# Machine Learning Certification Hub

> Independent, open-source study guides, practice quizzes, infographics, decks, videos and podcasts on vendor-neutral AI foundations and on Google Cloud and Anthropic Claude agentic AI products.

Independent study notes. Not affiliated with or endorsed by Google or Anthropic. Product and certification names are trademarks of their owners. Quiz questions are original practice material, not exam questions.

Every study guide is published as an interactive HTML page; full plain-text guide content is in llms-full.txt. Practice quizzes run at `quiz.html?topic=<slug>`. Content is grouped as Foundation (vendor-neutral, by track), Google and Anthropic.

- Site: https://mbettan.github.io/machine-learning-cert/
- Author: Michaël Bettan (https://www.linkedin.com/in/mbettan/ · https://github.com/mbettan)
- License: Apache-2.0 (https://github.com/mbettan/machine-learning-cert/blob/main/LICENSE)
- Full text of all guides: https://mbettan.github.io/machine-learning-cert/llms-full.txt

## Foundation: AI Fundamentals

- [ML 101](https://mbettan.github.io/machine-learning-cert/ML101.html): ML fundamentals: problem types, data prep and leakage, over/underfitting, evaluation metrics, serving and monitoring, neural networks. — Practice quiz: [quiz.html?topic=ml101](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=ml101) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (supporting)
- [Generative AI 101](https://mbettan.github.io/machine-learning-cert/GenAI101.html): GenAI 101 v3.0: Sparse MoE, LLM vs. SLM & MaaS vs. VPC selection, System 2 reasoning (thinking_level & Adaptive Thinking), L0–L4 agents & 5-Layer Protocol Stack. — Practice quiz: [quiz.html?topic=genai101](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=genai101) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (supporting)
- [Prompt Engineering](https://mbettan.github.io/machine-learning-cert/PromptEngineering.html): Explicit criteria & false-positive control, contrast few-shot pairs, Adaptive Thinking & effort, strict JSON schemas & tool_choice, validation-retry loops, batch SLAs & multi-pass review. — Practice quiz: [quiz.html?topic=prompt-engineering](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=prompt-engineering) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (core)

## Foundation: Agent Architecture & Protocols

- [Agentic Design Patterns](https://mbettan.github.io/machine-learning-cert/ADP.html): Core agent patterns: prompt chaining, routing, parallelization, reflection, tool use, planning, multi-agent orchestration and human-in-the-loop. — Practice quiz: [quiz.html?topic=adp](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=adp) · Exam relevance: Google Professional Agentic Architect (core), Claude Certified Architect – Foundations (core)
- [Context Engineering & Reliability](https://mbettan.github.io/machine-learning-cert/ContextEngineering.html): Context budgets, sliding-window trimming, compaction, tool-result clearing, scratchpads, just-in-time retrieval, sessions vs. memory and subagent context isolation. — Practice quiz: [quiz.html?topic=context-engineering](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=context-engineering) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (core)
- [Agent Development Kit (ADK)](https://mbettan.github.io/machine-learning-cert/ADK.html): Multi-language agent framework (Python, TS, Go, Java, Kotlin): LlmAgent, ManagedAgent (Interactions API), ADK 2.0 Workflows, Gemini 4 Argon routing, MCP/A2A, Skills, eval, and Agent Runtime. — Practice quiz: [quiz.html?topic=adk](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=adk) · Exam relevance: Google Professional Agentic Architect (core)
- [Model Context Protocol (MCP)](https://mbettan.github.io/machine-learning-cert/MCP.html): Vendor-neutral MCP guide: primitives, resource catalogs, tool descriptions, structured isError handling, transports, server scoping, OAuth and security. — Practice quiz: [quiz.html?topic=mcp](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=mcp) · Exam relevance: Google Professional Agentic Architect (core), Claude Certified Architect – Foundations (core)
- [Agent2Agent (A2A)](https://mbettan.github.io/machine-learning-cert/A2A.html): Open A2A v1.0 & agentic interoperability: Agent Cards, task lifecycle, AgentTool vs A2A boundaries, A2UI/AG-UI/MCP UI generative UI, and AP2/x402 commerce. — Practice quiz: [quiz.html?topic=a2a](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=a2a) · Exam relevance: Google Professional Agentic Architect (core)

