Review chat conversations
Chat conversations stores every exchange with full context. It is the only place where you see the questions your customers actually ask, in their own words.
Finding a conversation
The search box matches message text, bot responses, and session IDs. Combine it with the filters:
| Filter | Use it to |
|---|---|
| Type | Separate normal chats from canned answers, smart answers, category matches, follow-ups, and errors |
| Language | Check the quality of one language at a time |
| Device | Compare desktop, tablet, and mobile behaviour |
| Sort by | Newest or oldest first |
Use Columns to show or hide fields, and Clear to reset everything.
Reading a single conversation
Click View details to open the full record:
- User message and LLM response — the exchange itself
- Product search — which products were considered and shown
- Model / Tokens — which model answered and how much it cost
- Visitor info — device, language, and the page the visitor was on
- Response payload — the raw response, useful when something failed
The page URL matters more than people expect. The same question from a category page and from a product page should not get the same answer.
Marking what matters
- Star a conversation you want to come back to
- Add a Note explaining what went wrong — missing product data, wrong price, unclear policy, tone
- Notes are shared with everyone who has access, so write them for a colleague
Conversations started from a dashboard preview carry an [admin preview] note automatically, so your own testing is easy to exclude.
A weekly review routine
Thirty minutes, once a week:
- Filter on Type: error and check nothing systematic is failing
- Search for questions that produced no product suggestions
- Read ten conversations end to end, chosen at random, not cherry-picked
- Note the single most common underlying cause
- Fix that cause at the source: a product description, a category, a canned response, a field in Site info
- Star three conversations as your before-and-after benchmark
Resist the urge to fix wording. A better sentence in one response rarely changes the number; better product data always does.
Housekeeping
Select conversations and use Delete Selected to remove them. Select All applies to the current page of results.
Deletion is permanent. Export or note what you need first, and remember that deleting conversations does not reduce the message count already billed for the period.
Privacy
Visitors sometimes type personal details into a chat. Treat this screen as personal data:
- Give reporting-only colleagues the Viewer role rather than full access
- Delete conversations you no longer need
- Do not paste transcripts into external tools
Related
Related articles
Analytics and optimization
Read the Mikabot dashboard and turn its numbers into concrete changes.
Account setup
Create your Mikabot account, verify your email, and find your way around the dashboard.
AI responses explained
The difference between canned and smart responses, and how the bot decides which to use.
Contact us
Our support team is ready to give you fast, personal help when you need it.