Claude for Agentic AI Mastery.
For every IT professional ready to upskill in AI & Agentic AI — architects, developers, DevOps & SRE, QA, business analysts, administrators, and technical, project & program managers. A clear roadmap and hands-on learning path through 13 core modules to master agentic AI with Claude, then optionally upskill toward the Claude Certified Architect – Foundations exam.
Live sessions led by K21’s certified trainers — working professionals implementing Claude and cloud tools on the job today, with real-world experience, not people reciting slides.
Your Claude for Agentic AI Mastery & CCA-F roadmap
5 levels. From fundamentals
5 levels. From fundamentals
to Python, mastery & certification.
Start with the fundamentals, get oriented across the major clouds, build your Python foundations, go deep on Agentic AI Mastery with Claude, then finally the Claude Certified Architect certification — every module backed by hands-on labs.
Level 1 — Foundations for Everyone
For EveryoneFor EveryoneFor Everyone
Cloud for Beginners
What cloud computing is and why it matters — the foundation before you build on any platform.
Topics & Labs
Cloud for Beginners
▼- What is cloud computing and why it matters
- Public, private & hybrid cloud
- IaaS, PaaS, SaaS — what each is good for
- Regions, availability zones & scalability
- Cloud pricing models and cost basics
- Cloud security fundamentals
- ⚡ Explore free tiers across major cloud providers
Data for Beginners
The data literacy every AI builder needs — types, storage, pipelines and quality.
Topics & Labs
Data for Beginners
▼- What is data — structured, semi-structured & unstructured
- Databases vs data warehouses vs data lakes
- How data is stored, moved & queried
- Introduction to data pipelines (ETL / ELT)
- Data quality, cleaning & validation basics
- Data formats for AI — JSON, CSV, embeddings
- Data privacy & governance basics
- ⚡ Load, clean & explore a simple dataset
AI, ML, GenAI & Agentic AI for Beginners
AI, machine learning, deep learning and generative AI explained simply — before you architect with Claude.
Topics & Labs
AI, ML, GenAI & Agentic AI for Beginners
▼- What is AI, Machine Learning & Deep Learning?
- Generative AI & Large Language Models explained simply
- Supervised, unsupervised & reinforcement learning
- Real-world AI/ML use cases across industries
- Foundation models & how they are trained
- Prompts, tokens & inference basics
- Responsible AI & safety fundamentals
- ⚡ Chat with a foundation model and explore its behaviour
↓
Level 2 — Get to Know the Clouds
For Everyone
For EveryoneFor EveryoneFor Everyone
AWS for Beginners
A quick, practical tour of AWS so you can work across any cloud.
Topics & Labs
AWS for Beginners
▼- What AWS is & the global infrastructure
- Core services — EC2, S3, IAM, VPC, RDS
- AWS pricing, free tier & billing basics
- Where AI/ML fits — SageMaker & Bedrock overview
- ⚡ Create an AWS free-tier account & explore the console
Azure for Beginners
A quick, practical tour of Azure so you can work across any cloud.
Topics & Labs
Azure for Beginners
▼- What Azure is & core regions
- Core services — VMs, Blob Storage, Entra ID, VNet
- Azure pricing & free account basics
- Where AI fits — Azure AI & Foundry overview
- ⚡ Create an Azure free account & explore the portal
Google Cloud for Beginners
A quick, practical tour of Google Cloud so you can work across any cloud.
Topics & Labs
Google Cloud for Beginners
▼- What Google Cloud is & its infrastructure
- Core services — Compute Engine, Cloud Storage, IAM, VPC
- GCP pricing & free tier basics
- Where AI fits — Vertex AI overview
- ⚡ Create a GCP free account & explore the console
Oracle Cloud for Beginners
A quick, practical tour of Oracle Cloud so you can work across any cloud.
