Learning Paths¶

Not everyone needs to read everything. These four paths give you a clear, sequenced route through the site based on your role and goals.

Difficulty Levels¶

Every page on this site carries a difficulty badge in its tags. Here is what each level means:

Badge	Who It Is For
Beginner	No prior AI knowledge required. Plain-English explanations, minimal code.
Intermediate	Assumes you understand software development. Includes architecture concepts and some code.
Advanced	Assumes familiarity with AI/ML concepts. Deep technical content with implementation detail.
Expert	For architects and specialists. Production trade-offs, research references, design decisions.

Path 1 — Non-Technical / Business¶

For: Business analysts, product managers, operations leads, executives

Goal: Build enough AI vocabulary to participate in strategic decisions and evaluate AI proposals critically.

Estimated time: 4–6 hours

flowchart LR
    A["AI 101\n(Beginner)"] --> B["Glossary\n(Beginner)"]
    B --> C["Enterprise\nPatterns\n(Intermediate)"]
    C --> D["Tools &\nFrameworks\n(Intermediate)"]
    D --> E["Safety &\nResponsible AI\n(Intermediate)"]

    style A fill:#0d9488,stroke:#0b7a72,color:#fff
    style B fill:#0d9488,stroke:#0b7a72,color:#fff
    style C fill:#0284c7,stroke:#0270a8,color:#fff
    style D fill:#0284c7,stroke:#0270a8,color:#fff
    style E fill:#0284c7,stroke:#0270a8,color:#fff

Step	Page	Why
1	AI 101	Foundation — what AI, LLMs, and agents actually are
2	Glossary	Build your vocabulary — refer back here whenever you hit an unknown term
3	Enterprise Patterns	How organizations deploy AI at scale, governance, and risk
4	Tools & Frameworks	What the engineering team is building with
5	Safety & Responsible AI	Risks, bias, compliance, and responsible deployment

Path 2 — Developer (New to AI)¶

For: Software engineers who understand coding but are new to AI/ML concepts

Goal: Go from zero to building production-ready RAG systems and understanding how agents work.

Estimated time: 15–20 hours

flowchart LR
    A["AI 101\n(Beginner)"] --> B["Foundation &\nModels\n(Intermediate)"]
    B --> C["RAG\nFundamentals\n(Intermediate)"]
    C --> D["Embeddings\n(Intermediate)"]
    D --> E["Chunking\nStrategies\n(Intermediate)"]
    E --> F["Vector\nDatabases\n(Intermediate)"]
    F --> G["AI Agents\n(Intermediate)"]
    G --> H["Design\nPatterns\n(Intermediate)"]
    H --> I["AI Dev Tools\n(Beginner)"]

    style A fill:#0d9488,stroke:#0b7a72,color:#fff
    style B fill:#0d9488,stroke:#0b7a72,color:#fff
    style C fill:#0284c7,stroke:#0270a8,color:#fff
    style D fill:#0284c7,stroke:#0270a8,color:#fff
    style E fill:#0284c7,stroke:#0270a8,color:#fff
    style F fill:#0284c7,stroke:#0270a8,color:#fff
    style G fill:#0284c7,stroke:#0270a8,color:#fff
    style H fill:#0284c7,stroke:#0270a8,color:#fff
    style I fill:#0d9488,stroke:#0b7a72,color:#fff

Step	Page	Why
1	AI 101	Orientation
2	Foundation & Models	How LLMs work, tokens, context windows, model selection
3	RAG Fundamentals	The most important pattern for enterprise AI
4	Embeddings	The data representation underpinning RAG
5	Chunking Strategies	The most common source of RAG quality issues
6	Vector Databases	Where embeddings live and how to query them
7	AI Agents	Moving beyond RAG to autonomous systems
8	Agentic AI	Patterns for production agent systems
9	Design Patterns	Architectural patterns for agent implementations
10	AI Developer Tools	GitHub Copilot, Claude Code, MCP — your daily toolkit

Path 3 — Experienced Engineer (Production Focus)¶

For: Engineers who already know LLMs and want production-ready skills — evaluation, advanced RAG, developer tooling, and observability.

Estimated time: 8–10 hours

flowchart LR
    A["Agentic AI\n(Intermediate)"] --> B["GraphRAG\n(Advanced)"]
    B --> C["RAG\nEvaluation\n(Advanced)"]
    C --> D["Design\nPatterns\n(Intermediate)"]
    D --> E["Claude Code\nSkills\n(Intermediate)"]
    E --> F["MCP\n(Advanced)"]
    F --> G["Infrastructure\n& Ops\n(Advanced)"]

    style A fill:#0284c7,stroke:#0270a8,color:#fff
    style B fill:#d97706,stroke:#b86005,color:#fff
    style C fill:#d97706,stroke:#b86005,color:#fff
    style D fill:#0284c7,stroke:#0270a8,color:#fff
    style E fill:#0284c7,stroke:#0270a8,color:#fff
    style F fill:#d97706,stroke:#b86005,color:#fff
    style G fill:#d97706,stroke:#b86005,color:#fff

Step	Page	Why
1	Agentic AI	Refresh on production agent patterns
2	GraphRAG	When standard RAG isn't enough
3	RAG Evaluation	RAGAS metrics and golden datasets
4	Design Patterns	Orchestration, reflection, tool use patterns
5	Claude Code Skills & Agents	Subagents, hooks, custom skills
6	MCP	Extend any AI host with custom tools
7	Infrastructure & Operations	Observability, cost, scaling, MLOps

Path 4 — AI Architect / Lead¶

For: Solution architects, tech leads, and senior engineers designing AI systems end to end.

Goal: Full coverage — concepts, RAG depth, patterns, safety, observability, and developer tooling.

Estimated time: 30+ hours, self-paced

flowchart TD
    A["All Concepts\n8 pages"] --> B["All RAG &\nKnowledge Systems\n6 pages"]
    B --> C["All Patterns\n4 pages"]
    C --> D["Safety &\nResponsible AI"]
    D --> E["Infrastructure\n& Operations"]
    E --> F["All AI Dev Tools\n5 pages"]

    style A fill:#0d9488,stroke:#0b7a72,color:#fff
    style B fill:#0284c7,stroke:#0270a8,color:#fff
    style C fill:#0284c7,stroke:#0270a8,color:#fff
    style D fill:#dc2626,stroke:#b91c1c,color:#fff
    style E fill:#d97706,stroke:#b86005,color:#fff
    style F fill:#16a34a,stroke:#15803d,color:#fff

Next Steps¶

If you are new: AI 101
If you are ready to build: RAG Fundamentals
If you want your daily tools first: AI Developer Tools