating the need for manual creation.

Usage

The Platform can generate utterances in the NLU language to train your VA.

Once you request to generate utterances for a given intent, the Platform provides utterance suggestions (in the selected NLU language) based on the following information: 

  1. Intent
  2. Entities and Entity Types
  3. Probable entity values
  4. Different scenarios for training utterances based on entities, a combination of entities, structurally different utterances, etc.

You can add/delete the suggested training utterances from the list or generate more suggestions.

If this feature is disabled, you won’t see the Suggestions tab on the training page. Learn more.

Use Case Suggestions

In the standard Virtual Assistant creation journey, use case suggestions help link the standard bot to a business scenario. Based on the selected use case, the system identifies and creates specific dialog tasks or interactions that the virtual assistant should be able to handle.

Note: This feature is only available if Default Language is set to English.

Generating Use Cases automatically creates up to 30 customizable Dialog Tasks tailored to specific use cases. This streamlines the development process, as developers won’t need to manually create each interaction from scratch.

LLM and Generative AI help generate accurate suggestions automatically without configuring any LLM settings for this feature. Providing a detailed bot description is crucial for the effective functioning of this feature. The more information you provide about the virtual assistant’s intended purpose and capabilities, the better the generated use case suggestions will be.

Usage

  1. The user initiates a new standard virtual assistant creation on the XO Platform.
  2. The user provides the Bot Name and selects the following:
  • Purpose 
  • Standard Bot for Bot Type.
  • English for Default Language.
  1. When adding the short Bot description, the user must include specific details on the high-level scenarios the Bot needs to handle.
  2. The user generates use case suggestions by clicking Get Use Cases.
  3. Based on the user’s description, the system generates improved use case suggestions with the help of the OpenAI Model.

  1. The user selects the relevant use cases from the suggestions to create and configure the VA accordingly.

If you select Create without use cases when creating a bot, the system won’t provide use case suggestions for VA creation. Only the default Dialogs for Welcome and Fallback tasks are created for the VA. Learn more.

Co-Pilot Features

The Co-Pilot features add design-time capabilities to accelerate your bot development process using tailored LLM features. By default, all the features are disabled. To enable the feature, select the model, prompt, and toggle the status to enable it. You can select another supported model for a feature if you have configured multiple models. You can also change the model, its prompts, and its settings.

Steps to enable the feature:

  1. Navigate to Build > Natural Language > Generative AI & LLM > Co-Pilot.
  2. Select the Model and the Prompt from the drop-down list for a feature.
  3. Turn on the Status toggle. The success message is displayed.

Change Settings for a Model

Choose the option below based on the model for which you want to change the settings:

Change Settings for a Pre-built Model

Change Settings for a Pre-built Model

You can change the selected model’s settings if required. In most cases, the default settings work fine.

Follow these steps:

  1. Go to Build > Natural Language > Generative AI & LLM > Co-Pilot or Dynamic Conversation.
  2. Hover over the feature to view the Advance Setting (gear) icon.

  3. Click the Advance Setting. The Advance Settings dialog box is displayed.

    Adjusting the settings allows you to fine-tune the model’s behavior to meet your needs. The default settings work fine for most cases. You can tweak the settings and find the right balance for your use case. A few settings are common in the features, and a few are feature-specific:
    • Model: The selected model for which the settings are displayed.
    • Instructions or Context: Add feature/use case-specific instructions or context to guide the model.
    • Temperature: The setting controls the randomness of the model’s output. A higher temperature, like 0.8 or above, can result in unexpected, creative, and less relevant responses. On the other hand, a lower temperature, like 0.5 or below, makes the output more focused and relevant.
    • Max Tokens: It indicates the total number of tokens used in the API call to the model. It affects the cost and the time taken to receive a response. A token can be as short as one character or as long as one word, depending on the text.
    • Number of Previous User Inputs: Indicates how many previous user messages should be sent to the model as context for rephrasing the response sent through the respective node. For example, 5 means that the previous 5 responses are sent as context.
    • Additional Instructions: Add specific instructions on how prompts should be rephrased. You can create a persona, ask it to rephrase in a particular tone, etc.
    • Similarity Threshold: The Similarity Threshold is applicable for the Answer from Docs feature. This threshold refers to the similarity between the user utterance and the document chunks. The platform shortlists all chunks that are above the threshold and sends these chunks to the LLMs to auto-generate the responses. Define a suitable threshold that works best for your use case. Setting a higher threshold limits the number of chunks and may not generate any result. Setting a lower threshold might qualify too many chunks and might dilute the response.
Change Settings for a Custom Model

Change Settings for a Custom Model

For a custom model, you can only change the post-processor script to adjust the actual response with the expected response.

