History and Preview
Chat History
History holds every conversation the assistant has had, with the full transcript. It is the fastest way to find out what customers actually ask and where the assistant falls short.
The list shows one row per conversation:
| Column | Description |
|---|---|
| Visitor | The visitor, identified as a customer where the storefront knew who they were. |
| Date | When the conversation started. Sortable, newest first by default. |
| Location | The country the visitor connected from. |
| Pages | How many storefront pages the visitor had open during the conversation. |
| Messages | Messages exchanged. |
| Tokens | Tokens the conversation consumed - in effect, what it cost you. |
| Duration | How long the conversation lasted. |
Filters
Conversations can be narrowed by:
- Created from and Created to - a date range.
- Pages at least / at most.
- Messages at least / at most.
- Tokens at least / at most.
- Location - one or more countries.
- Visitor email - the conversations of one visitor, matched by the email eChat has on file for them (signed-in customers always have one). Capital letters do not matter.
The token filters are the useful ones for cost work. Filtering on Tokens at least a high value pulls up the handful of long, expensive conversations, and reading those transcripts usually shows a concrete cause: a question the knowledge base cannot answer, so the assistant keeps searching, or a loop that a Guidance rule should have ended with an escalation. See Costs and billing.
Exporting conversations
Export CSV at the top of History downloads the conversations as a spreadsheet, with one row per message. Choose which conversations by when they started:
- Last 7 days, Last 30 days (default) or Last 90 days.
- Custom range - a From and To date. If the list already has a Created from / Created to filter, the export starts with that range.
The list's other filters and its sort order apply as well, so filtering by Visitor email first exports one visitor's history. The export covers every matching conversation, not only the page on screen.
Each row carries the conversation ID, when it started, the visitor's name and email, their country and city, the message time, the sender type and name, the message text, and the names of the proposed products and attachments. Times are in UTC. The file is named with the export date, for example chat-history-2026-10-06.csv. A message that begins with =, +, - or @ is written with a leading apostrophe, so it is shown as text rather than run as a formula.
One export holds up to 50,000 messages. If the chosen range has more, nothing is downloaded and eChat asks you to narrow the date range.
Chat details
Opening a conversation shows the full transcript, including any files the visitor attached, which can be downloaded.
Download transcript at the top of the page saves the conversation as a plain-text file: when it started and ended, the visitor's name, email and location, then every message with its time and sender, the proposed products with their links, and the names of attached files. It is a quick way to share a conversation with someone who has no access to the eChat backend.
Deleting conversations and visitor data
Two actions at the top of Chat details delete data permanently:
- Delete conversation - the conversation with its messages and attachments. The visitor and their other conversations stay.
- Delete visitor data - the visitor with all their conversations, messages, attachments and browsing history, for example to answer a GDPR erasure request.
To erase a shopper by email instead, or to delete old conversations automatically, see Data & privacy.
Correcting an AI answer
Reading past conversations is where you find the assistant's mistakes, so it is also where you can fix them. Every AI message in Chat details carries a Correct action. Visitor, agent and system messages do not - there is nothing to correct in what the customer said.
Correct opens a form over the conversation, with the customer's own question already filled in. You choose what kind of mistake it was:
- A fact - the assistant said something untrue. Saved as a FAQ entry: a question and the answer it should have given. This is the default, because a wrong answer is almost always a wrong fact.
- How it behaves - the assistant should have acted differently. Saved as a Guidance rule, with the same Name, Trigger, Instructions and Status fields as the Guidance screen.
Switching between the two keeps whatever you have already typed, so changing your mind costs nothing. Save stays unavailable until the fields that matter have text, and Cancel saves nothing.
The marker
Once saved, the message shows what came out of it - FAQ item added or Guidance rule added - with a link to the record in its own editor. The marker is read from the record itself, so it is there after a reload, it is there for your colleagues, and correcting the same message twice leaves two markers rather than replacing the first.
Deleting the record removes its marker, because the marker was only ever the record's shadow.
A correction changes what the assistant says next time. It does not rewrite the conversation the customer already had, and the customer is not notified.
Preview
Preview runs the real chat widget against your real workspace, in the backend, without touching the storefront. It uses your live settings, your live knowledge base, and your live provider chain.
Use it to:
- Check a Guidance rule fires on the phrasing you expect.
- Read how a change to Instructions or Tone of Voice actually sounds.
- Confirm a newly synced product is answerable before customers ask.
- Try a provider or model change before it reaches customers.
Preview conversations are real conversations: they consume tokens on your provider account and they appear in History.