Agent Architecture and Control Loops
Explore the architecture of AI agents by understanding how models, tools, and instructions work together within control loops. Learn how agents perceive, recall, reason, act, and store information to create autonomous systems. This lesson covers memory types and orchestration strategies essential for both single-agent and multi-agent designs, preparing you to build flexible and continuous AI systems.
Modern agentic systems are not monolithic programs. They are composed of modular, configurable components that work together to perceive, reason, and act. At the core of this architecture are three foundational elements: model, tools, and instructions.
The model
The model serves as the cognitive core of the agent. It is responsible for reasoning, planning, and generating decisions. In modern agentic systems, this is typically a large language model.
Model selection depends on:
Task complexity: Some tasks are straightforward, such as extracting values from text or generating summaries. For these, smaller models such as Mistral or Gemma may be sufficient. More complex tasks that require planning, judgment, or creativity tend to benefit from more capable models like GPT-4 or Claude Opus.
Latency requirements: In scenarios where users expect fast responses, such as live chats or interactive tools, we choose models that are optimized for low-latency performance. This helps maintain a smooth user experience.
Cost constraints: Running large models repeatedly can be expensive. When building agents that handle frequent requests, we consider cost per query, and may opt for more efficient models when possible. In some designs, we mix models by using smaller ones for routine steps and calling larger models only when needed.
Context window size: Agents that need to handle long conversations or documents require models that support extended context windows. Models like Claude 3 Sonnet and Gemini 1.5 are designed for these situations, and help the agent retain more relevant information. ...