代理构建框架_agent-builder

shallwegzgdj

53人浏览 · 2026-07-01 06:48:47

shallwegzgdj · 2026-07-01 06:48:47 发布

以下为本文档的中文说明

该技能为构建任意领域的AI代理提供设计指导和实现框架，涵盖客户服务、研究、运营、创意工作或专业业务流程。其核心理念是"模型本身就是代理，你的工作是不要挡路"，强调AI代理的本质是简单的循环：模型看到上下文和可用能力，决定执行操作或回应。

使用场景包括：需要从零开始构建AI代理系统时；想了解代理架构、代理模式或自主AI的工作原理时；需要设计能力模块、子代理、规划或技能机制时；想了解Claude Code、Cursor等代理内部机制时；需要为商业、研究、运营或创意任务构建代理时。

核心特点在于：一是提出三个核心要素——能力（代理能做什么）、知识（代理知道什么）和上下文（发生了什么），构建了清晰的代理设计框架；二是渐进式复杂度设计，从基础的3-5个能力开始，根据实际使用需求逐步添加规划、子代理和技能功能；三是强调"信任模型"的理念，反对过度工程化，主张给模型能力和知识后让它自主推理；四是提供丰富的反模式列表，如过度工程化、能力过多、工作流僵化等常见陷阱；五是附带了完整的最小化代理实现参考代码（约80行），让开发者能够快速上手。该技能将复杂的代理开发简化为可操作的步骤和原则。

Agent Builder

Build AI agents for any domain - customer service, research, operations, creative work, or specialized business processes.

The Core Philosophy

The model already knows how to be an agent. Your job is to get out of the way.

An agent is not complex engineering. It’s a simple loop that invites the model to act:

LOOP:
  Model sees: context + available capabilities
  Model decides: act or respond
  If act: execute capability, add result, continue
  If respond: return to user

That’s it. The magic isn’t in the code - it’s in the model. Your code just provides the opportunity.

The Three Elements

1. Capabilities (What can it DO?)

Atomic actions the agent can perform: search, read, create, send, query, modify.

Design principle: Start with 3-5 capabilities. Add more only when the agent consistently fails because a capability is missing.

2. Knowledge (What does it KNOW?)

Domain expertise injected on-demand: policies, workflows, best practices, schemas.

Design principle: Make knowledge available, not mandatory. Load it when relevant, not upfront.

3. Context (What has happened?)

The conversation history - the thread connecting actions into coherent behavior.

Design principle: Context is precious. Isolate noisy subtasks. Truncate verbose outputs. Protect clarity.

Agent Design Thinking

Before building, understand:

Purpose: What should this agent accomplish?
Domain: What world does it operate in? (customer service, research, operations, creative…)
Capabilities: What 3-5 actions are essential?
Knowledge: What expertise does it need access to?
Trust: What decisions can you delegate to the model?

CRITICAL: Trust the model. Don’t over-engineer. Don’t pre-specify workflows. Give it capabilities and let it reason.

Progressive Complexity

Start simple. Add complexity only when real usage reveals the need:

Level	What to add	When to add it
Basic	3-5 capabilities	Always start here
Planning	Progress tracking	Multi-step tasks lose coherence
Subagents	Isolated child agents	Exploration pollutes context
Skills	On-demand knowledge	Domain expertise needed

Most agents never need to go beyond Level 2.

Domain Examples

Business: CRM queries, email, calendar, approvals
Research: Database search, document analysis, citations
Operations: Monitoring, tickets, notifications, escalation
Creative: Asset generation, editing, collaboration, review

The pattern is universal. Only the capabilities change.

Key Principles

The model IS the agent - Code just runs the loop
Capabilities enable - What it CAN do
Knowledge informs - What it KNOWS how to do
Constraints focus - Limits create clarity
Trust liberates - Let the model reason
Iteration reveals - Start minimal, evolve from usage

Anti-Patterns

Pattern	Problem	Solution
Over-engineering	Complexity before need	Start simple
Too many capabilities	Model confusion	3-5 to start
Rigid workflows	Can’t adapt	Let model decide
Front-loaded knowledge	Context bloat	Load on-demand
Micromanagement	Undercuts intelligence	Trust the model

Resources

Philosophy & Theory:

references/agent-philosophy.md - Deep dive into why agents work

Implementation:

references/minimal-agent.py - Complete working agent (~80 lines)
references/tool-templates.py - Capability definitions
references/subagent-pattern.py - Context isolation

Scaffolding:

scripts/init_agent.py - Generate new agent projects

The Agent Mindset

From: “How do I make the system do X?”
To: “How do I enable the model to do X?”

From: “What’s the workflow for this task?”
To: “What capabilities would help accomplish this?”

The best agent code is almost boring. Simple loops. Clear capabilities. Clean context. The magic isn’t in the code.

Give the model capabilities and kn
owledge. Trust it to figure out the rest.
3c:[“ $", "$ L3e”,null,{“content”:“$3f”,“frontMatter”:{“name”:“agent-builder”,“description”:"Design and build AI agents for any domain. Use when users:
(1) ask to \“create an agent\”, \“build an assistant\”, or \“design an AI system\”
(2) want to understand agent architecture, agentic patterns, or autonomous AI
(3) need help with capabilities, subagents, planning, or skill mechanisms
(4) ask about Claude Code, Cursor, or similar agent internals
(5) want to build agents for business, research, creative, or operational tasks
Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
"}}]

40:I[471044,[“/_next/static/chunks/051aanbhrv4br.js”,“/_next/static/chunks/0mizr60h7ayzt.js”,“/_next/static/chunks/0v9lm1dmbdoo-.js”,“/_next/static/chunks/0rxr1j1j3j-.r.js”,“/_next/static/chunks/02ftybezfvqjd.js”,“/_next/static/chunks/0.v9ksvnnj8ia.js”,“/_next/static/chunks/0bn6id9_{6nx3k.js",“/_next/static/chunks/13ybnhn37c.tc.js”,“/_next/static/chunks/0_fnrdtruz8uf.js”,“/_next/static/chunks/0r6l15utt1mwb.js”,“/_next/static/chunks/0dm9a5into854.js”,"/_next/static/chunks/0}7k6hqoibtcn.js”,“/next/static/chunks/0b4cao.4y…j.js”,“/_next/static/chunks/02i-n28z7kjd0.js”],“SkillSidebar”]
3a:[“ $", "$ L40”,null,{“skill”:“$6:3:props:children:props:children:props:children:0:props:children:0:props:skill”,“authorSocial”:{“twitter”:null,“blog”:“shareAI-Lab.com”},“occupationLinks”:[{“slug”:“computer-and-information-research-scientists-151221”,“name”:“计算机与信息研究科学家”,“level”:4,“groupName”:“计算机与数学类职业”,“socCode”:“15-1221”},{“slug”:“software-developers”,“name”:“软件开发工程师”,“level”:4,“groupName”:“计算机与数学类职业”,“socCode”:“15-1252”}]}]

3d:null