Awesome AI Agents › Courses and Tutorials
Disciplined AI Software Development is a methodology, not a runnable tool: it packages instruction files, personas and process rules for collaborating with an AI model on a development project. The stated problems it targets are code bloat, architectural drift, context dilution and behavioural inconsistency over long sessions. The process runs in four stages. First, behavioural configuration, where an AI preferences file is loaded as custom instructions and an optional persona framework is applied, with domain personas for methodology enforcement, technical documentation, research and visual systems, plus a template for creating project-specific personas. Second, collaborative planning, where a methodology file guides the model through scope, components, dependency ordering and phased tasks with measurable checkpoints. Third, systematic implementation, where work proceeds component by component under a hard constraint that source files stay at or under 150 lines, so each request stays inside a small context window. Fourth, data-driven iteration, where a benchmarking suite built at the start of the project feeds measurements back to the model so optimisation decisions rest on numbers rather than impressions. Instructions ship in two formats: prose in Markdown or XML for pasting into browser chat interfaces, and PAG, a pattern abstract grammar with explicit keywords such as READ, WRITE, SET and VALIDATE, aimed at command line agents with tool access and orchestration templates. The repository links example projects built under these rules to show the resulting structure. It suits developers who work with AI assistants across extended sessions and want repeatable constraints instead of ad hoc prompting. The material is licensed CC BY-SA 4.0 and consists mainly of documentation, prompt format files and persona definitions rather than a library.
https://github.com/Varietyz/Disciplined-AI-Software-Development
A comprehensive guide and resource hub for prompt engineering, context engineering, retrieval-augmented generation, and AI agents, offering tutorials, papers, tools, and courses to optimize the use of large language models.
Learn Claude Code is an educational project that teaches how to build modern AI coding agents like Claude Code through a progressive tutorial covering core concepts, planning, subagents, and skills mechanisms.
AI Engineering Hub is a comprehensive repository offering in-depth tutorials and practical resources on Large Language Models, Retrieval-Augmented Generation, and real-world AI agent applications for learners and practitioners.
The Hugging Face Agents Course is a comprehensive educational resource that teaches the fundamentals and advanced concepts of AI agents and large language models through structured units, practical frameworks, and community collaboration.
GenAI_Agents is a comprehensive repository offering tutorials, implementations, and community resources for building and advancing generative AI agents from basic to advanced levels.
This course provides a comprehensive project-based tutorial on Harness Engineering for building reliable AI coding agents, covering environment setup, state management, verification, and control.
An AI-powered tool that analyzes GitHub repositories and generates beginner-friendly tutorials with visualizations to simplify understanding complex codebases.
A comprehensive guide to prepare for machine learning and AI technical interviews at major tech companies, covering coding, ML fundamentals, system design, and behavioral aspects.