Topics & Labs
Oracle Cloud for Beginners
▼- What Oracle Cloud (OCI) is
- Core services — Compute, Object Storage, IAM, VCN
- OCI pricing & always-free resources
- Where AI fits — OCI AI services overview
- ⚡ Create an OCI free account & explore the console
↓
Level 3 — Python for AI, ML, Data, GenAI, Agentic AI & Claude
PythonNumPyPandasMatplotlibscikit-learnJupyterPydanticFastAPILangChain
For Everyone
Introduction to Python for AI, ML & GenAI
Overview of Python — key features and benefits for AI/ML — and 11 more topics & labs.
Topics & Labs
Introduction to Python for AI, ML & GenAI
▼- Overview of Python — key features and benefits for AI/ML
- Setting up the Python environment (Anaconda, Jupyter, VSCode)
- Variables, data types, and type conversion
- Strings, lists, tuples — creation and manipulation
- Conditional statements and loops (for/while)
- Functions — defining, calling, arguments, return values
- Importing libraries and using pip
- ⚡ Lab: Introduction to Python for Machine Learning
For Everyone
Python Data Structures, Control Flow & Functions
Tuples — definition, use cases, hands-on — and 16 more topics & labs.
Topics & Labs
Python Data Structures
▼- Tuples — definition, use cases, hands-on
- Lists — indexing, slicing, list comprehensions
- Dictionaries — keys, values, nested dicts
- Sets — operations, membership testing
- Lambda functions, map, filter, reduce
- Exception handling — try/except/finally
- File I/O — reading and writing files in Python
- ⚡ Lab: Python Data Structures, Control Flow & Functions
For Everyone
Object-Oriented Programming (OOP)
OOP Part 1 — objects, classes, attributes, methods, __init__ — and 4 more topics & labs.
Topics & Labs
Object-Oriented Programming (OOP)
▼- OOP Part 1 — objects, classes, attributes, methods, __init__
- Inheritance, method overriding, super()
- Encapsulation — private, protected attributes
- Polymorphism — duck typing and method resolution order
- Decorators and class/static methods
- ⚡ Lab: Object-Oriented Programming (OOP)
For Everyone
Python Frameworks & AI Libraries
TensorFlow, PyTorch and the core Python AI libraries for building AI, ML & GenAI — and more topics & labs.
Topics & Labs
AI Libraries: TensorFlow & PyTorch
▼- Introducing the Python AI/ML library ecosystem
- TensorFlow — tensors, the Keras API, building & training models
- PyTorch — tensors, autograd, nn.Module, training loops
- Keras for rapid model prototyping
- Hugging Face Transformers for GenAI & LLMs
- Choosing the right framework for AI, ML & GenAI
- ⚡ Lab: Build & train a model with TensorFlow
- ⚡ Lab: Build & train a model with PyTorch
Bonus
EDA & Feature Engineering
Feature engineering — encoding categorical variables, feature creation, binning, scaling — and 4 more topics & labs.
Topics & Labs
EDA & Feature Engineering
▼- Feature engineering — encoding categorical variables
- Feature creation, binning, and scaling (MinMax, Standard)
- Dimensionality reduction with PCA
- Correlation analysis and feature selection techniques
- Pipelines in scikit-learn for reproducible preprocessing
- ⚡ Lab: EDA & Feature Engineering
Bonus
Supervised Machine Learning
Supervised ML overview — regression vs classification, labelled data — and 10 more topics & labs.
Topics & Labs
Supervised Machine Learning
▼- Supervised ML overview — regression vs classification
- Linear Regression — OLS, gradient descent, regularization
- Logistic Regression — sigmoid, decision boundary, metrics
- K-Nearest Neighbors (KNN)
- Support Vector Machines (SVM) — kernels, margin
- Evaluation metrics — accuracy, F1, ROC-AUC, confusion matrix
- ⚡ Lab: Supervised Machine Learning
Bonus
Ensemble Learning
Decision Trees — splitting criteria, Gini impurity, information gain, pruning — and 5 more topics & labs.
Topics & Labs
Ensemble Learning
▼- Decision Trees — splitting criteria, Gini impurity, information gain
- Bagging — Bootstrap aggregation, Random Forest
- Boosting — AdaBoost, Gradient Boosting, XGBoost
- Stacking and blending ensemble methods
- Hyperparameter tuning — GridSearchCV, RandomizedSearch
- ⚡ Lab: Ensemble Learning
Bonus
Unsupervised Machine Learning
Unsupervised ML overview — clustering, dimensionality reduction, anomaly detection — and 9 more topics & labs.
