👤 For pipe admins
🔐 Available on all plans
🎯 For those who want to monitor the performance and accuracy of their digital workforce.
The AI Agent Logs area offers full visibility into how artificial intelligence behaves within your process. It allows you to understand exactly how the agent made a decision, what data it used, and where errors occurred.
What this solves:
Observability: Transparency regarding what the agent did during execution.
Debugging: Quickly identify the location and reason for an error.
Decision Logic: Clarity on which steps were followed or ignored (skipped).
Before you start
To access the logs, you must:
Have Pipe Admin permissions.
Have at least one AI Agent configured and active in the pipe.
Step-by-step to access Logs
1. Access the AI Agents area
Inside your pipe, click the AI Agents button located in the top header.
2. Navigate to the Logs tab
In the upper-left corner of the agents' screen, click the Logs tab. Here you will see a list of all recent executions, including the agent's name, the triggered behavior, the processed card, and the execution status.
3. Analyze the Summary
To understand a specific execution, click the See Details button next to the desired log. The first view is the Summary:
Status: Success, failure, or processing.
Dates: When the execution started and ended.
Context: Which trigger started the agent and which card was affected (including the Card ID).
4. Explore the Tracing
Click the Tracing tab to view the step-by-step execution. This area details the flow followed by your agent and which steps were completed. We are constantly evolving this section to provide even more data and visibility over time regarding your agent’s behavior.
💡 Tip: Your insights are vital for the evolution of our Agents! If you have suggestions or find something that could be improved, click the Send feedback button in the top right corner to share your thoughts directly with our team.
Understanding failures and decisions
Logs are essential for fine-tuning your agent's behavior:
Clear Errors: If a step fails, the Tracing will indicate exactly which step stopped and why (e.g., a missing required field or a permission error).
Skipped Actions: The agent will show when it decided not to perform an action, accompanied by a logical justification for that decision.
Validation Checklist
After configuring or editing an agent, use the logs to:
Verify Success: Confirm that the final status is "Success."
Validate Logic: In the Tracing tab, check if it consulted the correct sources (documents/fields).
Error Testing: If the agent did not behave as expected, identify the step in the Tracing and adjust the agent's instructions.