What actually separates an Agent from a Chatbot?

A Chatbot only talks — single turn, fixed flow. An Agent acts — multi-step planning, autonomous decisions. Tell a Chatbot "analyze this company's financials" and it lists the steps; tell an Agent the same and it searches the filings → extracts metrics → benchmarks against the industry → writes the report. Three things together make it an Agent: callable tools (search, code exec, DB, API) + task decomposition + short-term and long-term memory.

What's the difference between tool_choice="auto" and a manual choice in OpenAI Function Calling?

`tool_choice="auto"` lets the model decide "do I need a tool, and which one"; you can pass `{"type": "function", "function": {"name": "search_web"}}` to force a specific call. The chapter demo uses auto + gpt-5 + a single search_web tool (param: query) — given "what's the weather today?", the model decides on its own to fetch from the web. That's Agent decision-making in its smallest form. In production, high-risk steps (like committing code) skip auto — manual dispatch or human approval instead.

What goes into Agent short-term vs long-term memory?

Short-term memory = current conversation context (recent turns, tools just called, key results). Long-term memory = persistent knowledge and preferences (user's past questions, enterprise knowledge base, preferred output format). Short-term lives in an in-memory list or ConversationBufferMemory; long-term usually sits in a vector store + key-value store. The classic beginner mistake: cramming everything into short-term — context fills up, lost-in-middle kicks in, and important info gets forgotten.

How does an Agent decompose "analyze a company's finances" into executable steps?

Through planning. Given "analyze this company's finances," the Agent internally decomposes into: (1) search filings; (2) extract key metrics (revenue, margin, debt ratio); (3) benchmark against industry averages; (4) write the report. Each step maps to a tool call + result writeback. Planning quality depends on whether the system prompt provides examples, the tool list is clear, and the model is asked to output a plan before executing — ReAct (Reasoning + Acting interleaved) is the standard pattern.

What capabilities does a research assistant Agent need at minimum?

Three things: (1) web search (search_web tool, param: query); (2) document reading and analysis (fetch_url or read_pdf, plus OCR/chunking); (3) report generation (structured output, ideally section-by-section). Underneath: a Function Calling loop — model picks the next tool → executes → feeds result back → continues until the report is done. For production, add: max_steps (kill infinite loops), timeout, mandatory citations (every claim tied to a source). That's the gap between practice toy and shippable agent.

AI Agent Development Basics

学AI来匠人

📖

AI Engineer

50 chapters

·Introduction

01 基础与模型5

01
LLM API 入门
30分钟
02
AI 模型对比参考
20分钟
03
机器学习 / 深度学习基础速通
30分钟
04
Transformer 与注意力机制入门
30分钟
05
Prompt Engineering
45分钟

02 上下文与 RAG6

06
Context Fundamentals
30分钟
07
RAG 系统入门
60分钟
08
🔒LangChain 框架
60分钟
09
Context Engineering & Memory
35分钟
10
Context Compression & Optimization
35分钟
11
Context Degradation Patterns
30分钟

03 工具与能力5

12
Function Calling & Tool Use
35分钟
13
Tool Design Principles
35分钟
14
多模态与工具链
40分钟
47
Claude API 进阶 Tool Use：三招降本提准
40分钟
48
MCP 的 Code Execution 模式：把工具当代码库调用
25分钟

04 智能体构建8

15
🔒AI Agent 开发基础
90分钟
16
System Prompt 设计实战
45分钟
17
System Prompt 案例库
30分钟
18
Agent 框架速览
40分钟
19
Agent 框架横向对比
45分钟
20
Multi-Agent Patterns
35分钟
21
Agent 深入
45分钟
49
长任务 Agent 的 Harness 设计模式
25分钟

05 评测与工程化5

22
Evaluation & Quality Monitoring
45分钟
23
LLM-as-a-Judge 评测
35分钟
24
Synthetic Data & Augmentation
30分钟
25
LLM 工程化与网关
35分钟
26
工作流与自动化
40分钟

06 安全与部署6

27
安全与威胁建模
35分钟
28
Data Governance & Privacy
30分钟
29
部署与成本优化
35分钟
30
🔒生产环境部署
90分钟
31
Debugging & Incident Playbook
35分钟
50
Claude Code 沙箱安全机制：双层隔离
25分钟

07 AI Coding & 进阶实战13

32
AI Coding 工作流
40分钟
33
Vibe Coding 实战
45分钟
34
AI Rules 配置实战
30分钟
35
🔒MCP 开发最佳实践
45分钟
36
🔒MCP 发布指南
25分钟
37
Skills 范式：从 Agent 到技能库
35分钟
38
Claude Code 技术原理：上下文与记忆管理
45分钟
39
Claude Code Examples
30分钟
40
AI 产品与体验
35分钟
41
🔒AI 规则持续改进
30分钟
42
PR Review 方法论
20分钟
43
代码分析选项
15分钟
44
GitHub Issue 分析
15分钟

08 模型层：微调与开源部署2

45
LoRA / QLoRA / PEFT 微调原理与取舍
35分钟
46
开源模型、本地部署与模型路由
30分钟

Resources

🗺️ Learning Roadmap
📚 Wiki Docs
📋 Cheat Sheets

Home/Learn/AI Engineer/AI Agent Development Basics

🎯Learn More Efficiently

Keep your learning uninterrupted

✏️
Study Notes
Take notes while learning, synced to cloud
📈
Progress Tracking
Auto-save, resume anytime
🏅
Completion Certificate
Shareable learning achievement
💬
Community Q&A
Connect with 2000+ learners

Sign Up Free→Already have an account? Sign in

👥2,847 learners active

AI学习面试课程学习中心