Memory Poisoning: Why Stored Context Needs Review
Memory poisoning is what happens when incorrect or malicious content enters memory and later influences an agent. Governance and provenance reduce the risk.
securitygovernance
Read postBlogNotes from
Notes from
the Stash
Product thinking on governed AI memory, agent workflows, and the systems that connect them.
What an MCP Memory Server Does
An MCP memory server exposes memory operations as tools that compatible AI clients can call. Here is what that means for an agent workflow.
MCPintegrations
Read postWhy AI Memory Needs Governance
Storing context is easy. Knowing whether it is still true is not. Governance is what keeps stale and conflicting knowledge from influencing an agent.
governanceconcepts
Read postRAG vs Persistent Memory: What's the Difference?
RAG supplies context for a single response. Persistent memory retains knowledge across sessions. They are complementary, not interchangeable.
RAGconcepts
Read postWhat Is Agent Memory? A Practical Guide
Agent memory is the stored context an AI agent can save and retrieve across a workflow. Here is what it includes, why it matters, and where it breaks down.
agent memoryconcepts
Read post