Find your next starting point.

Foundation to advanced practice

Python & Data Structures

16 modules, 48 Python lessons and 96 coding exercises.

Foundation

Java Basics

18 written lessons, examples and downloadable code.

beginner

AI Foundations

Understand what AI systems do, evaluate their answers, and design a small evidence-grounded assistant with clear limits. No coding is required.

Prerequisites: No coding prerequisite; Comfort reading short tables and calculating simple percentages

beginner

Python for AI

Build from Python setup and readable code to tested data preparation, vector similarity, and a small local retrieval project. Includes an onboarding path for new coders and practical foundations for later AI engineering.

Prerequisites: Basic Python is helpful but not required if you complete the two onboarding lessons; Ability to create a text file or use a browser notebook; Simple arithmetic; vector operations are introduced step by step

intermediate

Machine Learning Foundations

Build and evaluate small predictive systems while protecting the boundary between evidence and wishful thinking. Use Python standard-library labs, synthetic data, and reproducible experiments. Course credits are internal CodeTrail progress units, not academic credit.

Prerequisites: Write Python functions and work with lists, dictionaries, and CSV files; Understand averages, proportions, and basic algebra; Complete introductory Python or demonstrate equivalent practice

intermediate

LLM Applications and Retrieval

Design a grounded document assistant by separating retrieval, evidence, generation, validation, and security. Build offline retrieval and evaluation labs before considering any live model integration. Course credits are internal CodeTrail progress units, not academic credit.

Prerequisites: Write Python functions and manipulate lists, dictionaries, strings, and JSON; Understand basic testing, file paths, and simple numerical similarity; Complete introductory AI concepts or use the prerequisite bridge before lesson one

advanced

Agentic AI Engineering

Design bounded, inspectable agents that can choose useful steps without acquiring unrestricted authority. Build and test an offline research-and-draft agent with tool contracts, approvals, scoped memory, injection-resistant boundaries, and explicit failure states. Credits are CodeTrail learning units only, not academic credit or professional certification.

Prerequisites: Comfortably write Python functions, dictionaries, lists, loops, exceptions, and assertions.; Explain model inputs and outputs, structured data, retrieval, and why generated text can be wrong.; Read and write JSON; distinguish a proposed action from an executed action.; Complete the intermediate AI material or independently demonstrate its practical outcomes.

advanced

Reliable AI Systems

Build evidence-backed release decisions for a small AI workflow through eight original, offline lessons. Practice evaluations, safe tracing, bounded execution, idempotency, reproducible manifests, authorization boundaries, incident response, and a complete release-readiness packet. Examples use deterministic stand-ins and synthetic data; completion is not a claim of comprehensive professional or accredited competence.

Prerequisites: Comfort with Python functions, dictionaries, lists, loops, exceptions, JSON, and terminal commands; Ability to distinguish user instructions, model output, retrieved content, and tool execution; Basic familiarity with request/response workflows, tests, and version control concepts; Bridge: before lesson one, write and run a three-case string-comparison function; before advanced tasks, practice reading a JSON fixture and catching a deliberate ValueError