Agent Engineering Roadmap – a beginner-friendly guide to building AI agents

A hands-on roadmap for building production-ready AI Agents, MCP Servers, Memory Systems, Multi-Agent Workflows, and Agent Colonies.

繁體中文 · Website · Course · Roadmap · Examples · Showcases · Benchmarks · Labs · Teaching · Templates · Architecture · Healthcare · Finance

flowchart LR
    User((User)) --> Agent[AI Agent]
    Agent --> Tools[Tool Use]
    Tools --> MCP[MCP Layer]
    MCP --> Memory[Memory System]
    Memory --> Workflow[Agent Workflow]
    Workflow --> MultiAgent[Multi-Agent Team]
    MultiAgent --> Colony[Agent Colony]
    Colony --> Production[Production AI App]

Most AI tutorials stop at prompts, RAG, or simple tool calling.

Real agentic products require more than that:

• agents that can use tools safely
• MCP servers that connect agents to real systems
• memory layers that persist useful context
• workflows that are observable and controllable
• multi-agent teams that can specialize and collaborate
• evaluation, security, and production guardrails

This repository is a practical learning path for builders who want to move from chatbot demos to real agent engineering.

This roadmap teaches agents like an engineering course, not a tool catalog.

Each major topic follows the same pattern:

• Start with the problem: what breaks if you only use a chatbot?
• Build the intuition: what is the simplest mental model?
• Open the box: what components are actually involved?
• Run a minimal example: what can you inspect locally?
• Add production judgment: what needs evaluation, observability, approval, or safety gates?

In one sentence: an agent is not magic. It is context, tools, memory, workflow, evaluation, and human judgment arranged around a useful task.

CurriculumVisual AssetsRoadmapExamplesBenchmarksShowcasesDomain CasebooksLabsTeaching LayerLab Solution GuidesLesson PlansStudy Group KitPatternsTemplatesPapersOpen Source ProjectsFramework Selection MatrixOpen Source Reading GuideDeepEval And RAGASRelease ChecklistAssessmentsCapstonePortfolio ProjectsCapstone StarterGlossary

AI Fundamentals
      ↓
Single Agent
      ↓
Tool Use
      ↓
MCP Integration
      ↓
Agent Memory
      ↓
Agent Workflow
      ↓
Multi-Agent Systems
      ↓
Agent Colony
      ↓
Production, Evaluation & Safety

Run a showcase without API keys:

python showcases/enterprise-support-agent/main.py
python showcases/finance-research-agent/main.py
python showcases/healthcare-agent-colony/main.py

Then run the evaluation harness:

python examples/07-evaluation-harness/main.py
python examples/08-mini-rag/main.py
python benchmarks/benchmark_runner.py
python scripts/verify_examples.py

Risk Assessment TemplateDeployment Review TemplateRelease Checklistv1.0 Readiness| Demo | Shows | |---|---| |

Finance Research AgentHealthcare Agent Colony| Example | Shows | No API key | |---|---|---| |

02 Tool-Using Agent03 MCP-style Agent04 Memory Agent05 Multi-Agent Workflow06 Agent Colony07 Evaluation Harness08 Mini RAG09 Graph Approval Agent10 Observable Agent11 Prompt Injection Defense12 Cost-Aware Agent13 Durable Workflow Agent14 Modern MCP Gateway15 Memory Governance Agent16 Agent Permission System17 Advanced Eval HarnessCapstone StarterRun every dependency-free example with:

python scripts/verify_examples.py

This README uses lightweight visual widgets commonly seen in popular GitHub projects:

• Local cover image for the top hero banner shields.io

for stars, forks, language, status, and topic badges- Mermaid for architecture diagrams

Agent Engineering is not only about prompts. A production agent needs a plugin ecosystem around it.

