Conversation Memory

Dieser Inhalt ist noch nicht in deiner Sprache verfügbar.

Conversation Memory

v1.7.0

Conversation Memory lets your AI assistant remember durable facts about each verified customer — their name, preferences, recurring issues, purchases, and feedback — so future conversations feel personal instead of starting from scratch.

How extraction works

When a conversation is resolved (closed by an agent or admin), Clienta.ai runs a durable background job that:

Generates a short AI summary of the conversation.
Extracts structured facts using a fast, low-cost language model.
Stores the facts, linked to the verified contact.

Extraction is non-blocking — resolving a conversation is instant; the memory work happens asynchronously and never delays your agents.

What gets remembered

Each fact has a category and a short key:

Category	Examples
`personal`	Name, timezone
`preference`	Preferred language, contact channel
`issue`	Recurring problem (“billing via PromptPay”)
`purchase`	Product or plan owned
`feedback`	Stated likes / dislikes

Sensitive data is filtered out — payment card numbers, government IDs, and similar patterns are discarded before anything is stored. Facts below a confidence threshold are also dropped.

How the AI uses memories

On a returning conversation with a verified customer, the AI is given a compact, read-only customer context block (capped to a small token budget). It references this data to personalize greetings and responses — for example, addressing the customer by name or recalling a prior issue.

Retention policy

Memories expire automatically. Each organization sets a retention period (default 365 days) under Settings → AI Settings. A daily cleanup job hard-deletes any memory past its expiry.

Re-extracted facts upsert by (contact, category, key) — the newest value always wins.
Withdrawing consent immediately wipes all of that contact’s memories.

See Privacy & Compliance for export, erasure, and consent controls.