#agent-architecture

Moonshot trained Agent Swarm against two failure modes it names itself, serial collapse and fake parallelism. Use them as your own fan-out decision test.

Qwen3.7 Flash listed at $0.03 per million input tokens on its base tier, 1M context and video input — but no published benchmarks. Where it fits in subagents.

OpenAI's GPT-5.6 caching overhaul, plus Anthropic and DeepSeek tiers, reshapes agent cost math. How to design cache-first, model-homogeneous agents.

Build a working Claude Code subagent from .claude/agents/ markdown to first invocation. Tool restrictions, system prompt design, orchestration patterns.

200 agentic AI terms — agents, MCP, memory, planning, evaluation, governance. Examples, source links, cross-references. The reference glossary.

120 MCP terms — server, transport, primitive, sampling, prompt, tool, resource, agent loop, governance. The plain-language MCP reference guide.

ReAct, Reflexion, plan-execute, multi-agent debate, swarm, hierarchy, blackboard, graph-orchestrated patterns. Reference architectures + trade-offs.

Twelve agency workflows as multi-agent graphs — research, brief, draft, audit, review, deploy. Reference architectures + role taxonomy + handoffs.

Build AI agents with memory: short-term, long-term, and episodic memory patterns. Vector stores, conversation management, and production architectures.

Master Cursor 2.0's agent-first architecture. Compare pricing ($20-200/mo), parallel agents, MCP integration, and Cursor vs Windsurf vs Copilot.