Voice AI - Agent Logs
Understanding how your AI handles conversations is essential for improving performance and fixing issues quickly. Agent Logs give you a clear, step-by-step view of every interaction so you can review conversations, track execution, and troubleshoot with confidence.Agent Logs provide full visibility into AI interactions, helping you understand what happened during a call, where delays occurred, and how decisions were made. This makes it easier to debug issues, optimize performance, and improve overall experience. * * * ## What is Voice AI Agent Logs? Agent Logs is a centralized view of AI interactions that shows conversation history, execution steps, timestamps, and system-level details. It allows you to analyze interactions from start to finish without guesswork. * * * ## Key Benefits of Voice AI Agent Logs Agent Logs help you better understand and optimize AI behavior by providing: - Conversation visibility: See full interactions between users and the AI - Execution tracking: Follow each step with precise timestamps - Transfer insights: Identify how and when agent handoffs occur - Latency analysis: Detect slow steps in conversations - Data inspection: View raw and formatted input/output data - Failure detection: Quickly identify where issues occurred * * * ## How To Navigate and Use Agent Logs ### Access Agent Logs !(https://assets.patientcopilot.ai/cff7e16e191009d5.png) This image shows where to access Agent Logs from the main navigation. - Navigate to AI Agents - Click on Agent Logs in the top menu ### Review the Logs Table !(https://assets.patientcopilot.ai/765536407ab22374.png) This image highlights the columns available in the logs table. - Use the table to review interactions based on: - Use filters at the top to narrow down results ### Locate and Select a Log !(https://assets.patientcopilot.ai/7e7756435dd2ed26.png) This view shows multiple interactions listed for review. - Scroll through logs to find the interaction you want - Look at timestamps and status to identify relevant sessions ### Open Detailed Log View !(https://assets.patientcopilot.ai/3a7d5142d46297c6.png) This screen shows how to open a specific interaction. - Click on an Agent name OR - Use the action menu (three dots) → View Details ### Analyze the Conversation !(https://assets.patientcopilot.ai/fa0bfab1aa13cd14.png) This section shows the full interaction between the AI and the user. - - Call recording playback (if enabled) - Context of the interaction ### Trace Execution Timeline !(https://assets.patientcopilot.ai/e205d351bfa88575.png) This panel shows step-by-step execution of the interaction. - Follow events in chronological order - - Failures - Use timestamps to pinpoint issues ### Inspect Input & Output Data !(https://assets.patientcopilot.ai/393e90c420eaea02.png) This image shows how to switch between raw and parsed data views. - - Raw: Original system data - Parsed: Human-readable format - Review what was sent and received at each step ### Review Technical Details !(https://assets.patientcopilot.ai/ec107e56ae5068e3.png) This panel provides deeper insights into execution. - Use this information to audit performance and debug issues * * * ## Frequently Asked Questions Q: Why is call recording not visible? Call recording appears only if it is enabled for the phone number used in the interaction. Q: What can I use Agent Logs for? You can review conversations, trace execution steps, debug issues, analyze performance, and identify failures. Q: What is the difference between conversation view and execution timeline? The conversation view shows the interaction as it happened, while the execution timeline shows the technical steps behind it. Q: What does Raw vs Parsed mean? Raw shows the original system data, while Parsed displays a cleaner, readable version. Q: Can I track agent transfers? Yes, you can see which agent initiated a transfer, which agent took over, and whether it was successful. Q: How do I troubleshoot a failed interaction? Open the log details, review the execution timeline, and inspect the step where the failure occurred. * * * ## Related Articles - How to Create Voice AI Agents
