Skip to main content
When viewing a conversation in the Admin Chat History, a sidebar provides tools to evaluate, categorize, and manage each thread. These per-thread features help you maintain quality standards and organize conversations effectively.

​
Accessing Conversation Management

  1. Navigate to Chat History in the sidebar
  2. Click on any conversation row to open it
  3. The conversation displays on the left, and the management sidebar on the right
Use the navigation arrows at the top to move between conversations without returning to the list.

​
Manual Evaluation

Manually assess conversation quality using the three evaluation buttons: Click a button to set the evaluation. Click again to clear it (returns to “Not Evaluated”).

​
Evaluation Comments

Add context to your evaluation:
  1. Click the pencil icon next to the evaluation section
  2. Enter your comment explaining the evaluation
  3. Click Save to store the comment
Comments help other reviewers understand why a conversation was rated a certain way and are useful for training and quality improvement.

​
LLM-Based Evaluation

When the Thread Evaluator is enabled, you can trigger automated evaluation:

​
Running an Evaluation

Click Run Evaluation to have the LLM assess the conversation. The system will analyze and score the thread across five dimensions.

​
CX Score Display

After evaluation, you’ll see:
  • CX Score Gauge: A 0-100 score representing overall quality
  • Dimension Breakdown: Visual bars showing scores for each dimension:
    • Resolution Quality
    • Response Accuracy
    • Tone & Empathy
    • Efficiency
    • Customer Effort

​
Review Flags

The LLM evaluation may flag conversations for human review:

​
Improvement Suggestions

If the LLM identifies issues, it provides specific suggestions for how the agent could have responded better. Use these insights to improve agent instructions or knowledge base content.
LLM evaluation is only available when the Thread Evaluator feature is enabled for your agent.

​
Reviewer Assignment

Assign conversations to team members for review or follow-up:
  1. Click the Reviewer dropdown
  2. Select a staff member from the list
  3. The assignment is saved automatically
Use reviewer assignments to:
  • Distribute quality review workload
  • Track who reviewed which conversations
  • Filter conversations by reviewer in the list view

​
Admin Status

Apply custom status labels to track conversation states:
  1. Click the Admin Status dropdown
  2. Select a status from your configured options
  3. The status badge appears with its assigned color
Example statuses:
  • “Under Investigation”
  • “Escalated to Engineering”
  • “Needs Follow-up”
  • “Resolved”
Configure admin statuses in the platform settings to match your workflow.

​
Tags

​
Conversation Tags

Add descriptive tags to categorize conversations:
  1. Click the Tags field
  2. Search for existing tags or type a new one
  3. Select tags to add them
  4. Click the X on any tag to remove it
Tags help you:
  • Categorize conversations by topic
  • Track issue trends
  • Filter conversations in list view

​
Admin Tags

Admin tags work like regular tags but are only visible to staff members:
  1. Click the Admin Tags field
  2. Search and select tags
  3. Admin tags display with color coding
Use admin tags for internal categorization like:
  • “Training Example”
  • “Bug Report”
  • “Feature Request”
  • “VIP Customer”

​
User Feedback Section

If users submitted feedback about the conversation, it appears in this section.

​
Feedback Display

For each feedback entry, you’ll see:
  • Issue Type Badges: Inaccurate, Incomplete, Information Not Found, Technical Issue
  • Additional Feedback: Free-text comments from the user
  • Reaction Count: Thumbs up/down summary

​
Managing Feedback

For each feedback item: Click on a feedback entry to expand it and edit these fields.

​
Conversation Details

The sidebar header shows:
  • Created Date: When the conversation started
  • Thread ID: Unique identifier (useful for support cases)

​
Workflow Example

Here’s a typical workflow for reviewing a flagged conversation:
  1. Open the conversation from the list (filtered by “Needs Review”)
  2. Read the full conversation on the left side
  3. Review the LLM evaluation and CX Score
  4. Set manual evaluation (OK/Neutral/KO) with a comment
  5. Add tags to categorize the issue
  6. Assign reviewer if follow-up is needed
  7. Set status if additional action is required
  8. Use navigation arrows to move to the next conversation

​
Best Practices

  1. Evaluate consistently: Use the same criteria across all reviewers
  2. Add comments: Explain your reasoning, especially for KO ratings
  3. Use tags strategically: Don’t over-tag; focus on meaningful categories
  4. Check LLM suggestions: Use improvement suggestions to improve your agent
  5. Track status: Keep admin status updated as conversations progress
  6. Review feedback promptly: User feedback often reveals important issues

​
Keyboard Shortcuts