Store and retrieve persistent user memory across conversations.
Agent Memory is an experimental feature that allows your assistant to persist data about users across conversations. This enables experiences like repeat-caller logic, customer preferences, and cross-channel continuity.
It uses a key-value store attached to a user identifier (like phone number). Memory is read at the start of each turn and written after the conversation ends.
You can:
conv.memory.get("key")
conv.state["key"] = value
(if configured via state_keys
)To enable Agent Memory:
analytics_enabled
: Adds repeat caller metrics to Studio analyticsstate_keys
: Keys to save from conv.state
to memoryidentifier_blacklist
: Optional list of excluded IDs (e.g. test numbers)state_keys
in your config.No. Each value must be a string, number, or flat serializable object. Always avoid packing PII into a single field.
Yes:
Not directly, but you can check before writing:
Need help? Contact platform-support@poly-ai.com.
Store and retrieve persistent user memory across conversations.
Agent Memory is an experimental feature that allows your assistant to persist data about users across conversations. This enables experiences like repeat-caller logic, customer preferences, and cross-channel continuity.
It uses a key-value store attached to a user identifier (like phone number). Memory is read at the start of each turn and written after the conversation ends.
You can:
conv.memory.get("key")
conv.state["key"] = value
(if configured via state_keys
)To enable Agent Memory:
analytics_enabled
: Adds repeat caller metrics to Studio analyticsstate_keys
: Keys to save from conv.state
to memoryidentifier_blacklist
: Optional list of excluded IDs (e.g. test numbers)state_keys
in your config.No. Each value must be a string, number, or flat serializable object. Always avoid packing PII into a single field.
Yes:
Not directly, but you can check before writing:
Need help? Contact platform-support@poly-ai.com.