Storm OpenAPI(en)
  1. Agent Builder
Storm OpenAPI(en)
  • Welcome to STORM
    • Introduction
  • Quickstart
    • Getting Started
      • Creating an Agent
      • Account Creation
    • Core Scenario
      • Document Upload
      • Workflow Design
      • Test
      • Deployment
      • Channel Integration
  • Feature Guide
    • Console
      • Agent Management
      • Dashboard
      • Permission Management
    • Agent Template
      • Knowledge Retrieval
      • Character Dialogue
      • Consultation Record Analysis
      • SQL Query
      • News Article
    • Agent Builder
      • Knowledge
        • Documents
        • Folders
        • Feedback
      • Workflow
        • Node Description
          • LLM
          • Search(RAG)
          • API
          • IF ELSE
          • Variable Declaration and Assignment
          • Postprocessing
      • Test
      • Log
      • Dashboard
    • Admin Tools
      • Deployment Management
      • Channel Integration
      • Model Fine-Tuning
      • Training Data Quality Management
      • Other Settings
  • Apis
    • Agent
      • Deploy Agent
      • View Agent Deployment History
      • View Agent
    • Bucket
      • Create Bucket
      • View Bucket
    • Document
      • Document Training Request by file
      • Document Training Request by URL
      • View Documents
      • Delete Document
    • Chat
      • Send Chat (non-stream)
      • Send Chat (stream)
      • Search Context
    • STORM Parse
      • /convert/md
    • Instance Agent
      • Add Instance Session
      • Upload Instance Document
      • Request RAG Source For Query
      • Delete Instance Session
  • Learn More
    • FAQ
    • Pricing
  1. Agent Builder

Log

Log#

The Log Page is a core tool that allows you to monitor agent response activity based on real user input history, helping you gain insights for knowledge enhancement and quality improvement.
Real User Query Analysis
Review the actual questions (queries) submitted by users to identify frequently asked topics or high-interest areas.
Use these insights to detect gaps or missing information within the knowledge base and to prioritize which knowledge items need to be updated or newly registered.
Agent Response Review
Check the responses generated by the agent for each query.
Assess whether the responses align with user intent, contain inaccuracies, or omit essential information.
This enables systematic identification of cases that require additional learning or correction.


Group 633223.png
Review the full conversation history between users and the agent.
Filter logs by specific date or specific channel to view only the relevant records.
Search by keywords to locate conversations containing specific topics.
Search by chat ID or thread ID to review individual conversations.
To view all messages exchanged in a specific chat, click the More button on the right and select View full conversation history.
All applied search terms and filters are combined using an AND condition.

To review only the test logs executed in STORM Admin, select STORM Test Environment from the environment filter.
To focus solely on real user interaction logs, select Service Environment instead.

You can filter logs to display only entries that require review:
Response Failure Messages – Items where the agent failed to respond. These can receive “Needs Improvement 👎” feedback.
System Error Messages – Cases where the agent couldn’t respond due to internal service issues. These users may require follow-up support.
Low Confidence – Responses with low accuracy. These can also receive “Needs Improvement 👎” feedback.
High Confidence – Responses with high accuracy. These can be marked as “Good 👍” feedback.

You can download the conversation logs between users and the agent.
Note that only logs matching the currently applied filters will be included in the download.
Modified at 2025-10-20 05:54:02
Previous
Test
Next
Dashboard
Built with