AI Agent Knowledge Library

Architect

Architecture, communication, orchestration, and context design for robust AI agent systems.

31 Published resources

Explore: Agent Architectures Context Architecture Protocols & Interoperability Workflow & Orchestration

Knowledge library

More resources — Page 3

31 published articles

A2A agent discovery where Agent A reads Agent Cards for research, finance, and contract agents and selects the appropriate contract agent.

Explainer Intermediate

A2A Agent Discovery and Agent Cards

Learn how A2A clients discover remote agents, read Agent Cards, match skills and interfaces, evaluate suitability, and begin an interaction.

Agents A, B, and C perform controlled reads and writes to a shared state and context store that an orchestrator uses to coordinate work.

Explainer Intermediate

Shared State and Context in Multi-Agent Systems

Learn how multi-agent systems separate local context from shared workflow state, exchange artifacts, synchronize updates, persist checkpoints, and avoid state conflicts.

A side-by-side comparison showing a sequential research-analysis-writing-review pipeline and parallel market-data-risk agents feeding an aggregator.

Comparison Intermediate

Sequential vs Parallel Agent Execution

Compare sequential, parallel, and hybrid agent execution by dependencies, latency, cost, state transfer, synchronization, aggregation, and failure handling.

A multi-agent system hub connected to supervisor-worker, orchestrator-specialist, router-selected-agent, parallel-agent aggregation, and peer-to-peer coordination patterns.

Explainer Intermediate

Multi-Agent Coordination Patterns Explained

Learn seven practical multi-agent coordination patterns and how they manage roles, ownership, state, handoffs, aggregation, conflicts, and stopping.

A side-by-side comparison of a centralized architecture where four agents connect through a supervisor and a decentralized architecture where four peer agents coordinate directly.

Comparison Intermediate

Centralized vs Decentralized Multi-Agent Architectures

Compare centralized, decentralized, and hybrid multi-agent architectures across control, state, coordination, scale, observability, governance, and resilience.

A user request enters an agent router that can select a research agent, coding agent, data agent, or general agent.

Explainer Intermediate

Agent Routing Patterns: How Agents Choose the Next Worker

Learn seven agent-routing patterns, from deterministic rules and classifiers to semantic, capability-aware, hierarchical, and fallback routing.

Three side-by-side architectures showing an orchestrator controlling workflow tasks, a supervisor managing worker agents, and a router choosing among destinations.

Comparison Intermediate

Orchestrator vs Supervisor vs Router in Multi-Agent Systems

Compare orchestrators, supervisor agents, and routers by purpose, decision ownership, state responsibility, delegation, routing, and workflow control.

A complete AI agent architecture showing a user goal entering an agent core with instructions, context, state, and memory before reasoning, action selection, tool use, observation, state update, repetition, or finish.

Explainer Beginner

AI Agent Architecture: Components and Data Flow

Understand modern AI-agent architecture from goals and instructions through reasoning, tools, observations, state updates, guardrails, and stopping.

An orchestrated agent workflow where input enters an orchestrator that coordinates retrieval and analysis agents, a tool or API step, human approval, aggregation, and output.

Explainer Beginner

Agent Workflows and Orchestration Explained

Learn how agent workflows and orchestration coordinate steps, dependencies, branches, parallel work, retries, checkpoints, tools, agents, and humans.

A delegation architecture where a primary agent assigns bounded research, data, and writing tasks to specialist sub-agents before validating and combining their results.

Explainer Intermediate

Agent Handoffs, Delegation, and Sub-Agents

Learn how delegation, handoffs, and sub-agents divide work while preserving task ownership, context, state, permissions, and reliable result contracts.