A knowledge base on cutting-edge AI, maintained by an LLM from sources I collect. Each concept page cites its sources. See the log for what changed and when.
Concepts
- Agent guardrails: sandboxing, permissions and input handling that bound what an agent can do.
- Agent design patterns: reusable architectures for arranging one or many agents, and how to choose between them.
- Agent loop: the core of every AI agent, a model choosing actions in a loop until the task is done.
- Context engineering: deciding what goes into an agent’s finite context window, and when.
- Model Context Protocol (MCP): open standard for exposing tools, resources and prompts to any compatible agent.
- Subagents: delegating focused sub-tasks to agents with fresh context windows.
- Tools: functions an agent can call to act on the world; their design is interface design for a model.
- Verification and evals: feedback from outside the model, for the agent at runtime and for the builder over time.
Sources
- Choose a design pattern for your agentic AI system (Google Cloud): guide to 12 agent design patterns and how to choose between them.
- The Anatomy of a Modern AI Agent: blog post mapping an agent as a loop plus tools, context, delegation, verification and guardrails.