Foundations of AI Coding Assistants with GitHub Copilot

Course Overview

AI Coding Assistant Foundations

• AI coding assistant architecture and components
• Context windows and token limits
• Agentic operation and the plan-execute-iterate cycle
• Autonomous file, terminal, and Git operations
• Reviewing and accepting proposed changes
• Tool permissions and safety controls

Context Engineering

• Context management fundamentals
• Prompting techniques (zero-shot, few-shot, chain-of-thought)
• Reference systems (@file, @codebase, @docs, @web)
• Extended thinking modes and budget allocation
• Memory and cross-session persistence

Configuration Standards

• Configuration file hierarchy and version control
• Universal context configuration (e.g., CLAUDE.md) and cross-tool compatibility
• AGENTS.md format and conventions
• Tool-specific configuration files
• File exclusion strategies

Model Context Protocol (MCP)

• MCP architecture (hosts, clients, servers)
• MCP primitives (tools, resources, prompts)
• Configuration and server installation
• Security considerations and permission management

Practical Workflows

• Code generation and multi-file scaffolding
• Automated code review and security scanning
• Test generation and test-driven workflows
• Agent-driven debugging and error diagnosis
• Refactoring patterns (single-file and multi-file)
• Documentation generation
• Git integration and automated commit messages

GitHub Copilot Features

• Model selection (GPT, Claude, Gemini) and optimization
• Copilot Chat, inline chat, and Copilot Edits
• Agent Mode for autonomous task execution
• Copilot Coding Agent (Issues to PRs)
• Copilot Spaces and context collections
• Copilot Extensions (@azure, @docker, etc.)
• Workspace indexing (remote, local, basic)
• GitHub Copilot configuration (copilot-instructions.md)
• GitHub platform integration (PRs, Issues, Code Review)

Prerequisites

• Familiarity using Generative AI
• Practical Python experience

AI Coding Assistant Foundations

• AI coding assistant architecture and components
• Context windows and token limits
• Agentic operation and the plan-execute-iterate cycle
• Autonomous file, terminal, and Git operations
• Reviewing and accepting proposed changes
• Tool permissions and safety controls

Context Engineering

• Context management fundamentals
• Prompting techniques (zero-shot, few-shot, chain-of-thought)
• Reference systems (@file, @codebase, @docs, @web)
• Extended thinking modes and budget allocation
• Memory and cross-session persistence

Configuration Standards

• Configuration file hierarchy and version control
• Universal context configuration (e.g., CLAUDE.md) and cross-tool compatibility
• AGENTS.md format and conventions
• Tool-specific configuration files
• File exclusion strategies