Topics & Labs
Unsupervised Machine Learning
▼- Unsupervised ML overview — clustering, dimensionality reduction
- K-Means Clustering — algorithm, elbow method, silhouette score
- DBSCAN — density-based clustering
- Hierarchical Clustering and dendrograms
- Autoencoders for anomaly detection
- t-SNE and UMAP for high-dimensional visualization
- ⚡ Lab: Unsupervised Machine Learning
↓
Level 4 — Claude for Agentic AI Mastery
Our core 13-module program for architects, developers, DevOps/SRE, MLOps, DBAs, QA/testing, technical leaders, and technical project/program managers — go from Claude fundamentals to production-grade agentic systems. Plus 2 bonus modules, included for everyone.
For Everyone
M01 — Foundations of Claude and Agentic AI
Foundations of Claude & Agentic AI
Topics & Labs
M01 — Foundations of Claude and Agentic AI
▼- Module 1 overview presentation
- Overview of Claude 3.5 Sonnet & Claude 4
- What is Claude? LLMs explained for developers
- Role of agents in GenAI workflows & the SDLC
- Agentic loop lifecycle and correct termination
For Everyone
M02 — Setup Environment & Enterprise
Enterprise Environment Setup
Topics & Labs
M02 — Setup Environment & Enterprise
▼- Module 2 overview presentation
- Your first Claude API call
- Claude Code — what it is
- Setup for UI, backend & knowledge base
- API/platform access, integrations & secrets
- ⚡ Lab 2.1 — Create & setup a Claude account
- ⚡ Lab 2.2 — Setup VS Code
- ⚡ Lab 2.3 — Install & setup Git, Node.js & Claude Code
- ⚡ Lab 2.4 — Install the Chrome extension for Claude
- ⚡ Lab 2.5 — Interactive workspace in a Claude Artifact
For Everyone
M03 — Prompt Engineering for Reliable Agents
Reliable Agent Prompts
Topics & Labs
M03 — Prompt Engineering for Reliable Agents
▼- Module 3 overview presentation
- Explicit criteria and instruction design
- Few-shot prompting for consistency
- Context optimization
- Escalation patterns and reliable decision-making
- ⚡ Lab 3.1 — Design and test basic prompts for Claude
- ⚡ Lab 3.2 — Structure prompts for relevant answers
- ⚡ Lab 3.3 — Implement context retention systems
- ⚡ Lab 3.4 — Simulate edge cases & test robustness
For Everyone
M04 — Designing Agents for SDLC
Scalable Agentic Architectures
Topics & Labs
M04 — Designing Agents for SDLC
▼- Module 4 overview presentation
- Modular architecture & the Agent SDK
- Task decomposition and chaining
- Multi-agent orchestration
- Tool distribution across agents
- Writing tool descriptions
- MCP patterns for real workflows
- ⚡ Lab 4.1 — Task decomposition, plan & implementation
- ⚡ Lab 4.2 — Creating multiple subagents with Claude
For Everyone
M05 — AI-Powered Code Gen & Engineering Standards
AI Code Gen Standards
Topics & Labs
M05 — AI-Powered Code Gen & Engineering Standards
▼- Backend and frontend standards
- API design (REST/GraphQL)
- Tool use for reliable structured output
- CLAUDE.md configuration hierarchy
- Custom slash commands and Skills
- Plan mode and iterative refinement
- Structured error responses
- ⚡ Lab 5.1 — Working with Claude Skills
- ⚡ Lab 5.2 — Working with Claude Plugins
- ⚡ Lab 5.3 — Calorie Tracker app with Claude Code
- ⚡ Lab 5.4 — Generate backend API code (CRUD, Auth)
- ⚡ Lab 5.5 — Generate frontend components & UI elements
- ⚡ Lab 5.6 — Generate and design RESTful/GraphQL APIs
- ⚡ Lab 5.7 — Fine-tune Claude for context assistance
For Everyone
M06 — UI and Experience Generation with AI
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M06 — UI and Experience Generation with AI
▼- Figma and HTML integration
- Design systems and AI-driven scaffolding