## Foundation: Knowledge & Retrieval

- [Retrieval-Augmented Generation (RAG)](https://mbettan.github.io/machine-learning-cert/RAG.html): Chunking, dense/sparse/hybrid retrieval, reranking, agentic RAG, GraphRAG, access control, caching and RAG evaluation. — Practice quiz: [quiz.html?topic=rag](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=rag) · Exam relevance: Google Professional Agentic Architect (core), Claude Certified Architect – Foundations (core)
- [Knowledge Engineering](https://mbettan.github.io/machine-learning-cert/KnowledgeEngineering.html): Turn raw enterprise data into clean, traceable, permission-aware agent knowledge: parsing, chunking, provenance, hybrid & graph indexes, typed tools. — Practice quiz: [quiz.html?topic=knowledge-engineering](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=knowledge-engineering) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (supporting)

## Foundation: AgentOps & Responsible AI

- [AgentOps: Evals, Observability & Cost](https://mbettan.github.io/machine-learning-cert/AgentOps.html): 3-tier evals & autoraters, pass@k vs. pass^k, OpenTelemetry gen_ai.* tracing, shadow/A/B rollouts, feedback flywheels, runtimes & heavy-tail FinOps. — Practice quiz: [quiz.html?topic=agent-ops](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=agent-ops) · Exam relevance: Google Professional Agentic Architect (core), Claude Certified Architect – Foundations (core)
- [Responsible AI: Guardrails, Safety & Governance](https://mbettan.github.io/machine-learning-cert/ResponsibleAI.html): Alignment vs. application guardrails, prompt-injection defenses, human-in-the-loop routing, fairness audits, privacy and governance controls. — Practice quiz: [quiz.html?topic=responsible-ai](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=responsible-ai) · Exam relevance: Google Professional Agentic Architect (core), Claude Certified Architect – Foundations (core)

## Foundation: Agentic Coding Practices

- [Vibe Coding](https://mbettan.github.io/machine-learning-cert/vibecoding.html): Vibe coding spectrum, swarm prototyping & worktrees, Claude Code/Antigravity/Cloud Workstations/GKE sandboxes, and PoC-verified security remediation. — Practice quiz: [quiz.html?topic=vibe-coding](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=vibe-coding) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (supporting)
- [Spec-Driven Development (IDD)](https://mbettan.github.io/machine-learning-cert/idd.html): Spec-first engineering (IDD/SDD): 6-phase workflow, SKILL.md 3-level progressive disclosure, GCPSkillRegistry, Antigravity/Claude hooks & agents-cli eval gates. — Practice quiz: [quiz.html?topic=idd](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=idd) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (supporting)

## Google

Google models and Google Cloud agent products.

