Guides

Agent Engineering Guides

Evergreen explanations for agent memory, agentic RAG, MCP servers, evaluation, and architecture patterns.

Last updated: 2026-05-11

AI Agent Memory Explained

Agent memory is the product-facing layer that controls what an agent remembers across interactions.

Last updated: 2026-05-11

Short-term memory keeps the current run coherent; long-term memory changes future runs.

Last updated: 2026-05-11

Agentic RAG lets an agent plan and refine retrieval instead of accepting one static context bundle.

Last updated: 2026-05-11

An MCP server exposes tools and context to agents through a common protocol boundary.

Last updated: 2026-05-11

Agent evaluation should cover traces, tool calls, retrieved evidence, final outcomes, cost, and latency.

Last updated: 2026-05-11

Agent architecture is about boundaries: tools, state, retrieval, memory, evals, and human review.