- Accessibility and responsiveness constraints
- ⚡ Lab 1 — Generate a UI design system in Figma
- ⚡ Lab 2 — Automatically generate HTML/CSS from a design
For Everyone
M07 — Automated Testing and Quality Engineering
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M07 — Automated Testing and Quality Engineering
▼- Unit & integration test generation
- Validation-retry loops
- Multi-pass review strategies
- Coverage and quality metrics
- ⚡ Lab 1 — Generate unit tests & validate correctness
- ⚡ Lab 2 — Write integration tests for multiple systems
- ⚡ Lab 3 — Assess test coverage and generate coverage reports
For Everyone
M08 — AI-Driven Documentation & Visualization
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M08 — AI-Driven Documentation & Visualization
▼- Mermaid and swimlane diagrams
- Technical documentation generation
- BRD to requirement traceability
- ⚡ Lab 1 — Create flowcharts / Mermaid diagrams
- ⚡ Lab 2 — Automatically generate tech docs
- ⚡ Lab 3 — Generate a Business Requirements Document
For Everyone
M09 — Enterprise Integration & DevOps Alignment
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M09 — Enterprise Integration & DevOps Alignment
▼- Rally integration & Excel export
- GitHub structure, commit standards
- CI/CD integration and session isolation
- MCP server configuration
- ⚡ Lab 1 — Integrate Rally with Claude
- ⚡ Lab 2 — Integrate Claude with GitHub
- ⚡ Lab 3 — Design a CI/CD pipeline using Claude
For Everyone
M10 — Debugging, Optimization & Improvement
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M10 — Debugging, Optimization & Improvement
▼- Troubleshooting common issues
- Context degradation in extended sessions
- Performance tuning
- Feedback loops
- ⚡ Lab 1 — Intentionally introduce bugs to test Claude
- ⚡ Lab 2 — Optimize code for memory management & speed
- ⚡ Lab 3 — Implement feedback loops
For Everyone
M11 — Governance, Security & Responsible AI
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M11 — Governance, Security & Responsible AI
▼- Coding standards & ethical AI practices
- Hooks and programmatic enforcement
- Human review, provenance
- Version control and audit trails
- ⚡ Lab 1 — Implement a security/compliance checklist
- ⚡ Lab 2 — Setup version control tracking for AI models
- ⚡ Lab 3 — Test outputs for bias and implement filters
For Everyone
M12 — Labs & Real-World Agentic Workflows
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M12 — Labs & Real-World Agentic Workflows
▼- IAG Booking (Iberia pilot) overview
- Custom agent creation for niche workflows
- Collaborative development scenarios
- ⚡ Lab 1 — Design real-world agentic workflows
- ⚡ Lab 2 — Hands-on multi-agent workflow
For Everyone
M13 — Wrap-Up and Next Steps
Part of the Claude for Agentic AI Mastery program.
Topics & Labs
M13 — Wrap-Up and Next Steps
▼- Q&A and feedback collection
- Exam strategy and certification overview
Bonus Modules — Included for Everyone
Bonus
Git & GitHub Actions Training
Included for everyone in the program.
Topics & Labs
Git & GitHub Actions Training
▼- Git introduction, installation & setup
- Working with Git — common terms & commands
- ⚡ Lab — Git & GitHub installation & setup
- Git workflows
- Create CI workflows with GitHub Actions
- ⚡ Lab — Create a CI workflow on GitHub
- Manage and debug workflows in GitHub Actions
- Customize workflows with environment variables
- Cache, share and debug workflows
- Automate GitHub using GitHub Script
- What is GitHub Script?
- ⚡ Lab — Using GitHub Script in GitHub Actions
Bonus
Claude + AWS Labs
Included for everyone in the program.
