UiPath Documentation
agents
latest
false
Agents user guide

Observability

Monitor your deployed chat agent performance, user satisfaction, and production behavior using the Instance Management dashboard.

This page describes observability for your deployed chat experiences - built in either Agent Builder or in Maestro Flow. For voice conversational agents, see Voice observability.

Use these tools to monitor production behavior and iterate on your agent's design.

Dashboard​

Instance Management provides a dashboard view for monitoring your deployed conversational experience's key metrics, performance indicators, and user-provided feedback.

Accessing the dashboard​

  1. Go to the UiPath Automation Cloud portal.
  2. Navigate to Agents > Conversational.
  3. Select your Conversational Agent (built in Agent Builder) or Conversational Flow (built in Maestro Flow)
  4. Select the Dashboard tab.
Important:

Only Instance Management — intended for admin monitoring and power users — distinguishes between build paths by labeling Agent Builder agents as Conversational Agents and Flow-built agents as Conversational Flows. Every other deployment channel surfaces both types as a Conversational Agent to end-users.

Available metrics​

The dashboard provides visibility into:

  • Usage metrics: Conversation volume and user engagement.
  • Performance indicators: Tool usage and active users.
  • User feedback: Summary of thumbs up/down ratings.

User feedback​

Feedback from users helps identify areas where your agent performs well and where it needs improvement.

How feedback works​

  1. Users provide thumbs up or thumbs down after agent responses.
  2. Users can optionally add comments explaining their feedback.
  3. Feedback is attached to the trace and can be reviewed in Instance Management.

Reviewing feedback​

Access user feedback through Instance Management:

  1. Navigate to Agents > Conversational.
  2. Select your Conversational Agent (built in Agent Builder) or Conversational Flow (built in Maestro Flow).
  3. Go to the Feedback menu.
  4. Review feedback entries with ratings and comments from users.

Use this feedback to identify areas for improvement and understand user satisfaction with agent responses.

Trace logs​

Trace logs provide detailed records of agent execution, enabling you to debug issues and understand agent behavior.

Accessing traces for Agent Builder agents​

  1. Select your Conversational Agent (built in Agent Builder).
  2. Navigate to the Review runs section.
  3. Select a job to view its trace. Any job correlated to a conversation will show the entire conversation's trace.

Accessing traces for conversational Flows​

  1. Select your Conversational Flow (built in Maestro Flow).
  2. Select Open in Maestro.
  3. Select any run to view its trace, status, and node executions.

What traces show​

Each trace includes:

  • Conversation exchanges: All back-and-forth turns in the conversation.
  • Agent runs: The agent execution under each exchange, with inputs and outputs.
  • LLM calls: Prompts sent to the model and responses received.
  • Tool invocations: Which tools were called, with inputs and outputs.
  • Timing information: Duration of each step.
  • Token usage: Tokens consumed per exchange.

Using traces for debugging​

When investigating issues:

  1. Find the conversation in Instance Management or Orchestrator jobs.
  2. Open the trace to see the full execution path.
  3. Identify where the agent deviated from expected behavior.
  4. Use insights to refine your system prompt or tool configuration.

Iterating on your agent​

Observability completes the feedback loop in the agent lifecycle. Use insights from production to improve your agent's design.

The iteration process​

  1. Identify issues: Review dashboards, feedback, and traces for problems.
  2. Diagnose root causes: Use traces to understand why issues occur.
  3. Update design: Modify system prompts, tools, or configurations.
  4. Test changes: Create evaluation tests covering the identified issues.
  5. Deploy updates: Publish the improved agent.
  6. Monitor results: Verify improvements through observability.

Common improvements based on observability​

ObservationPotential improvement
Negative feedback on specific topicsAdd or improve Context Grounding indexes
Tool failuresReview tool configuration and error handling
Long response timesOptimize tool selection or switch models
Users asking for unavailable featuresUpdate system prompt to set expectations

Audit and compliance​

AI Trust Layer Audit​

The AI Trust Layer provides a complete audit trail of LLM calls and agent behavior for compliance and governance purposes.

Access AITL audit logs through the Admin portal for:

  • Complete history of model interactions
  • Inputs and outputs
  • Data residency and compliance verification

For detailed deployment options, refer to viewing audit logs

Next steps​

Was this page helpful?

Connect

Need help? Support

Want to learn? UiPath Academy

Have questions? UiPath Forum

Stay updated