Skip to content

Conversations

View, analyze, and manage conversations between users and your AI agents.

Overview

The Conversations view provides access to all chat interactions with your agents, enabling you to: - Monitor agent performance in real conversations - Identify common user queries and issues - Review conversation quality - Export conversations for analysis - Debug agent responses

Accessing Conversations

  1. Navigate to MY AGENTS
  2. Select your agent
  3. Click Conversations from the agent menu

The Conversations menu (the conversation list panel on the left) is collapsible — collapse it to free up screen space for the conversation detail view.

Conversations Page Layout Conversations admin page — the conversation list on the left is the collapsible Conversations menu, and the Filters button at the top reveals filters that are collapsed by default

Continuous Conversations — No Hard Expiry

Conversations no longer reach a hard, user-visible expiry state. The chat input remains active across long idle periods, and post-processors run iteratively as the conversation continues.

Concept Behavior
Soft expiry on the backend When the configured stale period is reached, the backend triggers a soft expiry — Conversation Post-Processors run automatically, generating the initial outcomes (summaries, metadata extraction, CRM updates) just as before
Iterative post-processing If the user resumes the thread later, the new message is appended to the existing context. When the conversation hits the stale period again, post-processors re-run and update / overwrite the previously generated outcomes based on the newly accumulated context
User-visible state The chat input remains active across long idle periods — no "conversation expired" lockout

Configuration

The stale period is controlled by Conversation Inactivity Duration under Agent Settings > Behavior (default: 60 minutes). See Post-Processors → Conversation Inactivity Duration.

Conversation List

The conversation list displays:

  • User ID: Anonymous or identified user
  • Start Time: When conversation began
  • Duration: Length of conversation
  • Message Count: Number of messages exchanged
  • Status: Active, Completed, Escalated, or Abandoned
  • Rating: User satisfaction rating (if provided)

Filtering Conversations

Filters appear collapsed by default behind the Filters button (visible in the Conversations Page Layout above). Expand to reveal the controls below.

Filter by:

Date Range - Today - Last 7 days - Last 30 days - Custom date range

Status - Active (ongoing) - Completed (ended normally) - Escalated (handed off to human) - Abandoned (user left mid-conversation)

User Attributes - Location - Device type - Language - User segment

Quality Metrics - High satisfaction (4-5 stars) - Low satisfaction (1-2 stars) - Escalation occurred - Error encountered

Analysis Filter (Conversation Analyzer Outputs)

A new Analysis option under Filters lets you slice conversations by any Conversation Analyzer field and value. The value is free text, works on a contains-match, and is case-insensitive — e.g., filter by conversation Type: Sales to surface every conversation the analyzer tagged as a sales chat.

Analysis Filter Analysis filter — pick a Conversation Analyzer field (e.g., conversation Type), enter a free-text value (e.g., Sales), and Save. Applied filters appear as removable chips below

See Post-Processors → Conversation Analyzer for how the underlying fields are configured.

Conversation Analysis — Per-Conversation Post-Processor Inspection

Click the Conversation Analysis button on any conversation to view every post-processor that ran on it, with:

  • Status — Ready, Processing, or Failed
  • Extracted values — fields and JSON output from each analyzer / summary run
  • Error details — if a post-processor failed
  • Last-updated timestamps — most recent run for each post-processor

This makes analyzer outputs actionable at the individual conversation level, not just in aggregate reports.

Conversation Analysis Panel Conversation Analysis modal showing every post-processor run on the conversation — Conversation Analyzer (Processing), Conversation Analyzer 2 (Ready, with extracted conversation Type: Sales, competitor Mentioned: N/A), and Summary Post Processor (Failed, "Batch Models not found") — each with its last-updated timestamp

Viewing Conversation Details

Click on a conversation to view:

Message Thread

  • Complete conversation history
  • User messages
  • Agent responses
  • System messages (escalations, errors)
  • Timestamps for each message

Metadata

  • Session ID
  • User information (if available)
  • Agent version used
  • Models invoked
  • Tools called
  • Response times

Analytics

  • Average response time
  • Tool usage count
  • Knowledge base queries
  • Tokens consumed
  • Cost per conversation

Conversation Actions

Export Conversation

Export individual conversations in multiple formats: - JSON: Full conversation data with metadata - PDF: Formatted conversation transcript - CSV: Tabular message data - Text: Plain text transcript

Share Conversation

Share conversation links with team members: 1. Click Share button 2. Copy shareable link 3. Set access permissions (view only, edit) 4. Set expiration (optional)

Flag for Review

Flag conversations that need attention: - Quality issues - Agent errors - Inappropriate responses - Training opportunities

Add Notes

Add internal notes to conversations: - Document context - Note follow-up actions - Tag team members - Link related conversations

Bulk Actions

Select multiple conversations to: - Export in bulk - Tag for categorization - Delete (compliance) - Archive

Search Conversations

Search across all conversations:

Full-text Search - Search message content - Find specific keywords or phrases - Use quotes for exact matches

Advanced Filters - User ID - Agent version - Date range - Message count - Response quality

Conversation Analytics

Aggregate Metrics

  • Total conversations
  • Average messages per conversation
  • Average conversation duration
  • Completion rate
  • Escalation rate
  • User satisfaction score
  • Conversations over time
  • Peak usage hours
  • Common topics
  • Escalation patterns

Privacy & Compliance

Data Retention

  • Conversations stored for 90 days (default)
  • Configurable retention period
  • Automatic deletion after retention period
  • Compliance with GDPR, CCPA

User Privacy

  • PII detection and redaction
  • Anonymous user tracking
  • Right to deletion (on request)
  • Data export on request

Access Control

  • Role-based access to conversations
  • Audit logging of conversation views
  • Secure data transmission (encryption)

Troubleshooting

Conversation Not Showing

Issue: Recent conversation not visible in list

Solution: - Refresh the page - Check date range filter - Verify user has proper permissions - Allow 1-2 minutes for conversation to sync

Cannot Export Conversations

Issue: Export button is grayed out or fails

Solution: - Verify you have export permissions - Check if conversations contain PII (may require admin approval) - Try smaller date range (large exports may timeout) - Contact support if issue persists

Best Practices

Regular Reviews

  • Review conversations weekly
  • Identify patterns and common issues
  • Use insights to improve agent instructions
  • Flag excellent interactions for training

Quality Assurance

  • Sample conversations randomly for QA
  • Check agent adherence to instructions
  • Verify tool usage is appropriate
  • Ensure knowledge base retrieval is accurate

User Feedback

  • Monitor satisfaction ratings
  • Follow up on low-rated conversations
  • Incorporate feedback into agent improvements
  • Thank users for positive feedback