Topics & Labs
Claude + AWS Labs
▼- ⚡ Bonus Lab — Automate AWS diagrams using Kiro AI
- ⚡ Lab — Claude Code on Amazon Bedrock
- ⚡ Lab — Claude Design Lab
- ⚡ Lab — Claude on the AWS Platform
Where it all comes together
Real-World Capstone Project
A portfolio-ready, AI-powered end-to-end build that combines 11 lab modules into one project.
M02
M03
M04
M05
M06
M07
M08
M09
M10
M11
M12
combine into
Project #1
Airline Booking System Rewrite
Inspired by a real airline case study — Iberia
All 11 lab modules, one build.
↓
★
Resume-Ready Outcome
- ✓ Real agentic architecture
- ✓ Add to your resume as an Experience
- ✓ Demo-ready for interviews
Everything on the Claude Certified Architect – Foundations blueprint — all five domains, 40+ hands-on labs, and a full exam-prep module with 200+ questions and a practice simulator.
Certification Core
Module 1 — AI Foundations
What AI really is, LLMs, and the Claude product family — the grounding every architect needs.
Topics & Labs
AI Foundations
▼- What AI actually is
- Machine learning, deep learning & generative AI
- Large language models
- Claude 101
- How companies are using Claude today
- The Claude product family — Haiku, Sonnet, Opus
- Anthropic's safety-first approach and what it means for architects
Certification Core
Module 2 — Claude API (Domain I: Foundation)
The Claude API end to end — messages, streaming, tokens, caching and batching — with hands-on labs.
Topics & Labs
Claude API Foundation
▼- Understanding the Claude API & API responses
- Creating Claude API keys
- The three message roles — system, user, assistant
- ⚡ Passing the API key directly
- ⚡ Using .env to load the API key
- ⚡ Clean output (response JSON)
- ⚡ Using system prompts
- ⚡ Multi-turn conversations
- Streaming responses
- ⚡ Streaming responses
- ⚡ Temperature
- ⚡ Max tokens
- ⚡ Image input
- stop_reason — the field that drives everything agentic
- ⚡ Stop sequences
- Tokens & context windows — the budget every architect must understand
- ⚡ Tokens & context windows
- Prompt caching
- Message Batches API — processing at scale
- Error handling, retries, and rate limits
Domain 1
Module 3 — Agentic Architecture & Orchestration
From a single API call to multi-agent systems — loops, hub-and-spoke, hooks and escalation, with 5 labs.
Topics & Labs
Agentic Architecture
▼- From API call to agentic loop
- stop_reason as loop controller
- The Agent SDK
- Why single agents fail at scale
- Hub-and-spoke architecture
- Context isolation — what to pass and what NOT to pass subagents
- Hooks — PreToolUse and PostToolUse
- Hooks vs prompts — deterministic vs probabilistic
- Valid escalation triggers
- Prompt chaining vs dynamic adaptive decomposition
- ⚡ Lab 1.1 — Build a perceive–reason–act–observe loop for a single tool-using agent
- ⚡ Lab 1.2 — Decompose a goal into sequential and parallel (fan-out / fan-in) pipelines
- ⚡ Lab 1.3 — Build a hub-and-spoke orchestrator coordinating three subagents
- ⚡ Lab 1.4 — Add retry logic, fallback chains, and a human-escalation trigger
- ⚡ Lab 1.5 — Design a programmatic validation layer that gates a high-stakes action
Domain 2
Module 4 — Tool Design & MCP Integration
Design tools Claude uses reliably and build MCP servers — the USB standard for AI tools, with 6 labs.
Topics & Labs
Tool Design & MCP
▼- Tool descriptions as documentation for Claude
- Designing input_schema — types, required, enum, descriptions
- Structured error responses — the four required fields
- Access failure vs empty result — the most tested error distinction
- Model Context Protocol (MCP) — the USB standard for AI tools
- Tool count and tool distribution across agents
- Claude Code's built-in tools — Read, Write, Bash, Grep, Glob
- ⚡ Built-in tool — Web Search
- ⚡ Lab 2.1 — Write tool descriptions & input schemas that route correctly
- ⚡ Lab 2.2 — Build your first MCP server in Python
- ⚡ Lab 2.3 — Add MCP prompt templates and connect an MCP client
- ⚡ Lab 2.4 — Deploy a remote MCP server over StreamableHTTP with auth
- ⚡ Lab 2.5 — Decide built-in vs custom tools and set tool boundaries
Domain 3
Module 5 — Claude Code Configurations & Workflows
Drive Claude Code like a pro — CLAUDE.md, slash commands, plan mode, hooks and CI/CD, with 5 labs.