- [Gemini & Google Models](https://mbettan.github.io/machine-learning-cert/Google.html): Gemini 4 Argon, Gemini 3.8 Flash/Live/TTS, Model Garden MaaS vs self-hosted, agentic routing, Interactions API, Gemma 4, Nano Banana 2.1, Veo 3.1 & SynthID. — Practice quiz: [quiz.html?topic=google](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=google) · Exam relevance: Google Professional Agentic Architect (supporting)
- [Gemini Enterprise & Low-Code Agents](https://mbettan.github.io/machine-learning-cert/GeminiEnterprise.html): Gemini Enterprise (ex-Agentspace): editions, grounding, Workflow Builder, ADK/A2A registration, governance, CX Agent Studio flows & handoff, low vs pro-code. — Practice quiz: [quiz.html?topic=gemini-enterprise](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=gemini-enterprise) · Exam relevance: Google Professional Agentic Architect (core)
- [Antigravity & Agents CLI](https://mbettan.github.io/machine-learning-cert/Antigravity.html): Google Antigravity (App, agy CLI, IDE, SDK): customizations, subagents, sandboxing, Cloud Workstations and Agents CLI to build, eval and deploy ADK agents. — Practice quiz: [quiz.html?topic=antigravity](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=antigravity) · Exam relevance: Google Professional Agentic Architect (core)
- [Agent Platform: Build, Retrieve & Run](https://mbettan.github.io/machine-learning-cert/AgentPlatform.html): Gemini Enterprise Agent Platform: Managed Agents API, Agent Runtime, Sessions, Memory Bank, retrieval, 2-step simulation, observability & prompt optimization. — Practice quiz: [quiz.html?topic=agent-platform](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=agent-platform) · Exam relevance: Google Professional Agentic Architect (core)
- [Agent Platform: Identity, Security & Governance](https://mbettan.github.io/machine-learning-cert/AgentPlatformSecurity.html): Secure and govern Google Cloud agents: Agent Identity, auth manager, PAB, Agent Gateway & Registry, Model Armor, VPC-SC, CMEK, audit logs and HITL. — Practice quiz: [quiz.html?topic=agent-platform-security](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=agent-platform-security) · Exam relevance: Google Professional Agentic Architect (core)

## Anthropic

Claude models, the Claude API, Claude Code and the Claude Agent SDK.

- [Anthropic & Claude Models](https://mbettan.github.io/machine-learning-cert/Anthropic.html): Claude 4.6/4.7+ family & ecosystem, Adaptive Thinking (effort tiers), Constitutional AI (RLAIF), mechanistic interpretability (SAEs) & RSP ASL-3. — Practice quiz: [quiz.html?topic=anthropic](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=anthropic) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (core)
- [Claude Platform & API](https://mbettan.github.io/machine-learning-cert/ClaudeAPI.html): Production Claude API engineering: tool use, structured outputs and schema design, validation loops, caching, batches, review and calibration. — Practice quiz: [quiz.html?topic=claude-api](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=claude-api) · Exam relevance: Claude Certified Architect – Foundations (core)
- [Claude Code](https://mbettan.github.io/machine-learning-cert/ClaudeCode.html): Claude Code in depth: permissions, CLAUDE.md hierarchy, hooks, subagents, skills, slash commands, plan mode, built-in tools, MCP, CI review and Vertex AI. — Practice quiz: [quiz.html?topic=claude-code](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=claude-code) · Exam relevance: Google Professional Agentic Architect (supporting), Claude Certified Architect – Foundations (core)
- [Claude Agent SDK](https://mbettan.github.io/machine-learning-cert/ClaudeAgentSDK.html): Claude Agent SDK and agent orchestration: loops, stop_reason, subagents, hooks, sessions, tool errors, escalation, provenance and Managed Agents. — Practice quiz: [quiz.html?topic=claude-agent-sdk](https://mbettan.github.io/machine-learning-cert/quiz.html?topic=claude-agent-sdk) · Exam relevance: Claude Certified Architect – Foundations (core)

## Exam mapping: Google Cloud Professional Agentic Architect (PAA)

Official exam page: https://cloud.google.com/learn/certification/agentic-architect

