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)
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
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
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
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
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
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
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
Migrate External Bots
Google Dialogflow Bot
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
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. ホーム
  2. Docs
  3. Virtual Assistants
  4. Analyzing Your Bot
  5. LLM and Generative AI Logs

LLM and Generative AI Logs

The LLM and Gen AI Logs on the XO Platform provide detailed information about requests sent to LLMs and the corresponding responses. The logs include data on features accessing the LLMs, response generation time, payload details, tokens used, and more. It enables bot designers to track and compare usage across various LLM features and refine prompts and settings to boost performance and user experience.

The log analysis focuses on the following key areas:

  • Request-response dynamics: Analysis of request-response dynamics between user prompts and model responses offers insights into prompt and model performance in specific scenarios.
  • Payload details: Analyzing the payload data exchanged during interactions allows for effective monitoring and optimization of advanced AI functionalities.

To access the logs, Go to Analyze > LLM and Gen AI Logs. Click any record to view the log summary and payload details.

Field Description

You can sort the data by either Newest to Oldest or Oldest to Newest. Click the click to view the Summary and Payload Details.

Fields Description
Date & Time The timestamp of the call made to the LLM. 
User ID The distinct identifier of the end user engaged in the conversation.

You can view the metrics based on the Kore User id or Channel User Id.

Channel-specific ids are shown only for the users who have interacted with the VA during the selected period.

Feature The XO Platform feature (Co-Pilot and Dynamic conversation features) is making calls to the LLM models.
Description Extra details about the node and task name linked to the feature.
Model The Large Language Model to which the request was made.
Language The language in which the conversation occurred.
If it is a multi-lingual VA, you can select specific languages to filter the conversations that occurred in those languages. The page shows the conversations that happen in all enabled languages by default.
Time Taken Time taken by the LLM to generate the response.
Status Status of a call made to the LLM. “Success” or “Failure”.
User Bot designer or end user who made a call to the LLM.
Integration Type Type of integration used (e.g. System/Custom).
Prompt Name Prompt used with the model and running at the node/task level. The pre-built prompts are named ‘Default.
Channel The communication channel or platform used for the interaction with LLM.
Session ID Identifier for the session.
Request Payload The request payload sent to a Large Language Model (LLM) is the user’s input or question, along with any extra details needed for the model to give a good response. 
Response Payload The Large Language Model (LLM) produces a response payload as its answer to the input it receives. It’s in the text format and contains additional information required to present the response. This payload helps developers use the model’s output effectively.
Request Tokens Request tokens for a Language Model (LLM) are the individual parts of input text, like words or punctuation, given to the model to create a response. These tokens are the basis for the model’s understanding and its output generation.
Response Tokens Response tokens for a Large Language Model (LLM) are the pieces of generated output, like words or punctuation, showing the model’s response. These tokens make up the structured parts of the LLM’s text, making it easier to understand and analyze.

Filter Criteria

The LLM and GenAI logs data can be viewed based on specific filter criteria that can be selected. Learn more.

 

LLM and Generative AI Logs

The LLM and Gen AI Logs on the XO Platform provide detailed information about requests sent to LLMs and the corresponding responses. The logs include data on features accessing the LLMs, response generation time, payload details, tokens used, and more. It enables bot designers to track and compare usage across various LLM features and refine prompts and settings to boost performance and user experience.

The log analysis focuses on the following key areas:

  • Request-response dynamics: Analysis of request-response dynamics between user prompts and model responses offers insights into prompt and model performance in specific scenarios.
  • Payload details: Analyzing the payload data exchanged during interactions allows for effective monitoring and optimization of advanced AI functionalities.

To access the logs, Go to Analyze > LLM and Gen AI Logs. Click any record to view the log summary and payload details.

Field Description

You can sort the data by either Newest to Oldest or Oldest to Newest. Click the click to view the Summary and Payload Details.

Fields Description
Date & Time The timestamp of the call made to the LLM. 
User ID The distinct identifier of the end user engaged in the conversation.

You can view the metrics based on the Kore User id or Channel User Id.

Channel-specific ids are shown only for the users who have interacted with the VA during the selected period.

Feature The XO Platform feature (Co-Pilot and Dynamic conversation features) is making calls to the LLM models.
Description Extra details about the node and task name linked to the feature.
Model The Large Language Model to which the request was made.
Language The language in which the conversation occurred.
If it is a multi-lingual VA, you can select specific languages to filter the conversations that occurred in those languages. The page shows the conversations that happen in all enabled languages by default.
Time Taken Time taken by the LLM to generate the response.
Status Status of a call made to the LLM. “Success” or “Failure”.
User Bot designer or end user who made a call to the LLM.
Integration Type Type of integration used (e.g. System/Custom).
Prompt Name Prompt used with the model and running at the node/task level. The pre-built prompts are named ‘Default.
Channel The communication channel or platform used for the interaction with LLM.
Session ID Identifier for the session.
Request Payload The request payload sent to a Large Language Model (LLM) is the user’s input or question, along with any extra details needed for the model to give a good response. 
Response Payload The Large Language Model (LLM) produces a response payload as its answer to the input it receives. It’s in the text format and contains additional information required to present the response. This payload helps developers use the model’s output effectively.
Request Tokens Request tokens for a Language Model (LLM) are the individual parts of input text, like words or punctuation, given to the model to create a response. These tokens are the basis for the model’s understanding and its output generation.
Response Tokens Response tokens for a Large Language Model (LLM) are the pieces of generated output, like words or punctuation, showing the model’s response. These tokens make up the structured parts of the LLM’s text, making it easier to understand and analyze.

Filter Criteria

The LLM and GenAI logs data can be viewed based on specific filter criteria that can be selected. Learn more.

 

メニュー