Presents a GAN-inspired three-agent architecture (planner, generator, evaluator) for long-running application development, demonstrating how separating generation from structured evaluation with sprint contracts dramatically improves quality over single-agent approaches.

A practical breakdown of memory architecture for multi-agent systems — covering four memory categories (working, episodic, procedural, semantic), implementation approaches from file-based context to MCP-backed databases and RAG with pgvector, plus advanced techniques like memory distillation and semantic conflict resolution.

A comprehensive overview of the major design patterns for building AI agents, from single-agent architectures to multi-agent collaboration, with clear diagrams and practical trade-offs for each pattern.

Anthropic's guide to building effective AI agents, covering workflow patterns like prompt chaining, routing, parallelization, and the orchestrator-workers pattern. Emphasizes simplicity and starting with the least complex solution.