Topics & Labs
Claude Code Workflows
▼- Claude Code for IT professionals — more than an IDE plugin
- ⚡ Installing Claude Code
- ⚡ Code explanation using Claude Code
- ⚡ Claude Code quick overview & palette usage
- CLAUDE.md — your project's AI configuration file
- CLAUDE.md hierarchy — global, project, subdirectory
- Session operations — resume, fork, named sessions
- Custom slash commands
- Plan mode — mandatory approval before execution
- ⚡ Claude Code — Plan Mode
- TDD iteration workflow
- Non-interactive mode and CI/CD integration
- ⚡ Lab 3.1 — Onboard Claude Code to a codebase & author a 3-level CLAUDE.md hierarchy
- ⚡ Lab 3.2 — Build custom slash commands and a reusable SKILL.md
- ⚡ Lab 3.3 — Create custom subagents and drive them with plan mode
- ⚡ Lab 3.4 — Implement PreToolUse and PostToolUse hooks
- ⚡ Lab 3.5 — Run Claude Code headless in a CI/CD pipeline with the -p flag
Domain 4
Module 6 — Prompt Engineering & Structured Output
Production prompting, few-shot & chain-of-thought, and schema-locked JSON output, with 5 labs.
Topics & Labs
Prompt Engineering
▼- Production prompting vs casual prompting
- Prompting techniques
- ⚡ Prompting tips — context, examples, output constraints, task breakdown, space to think, role & tone
- ⚡ Zero-shot, one-shot & few-shot
- ⚡ Chain-of-thought (CoT)
- tool_use for guaranteed structured output
- JSON schema design that prevents extraction failures
- Validation-retry loops — closing the production reliability gap
- Multi-pass review — separate sessions, separate reasoning contexts
- ⚡ Lab 4.1 — Engineer a structured system prompt (role, XML tags, constraints)
- ⚡ Lab 4.2 — Design few-shot examples and chain-of-thought for a reasoning task
- ⚡ Lab 4.3 — Force schema-constrained JSON output using tool definitions
- ⚡ Lab 4.4 — Build a validation loop with a retry strategy to stop hallucinated fields
- ⚡ Lab 4.5 — Build a prompt evaluation workflow with a test dataset & model-based grading
Domain 5
Module 7 — Context Management & Reliability
Keep long-running agents accurate — context positioning, provenance, error propagation and escalation, with 5 labs.
Topics & Labs
Context & Reliability
▼- Context positioning — instruction placement matters
- Context degradation in long-running sessions
- Progressive summarization — when it's safe and when it's dangerous
- Information provenance — tracking where facts came from
- Error propagation — how silent failures corrupt final output
- Per-type accuracy metrics — avoid the aggregate trap
- Escalation patterns — retry, reroute, human review, fail gracefully
- ⚡ Lab 5.1 — Design a persistent fact block and trim strategy for long sessions
- ⚡ Lab 5.2 — Build a handoff payload and propagation contract between two agents
- ⚡ Lab 5.3 — Implement the scratchpad pattern as a durable memory slot
- ⚡ Lab 5.4 — Route low-confidence output through a review queue
- ⚡ Lab 5.5 — Add claim-to-source mappings and conflict annotation to a synthesis agent
Exam Prep
Module 8 — Exam Q&A & Practice Simulator
Lock in the certification: 200+ exam-style questions, a timed practice simulator, and full exam guidance.
Topics & Labs
Exam Q&A & Simulator
▼- 200+ exam-style questions across all five domains
- Timed practice exam simulator (exam-like conditions)
- Certification guidance & exam strategy
- Domain-by-domain revision
- Certification scenarios & walkthroughs
- Detailed answer explanations for every question
- Readiness checkpoints before you sit the exam
Bonus Module — Unlocked
Containers & Kubernetes for AI Deployment.
