customer-intelligence-memory
/customer-intelligence-memory
Design and review customer intelligence, long-term memory, personalization, customer history, profile summarization, retrieval, privacy, retention, deletion, and analytics systems for AI agents. Use when building AI memory over company local data, conversation history, orders, preferences, complaints, segments, customer lifetime value, or personalization that must improve revenue while controlling privacy and hallucination risk.
- Author
- LineLuLan ↗
- Repository
- line-harness ↗
- Licence
- MIT
- Last repository change
- 11.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 11.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Design and review customer intelligence, long-term memory, personalization, customer history, profile summarization, retrieval, privacy, retention, deletion, and analytics systems for AI agents. Use when building AI memory over company local data, conversation history, orders, preferences, complaints, segments, customer lifetime value, or personalization that must improve revenue while controlling privacy and hallucination risk.
Original author description
Design and review customer intelligence, long-term memory, personalization, customer history, profile summarization, retrieval, privacy, retention, deletion, and analytics systems for AI agents. Use when building AI memory over company local data, conversation history, orders, preferences, complaints, segments, customer lifetime value, or personalization that must improve revenue while controlling privacy and hallucination risk.
How it works
- Memory Architecture Flow
- Guardrails
- Output Shape
SKILL.md preview
--- name: customer-intelligence-memory description: Design and review customer intelligence, long-term memory, personalization, customer history, profile summarization, retrieval, privacy, retention, deletion, and analytics systems for AI agents. Use when building AI memory over company local data, conversation history, orders, preferences, complaints, segments, customer lifetime value, or personalization that must improve revenue while controlling privacy and hallucination risk. verified: 2026-08 --- # Customer Intelligence Memory Use this skill to design customer memory that is useful, scoped, and safe. ## Memory Architecture Flow 1. Define jobs-to-be-done: personalization, support continuity, upsell, churn prevention, routing, complaint handling, or customer segmentation. 2. Separate memory types: - Raw events: orders, messages, clicks, tickets, calls. - Derived facts: preferences, allergies, language, location, segment. - Summaries: customer timeline, recent issues, lifecycle state. - Embeddings: searchable snippets or normalized facts. - Decisions: why an offer, route, or recommendation was chosen. 3. Design write policy: what gets stored, who can write, confidence, source, timestamp, TTL, and correction/deletion path. 4. Design read policy: which memories are retrieved for which intents, how many, freshness, source citations, and privacy boundaries. 5. Define evals: memory precision, stale fact rate, harmful recall, personalization lift, cost, and support resolution impact. ## Guardrails - Prefer structured facts plus compact summaries over dumping raw transcripts into prompts. - Store source, timestamp, confidence, and scope for every durable memory. - Distinguish user-stated facts from model-inferred facts. - Do not use sensitive attributes unless explicitly approved and legally valid. - Support deletion, correction, and retention expiry. - Keep memory retrieval intent-scoped to avoid irrelevant or creepy personalization. ## Output Shape ```markdown ## Memory Strategy [What to store, summarize, embed, and retrieve] ## Data Model [Entities, fields, source, confidence, TTL] ## Read/Write Policy [When memory is created and when it is used] ## Evals [Precision, freshness, privacy, revenue/support metrics] ## Risks [Privacy, stale facts, hallucinated facts, over-personalization] ```
Files in this package (2)
- SKILL.md 2 KB
- agents/openai.yaml 1 KB
Versions
The database has no other skills named customer-intelligence-memory.
Database snapshot: 13.11.2026 · package version b0206bbb4881 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100agent-memory-systems
Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions. - 100personalization-rag
User-specific retrieval. Per-user namespaces/filters, preference embeddings, collaborative signals, reranking with user context (role, history, favorites), privacy-preserving design (encrypted metadata, differential privacy), GDPR- compliant personalization, long-term user… - 90conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history. - 98local-twilio-customer-memory-5ad0d85f
Store and retrieve customer context using Twilio Conversation Memory. Covers Memory Store provisioning, profile management, traits, observations, conversation summaries, and semantic Recall. Use this skill to give AI agents or human agents persistent memory of customer… - 90conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history. - 90conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.