Self-paced

Learning paths with a clear next step.

Start from first principles or jump into practical provider decisions across 6 Focus Areas. Every module ends with a short knowledge check.

Focus Area 01

AI Literacy & Foundations

Core mental models, language model generation, prompt anatomy, context tokens, verification, and privacy without assuming technical experience.

beginner16 modules · 576 min

AI Foundations

Build a clear mental model of AI, prompts, and agents without assuming technical experience.

For people starting with ai or filling foundational gaps.

1. What AI Does—and Does Not Do2. AI Systems and Useful Work3. How Language Models Produce Responses4. Context, Tokens, and Modalities5. Privacy, Safety, and Responsible Use6. Prompt with Purpose7. Prompt Anatomy and Success Criteria8. Context and Evidence Construction9. Examples and Output Contracts10. Verification and Iterative Improvement11. Research with Evidence12. Writing and Transformation Workflow13. Coding and Analysis Workflow14. Safe Tool-Use Workflow15. Agents, Tools, and Guardrails16. AI Foundations Capstone

Explore path

beginner5 modules · 230 min

What Is Agentic AI?

Classify models, assistants, workflows, agents, agentic systems, and multi-agent systems from observable evidence instead of product labels.

For learners from beginner through advanced who need a precise, provider-neutral way to explain and evaluate agentic ai.

1. Name the Layers in an AI Experience2. Classify Who Chooses the Next Step3. Locate Tools, State, and Human Authority4. Compare Exact Product Experiences5. Defend an Agentic-AI Classification

Explore path

Focus Area 02

Developer & Practitioner AI

Provider-neutral evaluation, capability comparison, structured outputs, function calling, and hands-on practice across Anthropic, OpenAI, and Google Gemini.

intermediate6 modules · 237 min

Providers in Practice

Learn what transfers across providers and where Anthropic, OpenAI, and Google workflows differ.

For practitioners choosing tools or supporting a mixed-provider team.

1. Anthropic in Practice2. OpenAI in Practice3. Choose a Provider Deliberately4. Compare AI Providers without False Equivalence5. Plan a Cross-Provider Migration6. Execute, Roll Back, and Close a Provider Migration

Explore path

intermediate7 modules · 372 min

Claude in Practice

Build practical Claude workflows from surface selection and prompting through APIs, tools, safety, evaluation, and migration.

For learners and practitioners who want to use claude deliberately in individual, developer, and agent workflows.

1. Navigate the Claude Ecosystem2. Prompt Claude with Testable Contracts3. Build Reliable Claude API Workflows4. Build Bounded Claude Tool and Agent Loops5. Secure Claude Workflows with Layered Trust Boundaries6. Evaluate and Observe Claude Workflows7. Migrate Claude Workflows with Evidence

Explore path

intermediate7 modules · 384 min

OpenAI in Practice

Choose the right OpenAI surface and build evaluated, secure, observable, migration-ready API, tool, and Codex workflows.

For learners and practitioners using chatgpt, the openai api, or codex for individual, application, and development workflows.

1. Navigate the OpenAI Ecosystem2. Prompt OpenAI Models with Evaluated Contracts3. Build Reliable OpenAI Responses API Workflows4. Build Bounded OpenAI Tool and Codex Agent Loops5. Secure OpenAI Workflows with Layered Trust Boundaries6. Evaluate and Observe OpenAI Workflows7. Migrate OpenAI Workflows with Evidence

Explore path

intermediate7 modules · 390 min

Gemini in Practice

Choose the right Gemini surface and build evaluated, secure, observable, migration-ready API, tool, and agent workflows.

For learners and practitioners using gemini apps, google ai studio, or the gemini api for individual, prototype, and application workflows.

1. Navigate the Gemini Ecosystem and Interfaces2. Prompt Gemini with Evaluated Contracts3. Build Reliable Gemini API Workflows4. Build Bounded Gemini Tool and Agent Loops5. Secure Gemini Workflows with Layered Trust Boundaries6. Evaluate and Observe Gemini Workflows7. Migrate Gemini Workflows with Evidence

Explore path

intermediate3 modules · 130 min

DeepSeek in Practice

Build evaluated, cost-optimized applications using DeepSeek V3, DeepSeek R1 reasoning models, and Mixture-of-Experts architecture.

For developers, system architects, and ai practitioners leveraging open and hosted deepseek models.

1. Navigate the DeepSeek Ecosystem & Architecture2. DeepSeek R1 Reasoning Tokens & Chain-of-Thought3. DeepSeek API Workflows, Tool Calling & Cost Optimization

Explore path

intermediate3 modules · 130 min

Mistral in Practice

Build applications using Mistral Small/Large, Codestral for code generation, Pixtral for vision, and native embeddings.