Once you can build with Claude, you need to ship it. This bonus module takes you from Docker basics to deploying containerized AI apps and agents on Kubernetes.
🎁 Included for everyone — a free bonus for all learners in the program. No lock, no deadline.
1
Docker Fundamentals
Images, containers & Dockerfiles
- What containers are and why they matter
- Images vs containers
- Writing a Dockerfile
- ⚡ Build and run your first container
2
Containerizing AI Apps
Package Claude apps & MCP servers
- Packaging a Python/Node app with Docker
- Containerizing an MCP server
- Environment variables & secrets
- ⚡ Containerize a Claude-powered app
3
Container Registries
Store & share images
- Pushing & pulling images
- Public vs private registries
- Tagging & versioning images
4
Kubernetes Essentials
Pods, deployments & services
- Kubernetes architecture in plain English
- Pods, deployments & services
- ConfigMaps & secrets
- Scaling with replicas
5
Deploying AI Apps on Kubernetes
Ship agents at scale
- Deploying a containerized AI app to a cluster
- Autoscaling based on load
- Rolling updates & safe rollouts
- ⚡ Deploy an AI app to Kubernetes
6
Operations & Monitoring
Keep it healthy in production
- Logs, metrics & health checks
- Basic troubleshooting
- Cost & resource awareness
Containers & Kubernetes is a free bonus for everyone — take your Claude apps from laptop to production.
See the program →
What the program includes
Everything to get certified — and actually build.
Not a video library. A hands-on, exam-focused system.
48+ Hours Live Hands-On Training
Instructor-led sessions with live demos and scenario-based problem solving — not passive videos. Recordings available after each session.
25+ Hands-On Labs
Build agents, MCP servers, Claude Code workflows, structured-output pipelines, and context-management patterns — real artifacts, not toy snippets.
CCA-F Certification Prep
Full coverage of all five exam domains, plus certification guidance and exam strategy so you walk in ready.
200+ Exam Q&A + Practice Simulator
Exam-style questions across every domain with detailed explanations, plus a timed practice exam simulator that mirrors the real test.
Scenario-Based Learning
Architecture scenarios and walkthroughs that teach you not just what to memorize, but how to apply Claude in production.
Containers & Kubernetes Bonus
A free bonus module: Docker, container registries, Kubernetes essentials, and deploying AI apps — included for everyone, no extra cost.
Real people. Real outcomes.
The path works when you work it.
Public reviews, real names — part of the 46,000+ professionals K21 has trained across Cloud, Data & AI.
“
“I had two offers just now, thanks to their help. Am incredibly grateful to you all. Atisha Sharma, Manish, you all are great. Sahid thank you again for your deep technical know how. K21 has an awesome team.”
SN
Shadrack Nanjh
Multiple offers, weeks apart
✓ Verified Trustpilot review
“
“I am a beginner on course for being an expert in Claude AI/ML course... Our trainer Sanjay has been marvelous in conducting a very structured course so beginners like me can follow easily... I was encouraged to see different prospects and avenues that I can master without getting overwhelmed.”
AP
Alka Prasad
Beginner → AI Business Analyst
✓ Verified Trustpilot review
“
“After moving to the UK, I faced a major challenge... Several attempts failed until I connected with Atul at K21 Academy... Since then, I have advanced as a global thought leader, supporting cloud-related project stacks with the World Bank and universities in the UK and Africa.”
KO
Kennedy Chinedu Okafor
Job Offer: Senior Technical Advisor
✓ Verified review
Steve — AI Engineer
SJ — Salary doubled, husband hired too
Debashish — AI Engineer (Cloud)
Shouvik — Senior Enterprise Architect
Devesh — Solutions Architect
Dinesh — Tech Program Manager
Gopinath — Cloud Architect
Amol — Senior System Engineer
Srikar — AWS Architect
Zeel — Software Test Engineer
Aarti — Informatica & AWS Developer
Bezzel — Cloud Ops Engineer
Narasimham — Platform Engineer
Etta David — DevOps role, under 2 months
Edobor — Azure Cloud Engineer
Winifred — Job offer in Canada
Tolu Daramola — No IT background → 2 job offers
Bibhu Datta — Says the price was worth it
...and hundreds more across every K21 program — see k21academy.com/reviews
Choose your path
Start here.