- [Agentic Design Patterns](https://mbettan.github.io/machine-learning-cert/ADP.html): core
- [Agent Development Kit (ADK)](https://mbettan.github.io/machine-learning-cert/ADK.html): core
- [Model Context Protocol (MCP)](https://mbettan.github.io/machine-learning-cert/MCP.html): core
- [Agent2Agent (A2A)](https://mbettan.github.io/machine-learning-cert/A2A.html): core
- [Retrieval-Augmented Generation (RAG)](https://mbettan.github.io/machine-learning-cert/RAG.html): core
- [AgentOps: Evals, Observability & Cost](https://mbettan.github.io/machine-learning-cert/AgentOps.html): core
- [Responsible AI: Guardrails, Safety & Governance](https://mbettan.github.io/machine-learning-cert/ResponsibleAI.html): core
- [Gemini Enterprise & Low-Code Agents](https://mbettan.github.io/machine-learning-cert/GeminiEnterprise.html): core
- [Antigravity & Agents CLI](https://mbettan.github.io/machine-learning-cert/Antigravity.html): core
- [Agent Platform: Build, Retrieve & Run](https://mbettan.github.io/machine-learning-cert/AgentPlatform.html): core
- [Agent Platform: Identity, Security & Governance](https://mbettan.github.io/machine-learning-cert/AgentPlatformSecurity.html): core
- [ML 101](https://mbettan.github.io/machine-learning-cert/ML101.html): supporting
- [Generative AI 101](https://mbettan.github.io/machine-learning-cert/GenAI101.html): supporting
- [Prompt Engineering](https://mbettan.github.io/machine-learning-cert/PromptEngineering.html): supporting
- [Context Engineering & Reliability](https://mbettan.github.io/machine-learning-cert/ContextEngineering.html): supporting
- [Knowledge Engineering](https://mbettan.github.io/machine-learning-cert/KnowledgeEngineering.html): supporting
- [Vibe Coding](https://mbettan.github.io/machine-learning-cert/vibecoding.html): supporting
- [Spec-Driven Development (IDD)](https://mbettan.github.io/machine-learning-cert/idd.html): supporting
- [Gemini & Google Models](https://mbettan.github.io/machine-learning-cert/Google.html): supporting
- [Anthropic & Claude Models](https://mbettan.github.io/machine-learning-cert/Anthropic.html): supporting
- [Claude Code](https://mbettan.github.io/machine-learning-cert/ClaudeCode.html): supporting

## Exam mapping: Claude Certified Architect – Foundations (CCAR-F)

Official exam page: https://anthropic-partners.skilljar.com/claude-certified-architect-foundations-certification

- [Prompt Engineering](https://mbettan.github.io/machine-learning-cert/PromptEngineering.html): core
- [Agentic Design Patterns](https://mbettan.github.io/machine-learning-cert/ADP.html): core
- [Context Engineering & Reliability](https://mbettan.github.io/machine-learning-cert/ContextEngineering.html): core
- [Model Context Protocol (MCP)](https://mbettan.github.io/machine-learning-cert/MCP.html): core
- [Retrieval-Augmented Generation (RAG)](https://mbettan.github.io/machine-learning-cert/RAG.html): core
- [AgentOps: Evals, Observability & Cost](https://mbettan.github.io/machine-learning-cert/AgentOps.html): core
- [Responsible AI: Guardrails, Safety & Governance](https://mbettan.github.io/machine-learning-cert/ResponsibleAI.html): core
- [Anthropic & Claude Models](https://mbettan.github.io/machine-learning-cert/Anthropic.html): core
- [Claude Platform & API](https://mbettan.github.io/machine-learning-cert/ClaudeAPI.html): core
- [Claude Code](https://mbettan.github.io/machine-learning-cert/ClaudeCode.html): core
- [Claude Agent SDK](https://mbettan.github.io/machine-learning-cert/ClaudeAgentSDK.html): core
- [ML 101](https://mbettan.github.io/machine-learning-cert/ML101.html): supporting
- [Generative AI 101](https://mbettan.github.io/machine-learning-cert/GenAI101.html): supporting
- [Knowledge Engineering](https://mbettan.github.io/machine-learning-cert/KnowledgeEngineering.html): supporting
- [Vibe Coding](https://mbettan.github.io/machine-learning-cert/vibecoding.html): supporting
- [Spec-Driven Development (IDD)](https://mbettan.github.io/machine-learning-cert/idd.html): supporting

## Optional

- [Full text of every guide (llms-full.txt)](https://mbettan.github.io/machine-learning-cert/llms-full.txt): concatenated Markdown sources
- [Card catalog (catalog.json)](https://mbettan.github.io/machine-learning-cert/catalog.json): machine-readable list of guides, tracks, exam mapping and assets
- [Sitemap](https://mbettan.github.io/machine-learning-cert/sitemap.xml)
- [Hub landing page](https://mbettan.github.io/machine-learning-cert/)