Architecture terms
The reasoning patterns and loops that make an agent work.
- 🏗️ArchitectureAgentic loop
The core control flow of an agent: observe → reason → act → observe, repeated until the goal is met or a stop condition fires.
- 🏗️ArchitectureChain of thought
A prompting technique that asks the model to lay out its reasoning step-by-step before committing to an answer — improves accuracy on multi-step tasks.
- 🏗️ArchitectureFrontier model
The current generation of state-of-the-art LLMs — typically the largest models from OpenAI, Anthropic, Google, and a small number of others.
- 🏗️ArchitecturePlanning
The phase where an agent decomposes a goal into a structured sequence of sub-tasks before executing any of them.
- 🏗️ArchitectureReasoning model
A class of LLM (o3, Claude Sonnet 4.6, Gemini 2.5 reasoning) that produces a long internal chain of thought before responding — trading latency for accuracy on hard problems.