Follow these steps:

  1. Go to Build > Natural Language > Generative AI & LLM > Co-Pilot.
  2. Hover over the feature to view the Setting (gear) icon.

  3. Click Edit. The Actual Response is displayed.

  4. Click Configure. The Post Processor Script is displayed.

  5. Modify the script and click Save & Test. The Response is displayed.

  6. Click Save.

Model and Feature Support Matrix

The following table displays the Co-Pilot features and the supported models.

(✅ Supported | ❌ Not supported)

Model/Feature Automatic Dialog Generation Conversation Test Case Suggestions Conversation Summary NLP Batch Test Case Suggestions Training Utterance Suggestions
Azure OpenAI – GPT 3.5 Turbo
Azure OpenAI – GPT 4
Azure OpenAI – GPT 4 Turbo
Azure OpenAI – GPT 4o
OpenAI – GPT 3.5 Turbo
OpenAI – GPT 4
OpenAI – GPT 4 Turbo
OpenAI – GPT 4o
Anthropic – Claude Instant
Anthropic – Claude
Custom LLM
Kore.ai XO GPT

 

Note: Azure OpenAI and OpenAI have officially ended support for their GPT-3 model on January 4, 2024. We recommend selecting a higher or alternate model for supported features as soon as possible. Learn more.

Feature Details

Automatic Dialog Generation

This feature auto-generates conversations and dialog flows in the selected language using the VA’s purpose and intent description provided (in English or the selected Non-English Bot Language) during the creation process. The Platform uses LLM and generative AI to create suitable Dialog Tasks for Conversation Design, Logic Building & Training by including the required nodes in the flow. 

You must provide an intent description, and the Platform handles the Conversation Generation for the Dialog Flow.

You can preview the conversation flow, view the Bot Action taken, improvise the intent description, and regenerate the conversation to make it more human-like.

The nodes and the flow for the Business Logic are automatically built for your conversation, and you only need to configure the flow transition.

The Platform auto-defines the Entities, Prompts, Error Prompts, Bot Action nodes, Service Tasks, Request Definition, Connection Rules, and other parameters.

Usage

Once you enable this feature:

  1. The Platform triggers the flow when you launch a task for the first time.
  2. The Platform presents the intent description and an option to generate conversation.
  3. You can preview the generated conversation, edit the description, and regenerate it.
  4. The Platform sends the updated description to Generative AI in the background to get the new conversation.
  5. Once you’re satisfied with the conversation, generate a dialog task.

If this feature is disabled, you will not have the option to auto-generate a dialog flow when first launching a Dialog Task.

Note: The Platform uses the configured API Key to authorize and generate the suggestions from OpenAI.

Learn more.

Conversation Test Cases Suggestions

This feature provides a regression tool or a Playbook that creates a conversation test suite for each intent (new and old) in English or Non-English Bot language to evaluate the impact of the change on the conversation execution.

You can view input/utterance suggestions at every conversation step simulating the various input types and scenarios. This feature helps check if the task/intent is robust enough to handle random user utterances.

This feature also helps you predict and simulate the end user’s behavior and check if the VA can execute all the defined flows by generating user responses and presenting any digressions from the specified intent.

Usage

  1. You can create a test suite by recording a live conversation with a VA by initiating the interaction or letting the VA initiate it.
  2. An icon displays to indicate the user input suggestions from Generative AI.
  3. The Platform triggers OpenAI or Anthropic Claude-1 based on your model selection to generate suggestions for user input where expected in English or a Non-English Bot Language.
  4. The Platform shares the following information with OpenAI/Anthropic to generate suggestions
  • Randomly picked intents from the VA (Dialog, FAQ),
  • Conversation flow,
  • Current Intent, if any,
  • Current node type:
    • For an entity node, the system sends the following:
      • Entity name,
      • Entity type,
      • Sample entity values. 
    • Types of user input scenarios:
      • Entities,
      • Without entities,
      • Different entity combinations in the user input,
      • Digression to another intent,
      • Trigger error scenarios.
  • You can regenerate suggestions if required.
  • You can accept the suggestions shown or type custom input at every step.
  • Create a Test Suite after stopping the recording and validating the model.

If the feature is disabled, the Platform doesn’t display the Generative AI suggestions icon and the suggestions themselves. Learn more.

Conversation Summary

This feature generates concise, natural language summaries of interactions between the virtual assistant, users, and human agents. It distills the key intents, entities, decisions, and outcomes into an easy-to-read synopsis. Companies can leverage conversation summarization to boost agent productivity, ensure process compliance, and create better contextual recommendations – without having to read lengthy transaction histories. It is pre-integrated with Kore.ai’s Contact Center platform. It is also extensible to third-party applications via API integration.

