> ## Documentation Index
> Fetch the complete documentation index at: https://docs.typewise.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Past conversations

> The AI Agent reads a customer's earlier conversations so they don't repeat themselves

The AI Agent can look up the conversations a customer had with you before. When
a returning customer refers to an earlier request, such as "the order I emailed
you about last week", the AI finds that conversation and continues from there
instead of asking the customer to explain everything again.

## How it works

At the start of a conversation, the AI receives short summaries of a handful of
the customer's most recent conversations, so it knows whether relevant history
exists. The summaries alone are never used to answer. To use information from an
earlier conversation, the AI has to open it first:

* **Search** scans the customer's past messages for a keyword, optionally
  narrowed down by date, channel, or ticket status.
* **Read** loads the messages of one past conversation in full.

Both appear as
[AI lookups](/documentation/tickets/conversation-view/ticket-conversation#ai-lookups)
in the conversation timeline, so you can always see which past conversations the
AI opened and when.

<Info>
  Retrieval never gets in the customer's way. If past conversations are
  temporarily unavailable, the AI continues with what it has in the current
  conversation.
</Info>

## What the AI can see

The AI only reaches conversations that belong to the same customer and the same
workspace. This works across channels: if a customer wrote an email earlier and
now uses the chat, the AI can find the email conversation, as long as both
tickets belong to the same customer record. A customer without an identity, such
as an anonymous chat visitor, has no history to search.

Within a past conversation, the AI sees the messages that were exchanged: the
customer's messages and the replies from the AI or Human Agents. Internal notes,
activity events, attachments, and the AI's own reasoning from the past
conversation are never included.

Some conversations are left out entirely: deleted tickets, spam,
[outbound tickets](/documentation/tickets/compose-outbound), and test
conversations from the
[Simulator](/documentation/testing-and-feedback/simulator).

## Safeguards

* When the AI uses information from an earlier conversation, it says so in its
  reply, so the customer knows where the information comes from.
* Past conversations never replace current, verified data. For sensitive
  actions, the AI collects and verifies the required information in the current
  conversation, for example through
  [Trusted-only context variables](/documentation/settings/context-variables).
* Access is read-only. The AI never changes past tickets.
* The customer scope is enforced by the platform. The AI cannot request another
  customer's or another workspace's conversations.

## Testing in the Playground

You can try the feature in the
[Playground](/documentation/testing-and-feedback/simulator). Start a test
conversation with a real customer's email address, and the AI sees that
customer's history exactly as it would in a live conversation. An address
without previous tickets simply has no history. Playground conversations never
become history themselves, so testing doesn't pollute the customer's record.

In automated [Tests](/documentation/testing-and-feedback/tests), retrieval is
off: test runs never read real customer history.

## Availability

Past conversations are enabled by default and need no setup. Contact us if you
want the feature turned off for your account.