OpenAI's architecture for turning isolated model calls into sustained agent workflows by combining the Responses API with shell tools, persistent containers, and native context compaction.

A comprehensive skill containing 152 prioritized rules across 12 categories for reviewing web interface implementations, from animation principles and timing functions to UX laws and visual design, each with incorrect vs. correct code examples.

Introduces three advanced tool use features — tool search, programmatic tool calling, and tool use examples — that enable Claude agents to dynamically discover, efficiently orchestrate, and accurately invoke tools across large tool libraries while minimizing context token consumption.

A detailed reverse-engineering of Claude Code's agent architecture, revealing how a single-threaded master loop with flat message history, structured tool interfaces, async steering, and TODO-based planning delivers controllable autonomy without multi-agent complexity.

Google's comprehensive whitepaper distinguishing agents from plain models, explaining how tools, orchestration layers, and cognitive architectures combine to create capable AI agents.

OpenAI's practical guide covering the three pillars of agent construction — choosing the right model, defining tools clearly, and writing effective instructions — with actionable advice on guardrails and evaluation.

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.

Lilian Weng's seminal deep-dive into the architecture of LLM-based autonomous agents, covering planning (CoT, ToT, self-reflection), memory systems (sensory, short-term, long-term), and tool use as the three pillars of agent design.