View Logs

Feature Overview

The Logs feature offers real-time insights into each input and output message within the dialog simulator, providing essential information that simplifies the debugging process and accelerates troubleshooting.

Log expanded. Click the pin next to the message to view details for that specific message.

Accessing Logs

The Logs can be accessed through the dialog simulator by clicking on the Open log (pin icon).

Key Functionalities

Function	Description
Error Tracking and Identification	Displays a field detailing the error that occurred with that functionality, such as error type and precise timestamp (in milliseconds).
Detailed Information on Services	External Services: Logs show timestamps, error messages, error codes, service type, response, and metadata for all external service calls (e.g., Rest Connector, Prompt cell, Knowledge AI, Multilingual suppport, Webhook, Transactional answers). Gen AI services include prompt details, language model, tokens used, and temperature settings. Internal Services: Logs include information on internal components (e.g., NLP calls, masking, Knowledge AI), covering intent scores, error codes, and answers.
Exporting and Downloading	Logs can be downloaded in JSON format for documentation, further analysis, or archiving.
Entry Structure	Each entry is displayed as a single line for easy scanning, with comprehensive tracking of interactions, particularly for cells that call external services.
Filtering	Logs can be pinned to specific conversation points, allowing users to filter by message and trace errors to their origin within the dialog flow. You can filter logs based on date/time and type (info or error), ensuring an easier way to navigate.

The NLP option only appears when the agent is integrated with a NLP. If your agent is integrated with a LLM, Zero-Shot will appear instead.

If you need a more in-depth insights into your analysis, try executing an Advanced Request task to assess your agent’s performance.