graph TD
    User[User] --> Supervisor[Supervisor Agent]
    Supervisor --> Planner[Planner]
    Planner --> MemoryAgent[Memory Agent]
    Planner --> ResearchAgent[Research Agent]
    Planner --> ToolAgent[Tool Agent]
    Planner --> DomainAgent[Domain Agent]
    MemoryAgent --> SharedMemory[Shared Memory]
    ToolAgent --> MCP[MCP Servers]
    DomainAgent --> MCP
    ResearchAgent --> MCP
    MCP --> PluginLayer[Plugin Ecosystem]
    PluginLayer --> Databases[Databases]
    PluginLayer --> Documents[Documents]
    PluginLayer --> APIs[External APIs]
    PluginLayer --> SaaS[SaaS Apps]
    Supervisor --> Evaluator[Evaluator Agent]
    Evaluator --> Final[Final Response]
    Final --> User
    Evaluator --> SharedMemory
agent-engineering-roadmap/
├── README.md
├── README_zh.md
├── COURSE.md
├── assets/           # Visual diagrams and teaching images
├── roadmap/          # Level 0-8 learning path
├── curriculum/       # Full course chapters
├── examples/         # Hands-on examples
├── benchmarks/       # Lightweight behavior checks
├── security/         # Prompt injection and agent security labs
├── study-groups/     # Cohort and workshop facilitation kit
├── showcases/        # Shareable demos with sample outputs
├── labs/             # Guided exercises
├── lesson-plans/     # Instructor-ready lesson plans
├── patterns/         # Architecture pattern catalog
├── architecture/     # System design patterns
├── templates/        # Reusable agent and MCP templates
├── assessments/      # Quiz bank and rubrics
├── projects/         # Capstone and portfolio projects
├── glossary/         # Agent engineering terms
├── healthcare/       # Healthcare agent engineering track
├── finance/          # Finance and quantitative research track
├── resources/        # Curated learning resources
├── docs/             # GitHub Pages site
└── launch-kit/       # Launch copy, topics, and checklist

Build agent systems for care management, nutrition tracking, personal health memory, and healthcare workflow automation.

Example colony:

Care Manager Agent
├── Nutrition Agent
├── Vital Sign Agent
├── Psychology Agent
├── Medication Agent
├── Memory Agent
└── Safety Evaluator Agent

Build research agents, factor-analysis agents, portfolio agents, risk agents, and trading research workflows.

Example colony:

Research Agent
├── Market Data Agent
├── Factor Analysis Agent
├── Portfolio Agent
├── Risk Agent
└── Report Agent

Build customer support agents, internal knowledge agents, document agents, workflow automation agents, and evaluation pipelines.

• Agents should be useful before they are autonomous.

• Memory should be intentional, auditable, and safe.

• MCP should be treated as an integration layer, not just a plugin mechanism.

• Multi-agent systems should reduce complexity for users, not create complexity for developers.

• Production agents need evaluation, observability, cost control, and human approval gates.

• Initialize bilingual repository structure

• Add Level 0-8 roadmap skeleton

• Add architecture documents

• Add healthcare and finance tracks

• Add README badges and hero banner

• Expand each roadmap level into handbook chapters

• Add minimal runnable examples

• Add MCP server templates

• Add memory system examples

• Add agent colony demo

• Add evaluation and safety templates

• Add full course syllabus

• Add observable agent and prompt injection defense examples

• Add benchmark runner and study group kit

• Add cost, durable runtime, and modern MCP gateway modules

• Add memory governance, identity permission, and incident response modules

• Add advanced eval, product UX, and enterprise operating model modules

• Add guided labs

• Add instructor-ready lesson plans

• Add pattern catalog

• Add quiz bank, rubrics, glossary, and capstone

• Add full healthcare agent colony application

• Add full finance research agent application

• AI engineers

• LLM application developers

• Startup builders

• Researchers building agent systems

• Product teams moving from chatbot demos to real workflows

• Developers interested in MCP, memory, and multi-agent systems

This project is licensed under the MIT License.