Claude for Agentic AI Mastery
$1,200
$997
Pay in full — the core 13-module program
- ✓ All 13 Agentic AI Mastery modules
- ✓ 37 hands-on labs with Claude & Claude Code
- ✓ Bonus: Git & GitHub Actions Training
- ✓ Bonus: Claude + AWS Labs
- ✓ Real-world agentic workflows & capstone project
- ✓ Community access
6-month action-based money-back guarantee
Claude for Agentic AI Mastery
$397 × 3
Total $1,191 — spread over 3 payments
Installments — the core 13-module program
- ✓ All 13 Agentic AI Mastery modules
- ✓ 37 hands-on labs with Claude & Claude Code
- ✓ Bonus: Git & GitHub Actions Training
- ✓ Bonus: Claude + AWS Labs
- ✓ Real-world agentic workflows & capstone project
- ✓ Community access
6-month action-based money-back guarantee
Optional add-on
Add Claude Certified Architect (CCA-F) prep
All 5 exam domains, 40+ additional labs, 200+ exam Q&A + practice simulator. Same 6-month guarantee. Available at checkout with either option above.
+$1,000
Prices shown are launch pricing — confirm final numbers before go-live.
The 6-month money-back guarantee.
Complete the program the way it's designed — attend the live sessions, do the labs, work through exam prep — and if you're not satisfied within 6 months, we'll refund you. Action-based, no fine print. Applies to Claude for Agentic AI Mastery and the CCA-F certification add-on.
✓ Attend the live sessions and complete the labs
✓ Work through the 200+ exam questions & simulator
✓ Ask for support when you need it — don't go silent
✓ Sit the exam within the guidance window
Did all that within 6 months and still not satisfied? Full refund. Action-based, no fine print.
Common questions
Before you enroll.
What is the CCA-F certification?
Claude Certified Architect – Foundations (CCA-F) validates that you can design and build AI solutions with Claude — prompt design, tool use & MCP, agentic architecture, structured outputs, and context management. This program prepares you for that exam with hands-on labs, scenarios, and practice tests.
Who is this program for?
Software engineers, DevOps professionals, solutions architects, and technical leaders who want to master Claude-based AI application design, deployment, and architecture best practices.
What are the prerequisites?
No prior AI or cloud experience required. Levels 1–3 build your Python, cloud, and AI foundations from scratch, so you can start with an open mind. Working knowledge of a cloud platform is a bonus, not a requirement.
How long is the program?
The core Claude for Agentic AI Mastery program is 48+ hours of live instructor-led training. Levels 1–2 (foundations and clouds) are self-paced and included at no extra time cost. Adding CCA-F certification prep brings roughly 36+ more hours of exam-focused training.
Is it hands-on or just theory?
Very hands-on. The core program alone has 37 labs (100+ across the full path) where you build agent loops, MCP servers, Claude Code workflows, structured-output pipelines, and context-management patterns — plus a full Real-World Capstone Project where you combine everything into one build, alongside the certification theory.
Do I get exam practice?
Yes — 200+ exam-style questions across all five domains with detailed explanations, plus a timed practice exam simulator that mirrors real exam conditions, and certification scenarios for exam readiness.
What's the Containers & Kubernetes bonus?
A free bonus module covering Docker, container registries, Kubernetes essentials, and deploying containerized AI apps and agents — so you can take what you build with Claude all the way to production. Included for everyone, no extra cost.
Is the training live or recorded?
Live and instructor-led, so you can ask questions and build alongside the trainer. Recordings are available after each session.
Ready to master Agentic AI with Claude?
Join the next cohort, build real Claude systems, and lead with confidence — certification-ready when you are.
View pricing & enroll →
