Chat Logs display conversations in real time. As new conversations occur, they appear in the list automatically.
Accessing chat logs
Navigate to Monitor → Chat Logs in the left sidebar. You’ll see a searchable, filterable table of all conversations.Filtering conversations
Use the filter bar at the top to narrow down the conversation list:- Initiative — Filter by a specific initiative.
- Agent Type — Show only HCP Product Detailer or Patient Navigator conversations.
- Deployment — Narrow to a specific widget deployment.
- Time Range — Select 7, 30, 60, or 90 days.
- Search — Search within the filtered results by keyword.
Conversation table
The table displays one row per conversation with the following columns:| Column | Description |
|---|---|
| User | The user’s name if available, or Session: for anonymous visitors |
| Last Active | Relative time since the last message (e.g. “2 hours ago”) |
| Deployment | A badge showing which widget deployment the conversation occurred in |
| Messages | The total number of messages exchanged |
| Action | A View Chat button to open the full conversation |
Reviewing a conversation
Click View Chat on any row to open the chat detail panel — a slide-out panel on the right side of the screen showing the full conversation thread. The panel displays:- Message bubbles — User messages and agent responses in a familiar chat layout, clearly distinguished by colour.
- Timestamps — Each message includes the time it was sent.
- Agent info badge — Shows which agent and model powered the responses.
Chat logs link directly to other areas of the platform. For example, adverse events detected in a conversation will include a link back to the relevant chat log entry for full context.
Deep linking
You can link directly to a specific conversation using a URL parameter:Exporting conversations
Click the Export CSV button to download all conversations matching your current filters. The export includes:- Conversation ID
- User identifier
- Deployment name
- Timestamps
- Full message content (user and agent messages)
CSV exports are generated based on your active filters. Apply the filters you need before exporting to ensure the data is relevant and manageable.
Common use cases
Quality assurance
Review conversations where your agent discussed a specific product to ensure response quality and accuracy. Search by product name to find relevant conversations quickly.
Compliance review
Export conversation data for internal compliance audits. Use time range filters to pull data for specific reporting periods.
Knowledge gap identification
Look for conversations where the agent struggled to provide useful responses. These gaps indicate areas where your knowledge base could be strengthened.
Deployment comparison
Filter by deployment to compare conversation patterns across different widget placements. This helps you understand how different audiences interact with your agent.