PATH 01
Foundations
Rules, search, constraints, and planning—the ideas that make intelligent problem-solving explicit.
→Applied learning for modern AI
Learn AI by building it.
Clear technical tutorials that move from first principles to a toy problem—and then into a practical system you can understand, adapt, and show.
- First principles
- Working code
- Useful systems
learning_pipeline01 → 03
01 / understandTheory
why the method works02 / testToy problem
make the idea observable03 / applyReal-world application
build a useful systemRecent tutorials
Practical depth, not disposable updates.
Work through tested concepts, readable code, mathematical context, and a path from demonstration to application.
Shipping an AI System: Architecture, Observability, Cost, and Reliability
Package an evaluated AI workflow behind a local API boundary with structured logs, latency accounting, fallbacks, privacy controls, and rollback thinking.
Securing AI Applications: Prompt Injection, Data Leakage, and Tool Safety
Build a harmless local prompt-injection test lab and map trust boundaries, least privilege, output validation, sandboxing, approvals, and incident response.
Evaluating Generative AI: From Vague Impressions to Reproducible Tests
Create a small golden dataset and evaluation harness for groundedness, citations, retrieval, task success, regression, and uncertainty.
Agent Memory: What AI Systems Should Remember—and What They Should Forget
Implement short-term state, episodic records, and retrieval-based memory while handling retention, stale facts, conflicts, privacy, and deletion.
AI Agents: Models, Tools, State, and the Execution Loop
Build a bounded tool-using agent with explicit state, permissions, retries, and stopping rules, then place it inside an operational investigation workflow.
Beyond Basic RAG: Hybrid Search, Reranking, and Better Retrieval
Compare lexical, dense, hybrid, and reranked retrieval on a small labelled set, then decide when the extra complexity is justified by measurable search failures.
Learning paths
Start where you are. Build toward complete systems.
Four connected paths move from symbolic problem-solving and classical machine learning to neural networks and modern generative systems.
PATH 02
Core Machine Learning
Prediction, classification, clustering, dimensionality reduction, and ensemble methods grounded in data.
→PATH 03
Deep Learning
Perceptrons, convolution, sequence models, attention, and transfer learning through working examples.
→PATH 04
Advanced & Generative AI
A planned systems path for embeddings, retrieval, evaluation, tools, agents, guardrails, and deployment.
→A deliberate way to learn
Understanding grows when ideas survive contact with code.
Every strong tutorial follows a progression that makes abstract concepts inspectable, testable, and useful.
01 — MODEL
Theory
Build the mental model: the assumptions, mathematics, and mechanics that explain what the method is doing.
02 — OBSERVE
Toy problem
Use a small, controlled example where the moving parts are visible and mistakes are inexpensive.
03 — TRANSFER
Real-world application
Carry the idea into a practical scaffold, including the constraints and decisions that make implementation credible.
Practical project kits
From tutorial to portfolio-ready project.
Structured project kits are being planned to help you extend a tutorial into a documented, testable system. They are not available yet.
In development
project/
├── theory-notes.md
├── toy-experiment.ipynb
├── application/
├── evaluation.md
└── README.mdPlanned contents shown for direction; final kits may differ.
Why this site exists
Technical education should make the hard parts visible.
Applied AI Tutorials is an independent learning platform focused on understandable explanations, working implementations, and the judgment required to move from a model demo to a useful system.
The existing curriculum begins with symbolic AI and classical machine learning, then builds through neural networks, sequence models, and attention. New material will extend that foundation into modern applied AI systems.
Build your understanding