Note: For existing bots, by default, the feature is enabled with the Kore.ai XO GPT Model. For new bots, the feature is disabled.
This feature is broadly implemented in two scenarios discussed below:

Scenario 1

In a contact center environment, the customer interacting with a VA may request to transfer to a live agent. During agent handoff, the agent must have the necessary context information and interaction history to assist the customers efficiently. The system generates the conversation transcript and interaction summary and routes it to the agent for better understanding.

An example of the usage: When Conversation Summary is enabled and the conversation is transferred to an agent in SmartAssist, the Conversation Summary is displayed on the Agent Console, as shown in the screenshot below.

Conversation Summary Generated by XO GPT

Usage

The Conversation Summary public API fetches the summary of the entire conversation included in the transcript. LLM and Generative AI are leveraged to provide a concise and informative conversation summary from the transcript.

Scenario 2

When closing a conversation request, contact centers require an agent to summarize the customer interaction and context in their closing notes to confirm that the issue has been resolved effectively. Closing notes help document the interactions, provide context for future interactions, support quality assurance efforts, and serve as references to deliver effective customer service.

Usage 

The system uses the Conversation Summary public API to fetch the details of the entire conversation between the customer and the VA or agent. The API uses an open-source LLM to summarize conversations using a large number of sample conversation transcripts.

NLP Batch Test Cases Suggestions

This feature lets you generate test cases based on the NLU Language selected, and add them to the test suite with minimum or no errors. You can give instructions in English or any Non-English bot language you’ve selected. Additionally, in case of a Multilingual NLU, the system generates utterances in the language prompted by the user. For instance, if your instructions are in Hindi, the utterances are generated in Hindi.

Usage

  1. When creating a New Test Suite, select Add Manually or Upload Test Cases File to add test cases. 
  2. Add Manually creates an empty test suite where you can generate test cases and do the following:
  • Select a Dialog Task.
  • Based on the intent context, the Generative AI generates test cases you can review and add to or remove from the Test Suite.
  1. When you click Generate Test Cases, the Platform sends Generative AI (OpenAI or Anthropic Claude-1 model based on your selection) the following information to generate test cases:
  • Intent
  • Entities
  • Probable entity value
  • Different scenarios to simulate end-user utterances,
  • Random training utterances and test cases that are generated to avoid duplicate test cases from Generative AI.

If this feature is disabled, you will not have the option to generate test cases during batch testing. Learn more.

Training Utterance Suggestions

This feature generates a list of suggested training utterances and NER annotations based on the selected NLU language for each intent description and Dialog Flow, eliminating the need for manual creation.

Usage

The Platform can generate utterances in the NLU language to train your VA.

Once you request to generate utterances for a given intent, the Platform provides utterance suggestions (in the selected NLU language) based on the following information: 

  1. Intent
  2. Entities and Entity Types
  3. Probable entity values
  4. Different scenarios for training utterances based on entities, a combination of entities, structurally different utterances, etc.

You can add/delete the suggested training utterances from the list or generate more suggestions.

If this feature is disabled, you won’t see the Suggestions tab on the training page. Learn more.

Use Case Suggestions

In the standard Virtual Assistant creation journey, use case suggestions help link the standard bot to a business scenario. Based on the selected use case, the system identifies and creates specific dialog tasks or interactions that the virtual assistant should be able to handle.

Note: This feature is only available if Default Language is set to English.

Generating Use Cases automatically creates up to 30 customizable Dialog Tasks tailored to specific use cases. This streamlines the development process, as developers won’t need to manually create each interaction from scratch.

LLM and Generative AI help generate accurate suggestions automatically without configuring any LLM settings for this feature. Providing a detailed bot description is crucial for the effective functioning of this feature. The more information you provide about the virtual assistant’s intended purpose and capabilities, the better the generated use case suggestions will be.

Usage

  1. The user initiates a new standard virtual assistant creation on the XO Platform.
  2. The user provides the Bot Name and selects the following:
  • Purpose 
  • Standard Bot for Bot Type.
  • English for Default Language.
  1. When adding the short Bot description, the user must include specific details on the high-level scenarios the Bot needs to handle.
  2. The user generates use case suggestions by clicking Get Use Cases.
  3. Based on the user’s description, the system generates improved use case suggestions with the help of the OpenAI Model.

  1. The user selects the relevant use cases from the suggestions to create and configure the VA accordingly.

If you select Create without use cases when creating a bot, the system won’t provide use case suggestions for VA creation. Only the default Dialogs for Welcome and Fallback tasks are created for the VA. Learn more.

メニュー