Chat management
The Chats section gives you visibility into customer conversations so you can review what the AI said, spot problems, and find recurring questions your store content doesn't yet answer.
Accessing Chat Transcripts
- From your ShopGuide dashboard, click Chats
- Browse the conversation list
- Use search and badge filters to narrow it down
- Click any conversation to view the full transcript
Conversation List View
Each conversation shows the customer identifier (or anonymous ID), start time, the page context, and badges for any notable tool calls (Discount, Guided Search, Web Search, and similar special actions — routine tools like basic product search aren't badged).
Transcript Features
Full Conversation View
Opening a transcript shows the complete message timeline with timestamps, the customer's context (page, product, order info if available), and the detected intent(s) for the conversation (from ShopGuide's 12-intent router: product search, comparison, guided discovery, order management, support, checkout, and more).
Search and Filtering
- Keyword search: Search message content
- Badge filters: Filter by tool used (e.g. Discount, Web Search), by ⭐ starred conversations, or by your own 👍/👎 rating on an AI response
- Date range: Filter by time period
Starring & Rating
You can star a transcript to flag it for follow-up, and leave a 👍 or 👎 rating directly on an AI response (a 👎 requires a short note on what went wrong). This is your own internal quality review — it does not collect a satisfaction score from the customer.
Knowledge Gaps
The Knowledge gaps tab surfaces issues ShopGuide's background detector found across conversations — things the AI couldn't fully resolve. Each row is categorized:
| Category | Meaning |
|---|---|
| Knowledge gap | Your store is missing documented info (packaging, materials, sizing, shipping, policy) |
| Bug | A customer reported something broken (add-to-cart, checkout, pricing) |
| Live data | The AI needed real-time data it has no tool for (exact delivery date, live stock) |
| System error | The chat app itself malfunctioned |
| Other | A real need outside the above (wholesale, partnerships, careers) |
Recurring rephrasings of the same underlying question are stacked into a single row with an occurrence count, rather than listed separately, so you can see what actually needs attention.
Next Steps
Leverage your chat data effectively:
- Set up an A/B test informed by what you see in transcripts
- Adjust AI behavior in Settings to close knowledge gaps
- Review chat analytics
Regular transcript review helps you understand your customers and catch issues early.