What are memories?
They are structured records (information, texts, parts of answers) that you save and Tess can always consult while you’re working on the platform.
In Chat, you link the conversation to Memory Collections, which store, for example:
profile data (company, segment, plan)
user or account preferences
history that’s relevant for future interactions
important notes about specific projects and cases
These memories can be used in new conversations, without the user having to repeat everything all the time. You can turn any Memory Collection on or off whenever you want.
Why is it important?
Real personalization: Tess responds taking the history (the memory) into account, not just the current message.
Less repetition: The user doesn’t need to provide the same data every time they get support.
Context for the team: Organized memories help both the AI and the human team keep the same level of support, even when agents are switched.
Setting Up and Managing Memories
Open the Chat screen
Find the Memory Collections icon (atom) – top right corner
Select an existing collection or create a new one, according to your needs
Create memories and a collection
Remember to activate the collection; a number will appear on the atom symbol and active collections are shown in color
In the atom icon, you can:
Enable or disable memory collections
Create new collections segmented by use case
Review, edit, or remove existing memories
After you have some collection activated, you can start the conversation normally with the chat. Watch whether the LLM is using the memory information to complement the answers (when it makes sense).
Best practices
Clearly define what kind of information can become memory – and what should never be saved (for example, sensitive data, passwords, information that violates privacy or compliance policies).
Use different collections for different contexts (one for support, another for sales, another for internal projects).
Periodically review memories and collections to remove anything outdated or irrelevant, keeping only what really helps with personalization and service quality.
