AI Agent Prompts

Agent Memory Architecture Planner

Design a practical memory system for an AI agent, including what to retain, how to retrieve it, and when to forget it.

FreeClaudeChatGPT
Best for

AI product teams designing agents that need useful continuity without retaining irrelevant, stale, or sensitive information.

Suitable LLM groups
FrontierReasoning
Download Prompt.md
Prompt
You are an AI agent architect who specializes in memory design, retrieval quality, and privacy-aware retention.

Inputs:
1. Agent purpose: {{agent_purpose}}
2. Typical users and sessions: {{users_and_sessions}}
3. Information the agent encounters: {{information_types}}
4. Available storage and retrieval systems: {{storage_options}}
5. Privacy, retention, and cost constraints: {{constraints}}

Do the following:
1. Classify the information into working, episodic, semantic, and user-preference memory, and explain which information should never be stored.
2. Define the write criteria for each memory type, including confidence thresholds, deduplication rules, expiration periods, and user-consent requirements.
3. Design the retrieval flow: query construction, filters, ranking signals, context budget, and behavior when memories conflict or appear stale.
4. Specify update, correction, deletion, and compaction procedures, including how users can inspect or remove stored information.
5. Produce a memory architecture table, a read/write decision tree, five failure tests, and a phased implementation plan. Clearly label assumptions and unresolved decisions.

How to use

  1. Describe the agent's real tasks and session patterns.
  2. List every data source the agent may read or write.
  3. State retention, privacy, and context-window limits.
  4. Review the proposed memory classes with security and product owners.

Example input

Agent purpose: A customer success copilot for a 40-person B2B analytics company. Users and sessions: 18 account managers, each handling 25-40 accounts across weekly sessions. Information types: call notes, renewal dates, product issues, stakeholder preferences, and health scores. Storage options: PostgreSQL, vector search, and CRM records. Constraints: EU customer data, 12-month retention, users must be able to delete memories, and retrieval must stay under 1,500 tokens per response.

Example output

The plan stores active-turn facts in working memory, dated account events in episodic memory, verified product knowledge in semantic memory, and explicit communication preferences as user memory. It blocks passwords, health data, and unsupported inferences. Account memories expire after 12 months unless renewed by a new event; conflicting renewal dates trigger CRM verification rather than silent overwrite. Retrieval uses account ID and access controls as hard filters, then ranks recency, source authority, and task relevance. The output includes deletion workflows, a 1,500-token packing policy, and tests for cross-account leakage and stale facts.

Customization tips

  • Add jurisdiction-specific retention rules.
  • Specify authoritative sources for facts that may conflict.
  • Include expected memory volume and retrieval latency targets.
  • Name sensitive data types that must be excluded.

Tags

#agent-memory#retrieval-design#context-management#privacy-by-design#ai-architecture

FAQ

What is this prompt for?
It creates a complete policy for how an AI agent writes, retrieves, updates, and deletes different kinds of memory.
How should I customize it?
Provide concrete session patterns, data types, storage systems, retention periods, and privacy obligations so the design reflects your operating environment.
Are there any limitations?
It cannot validate whether a storage vendor meets your legal or security requirements; specialists should review the resulting architecture before implementation.
How is it different from a basic prompt?
It separates memory into distinct classes and defines explicit write, retrieval, conflict, expiration, and deletion rules instead of merely recommending a vector database.
Free

Multi-Agent Workflow Architect

Design a complete multi-agent system architecture for a complex task, including agent roles, handoff logic, failure handling, and human checkpoints.

ClaudeChatGPT
#ai agents#multi-agent systems#workflow design
Free

Agent Retrieval Strategy Designer

Design how an agent finds, verifies, ranks, and cites external knowledge across structured and unstructured sources.

ClaudeChatGPT
#agent-retrieval#rag-design#knowledge-grounding
Free

Multi-Agent Role Designer

Designs a clean division of labor for a multi-agent system, defining each sub-agent's role, boundaries, and handoff protocol so agents don't overlap or conflict.

ClaudeChatGPT
#ai-agents#multi-agent-systems#agent-architecture

Related Skills

Agent Systems & LLM WorkflowsFree

Agent Memory Scope and Retention Architect

Design what an AI agent may remember, for whom, for how long, with which evidence, controls, deletion paths, and privacy boundaries.

ClaudeChatGPT
#agent memory#LLM memory architecture#AI personalization
Agent Systems & LLM WorkflowsFree

Agent Memory and Context Governance Architect

Design agent memory governance with memory types, relevance, consent, retention, editing, deletion, isolation, retrieval, and safety.

ClaudeChatGPT
#agent memory#context governance#LLM architecture
Agent Systems & LLM WorkflowsFree

Agent Prompt & Tool Spec Designer

Designs a complete system prompt and tool specification for an LLM agent from a description of what the agent should do.

ClaudeChatGPTCursor
#llm-agents#prompt-engineering#system-prompt

Related Articles

Article · AI Agents

How do AI agents use tools, memory, and APIs?

Agents use tools and APIs to retrieve data or act in external systems, while memory helps preserve selected context. Both need permission limits and review design.

Jul 9, 20268 min read
Read How do AI agents use tools, memory, and APIs?