Architecture
The simplest AI-native architecture — a single agent that receives user input, reasons, plans, decides on tool calls, processes results, and generates responses. Direct MCP connection over stdio or HTTP. Best for MVPs and when low latency matters.
User { # User
n1: circle label="Start"
n2: rectangle label="Send request"
n1.handle(right) -> n2.handle(left)
n2.handle(bottom) -> Agent.n3.handle(top) [label="Request"]
}
Agent { # Single AI Agent
n3: rectangle label="Receive input"
n4: rectangle label="Reason and plan"
n5: rectangle label="Decide tool call"
n6: rectangle label="Process tool result"
n7: rectangle label="Generate response"
n8: circle label="Done"
n3.handle(right) -> n4.handle(left)
n4.handle(right) -> n5.handle(left)
n5.handle(bottom) -> Tools.n9.handle(top) [label="MCP request"]
n6.handle(right) -> n7.handle(left)
n7.handle(right) -> n8.handle(left)
n7.handle(top) -> User.n2.handle(bottom) [label="Response"]
loop [retry until goal met] n4 n5 n6 n7
}
Tools { # Tool Server (MCP)
n9: rectangle label="Receive MCP call"
n10: rectangle label="Execute tool"
n11: rectangle label="Return result"
n9.handle(right) -> n10.handle(left)
n10.handle(right) -> n11.handle(left)
n11.handle(top) -> Agent.n6.handle(bottom) [label="Tool result"]
}
Architecture
A single-agent AI architecture where one agent handles everything: parsing requests, reasoning, calling tools via MCP, and generating responses. This is the default architecture for prototypes and simple automations—easy to debug but hits context-window limits quickly and is hard to parallelize. Ideal for MVPs and solo builders shipping fast.
Architecture
An assembly-line architecture where agents are arranged in a strict sequence. Each agent transforms or enriches the output of the previous one, then passes it forward. Best for tasks with clear sequential dependencies — document processing, content production pipelines, compliance workflows.
Architecture
A conductor-style architecture where one orchestrator agent receives a complex task, breaks it into subtasks, dispatches each to specialist worker agents (research, code, review), collects results, and synthesizes the final answer. Best for complex multi-step tasks with dynamic decomposition.
Architecture
An org-chart architecture with multi-level structure. A top-level supervisor manages team leads, who each manage their own pool of specialist workers. Teams within teams. Best for enterprise-scale automation with 10+ specialized agents spanning multiple domains.
Architecture
A map-reduce style architecture where a coordinator fans out tasks to multiple parallel worker agents (style check, security audit, performance analysis), gathers all results, and makes an aggregate decision. Best for PR reviews, code reviews, and multi-dimensional analysis.
Architecture
An event-driven agent mesh architecture using a Kafka-style event broker. Multiple agents subscribe to topics (orders, alerts, analytics), process events independently, and publish results back to the bus. Best for real-time event processing and decoupled service architectures.