For developers and engineers building multilingual, code, and multimodal applications on mistral.

1. Navigate the Mistral Ecosystem & Model Family2. Mistral Function Calling & Codestral FIM3. Pixtral Vision & Mistral Embeddings

Explore path

Focus Area 03

Frontier Agentic Systems & MCP

Bounded agent loops, tool authority, memory boundaries, Model Context Protocol (MCP) architecture, multi-agent handoffs, and scored capstone.

intermediate12 modules · 689 min

Reliable Agent Workflows

Turn agent capability into dependable work through clear scope, permission boundaries, and evidence-based review.

For people using coding, research, or operations agents for work that must be checked and repeatable.

1. Design a Bounded Agent Loop2. Design Typed Tool Contracts and Action Controls3. Engineer Context for Reliable Decisions4. Design Safe Agent Memory Boundaries5. Understand MCP Architecture and Contracts6. Secure MCP Trust Boundaries7. Choose Reliable Orchestration Patterns8. Build Auditable Multi-Agent Handoffs9. Evaluate Agent Behavior with Evidence10. Observe Agent Quality, Cost, and Risk11. Operate, Recover, and Improve Agent Systems12. Reliable Agent Capstone: Design, Test, and Operate

Explore path

Focus Area 04

Retrieval, RAG & Fine-Tuning

Advanced retrieval architectures, hybrid search, embedding stores, knowledge graphs, and LoRA/QLoRA fine-tuning.

advanced5 modules · 255 min

Advanced RAG Engineering

Design, index, retrieve, rerank, and evaluate production Retrieval-Augmented Generation systems across hybrid search and knowledge graphs.

For ml engineers, backend developers, and data architects building enterprise knowledge systems.

1. Chunking Strategies & Document Ingestion in Practice2. Hybrid Search & Cross-Encoder Reranking3. GraphRAG & Multi-Hop Entity Reasoning4. RAG Evaluation & The RAG Triad5. Advanced RAG Capstone: Design, Implement & Evaluate

Explore path

advanced5 modules · 250 min

Model Customization & Fine-Tuning

Master Parameter-Efficient Fine-Tuning (LoRA, QLoRA), instruction dataset curation, preference alignment (DPO), and model evaluation.

For machine learning engineers, ai practitioners, and developers tailoring open-weight models.

1. The AI Customization Decision Matrix2. LoRA & QLoRA Parameter-Efficient Fine-Tuning3. Dataset Curation & Direct Preference Optimization (DPO)4. Evaluation, Merging & GGUF/AWQ Quantization5. Model Customization Capstone: Train, Align & Serve

Explore path

Focus Area 05

Self-Hosted, Open-Weight & AIOps

Open-weight model selection, vLLM/Ollama serving, VRAM calculations, artifact integrity, endpoint security, and disaster recovery.

advanced12 modules · 826 min

Self-Hosted Model Operations

Select, verify, deploy, evaluate, observe, update, roll back, and recover a self-hosted model endpoint.

For practitioners and operators responsible for open-weight or otherwise self-managed model services across workstations, edge, on-premises, and cloud environments.

1. Choose a Deployment Shape and Operating Model2. Model Identity, Licensing, and Provenance3. Model Artifact Integrity and Safe Promotion4. Hardware, Runtime, and Capacity Planning5. Model Serving and API Compatibility Contracts6. Endpoint Identity, Network, and Secrets Security7. Evaluate the Exact Serving Build8. Observability, Cost, and Performance9. Scaling, Failure, and Capacity Controls10. Model Update and Rollback Lifecycle11. Model Incident Response and Recovery12. Self-Hosted Model Operations Capstone

Explore path

Focus Area 06

AI Security, Red-Teaming & Governance

OWASP Top 10 for LLMs, sandboxing, guardrails, compliance frameworks, and cryptographic audit receipts.

advanced4 modules · 205 min

Adversarial AI Security & Red-Teaming

Identify, exploit, and remediate OWASP Top 10 for LLMs vulnerabilities, prompt injections, and jailbreak vectors.

For security engineers, red-teamers, cloud architects, and ai application developers.

1. OWASP Top 10 for LLM Applications2. Jailbreaking, Prompt Injection & Defense in Depth3. Automated Red-Teaming & Vulnerability Scanners4. Adversarial Security Capstone: Audit, Attack & Fortify

Explore path

Would you rather watch it taught? See the on-demand classroom →