Glossary AI & Vibecoding
Fundamental reference guide for the new era of software engineering by Andriy Orlov: autonomous agents, loop engineering, Model Context Protocol, context scaling, VPS infrastructure, and burnout prevention.
A
ENAgent Rules (.cursorrules / CLAUDE.md / AGENTS.md)
Machine-readable files of architectural regulations and constraints in the repository that are automatically mounted into the system context of AI agents to prevent codebase degradation.
Agent-Native Testing Strategies
A methodology for writing automated tests designed not only for humans but as a deterministic feedback system for autonomous AI agents with semantic diff error messages.
Agentic IDE
A class of integrated development environments where the model acts as a fully autonomous operator of the workspace with direct access to the file system, terminal, AST, and tests.
AI as Code Reviewer (Bug Detection Before Release)
A methodology for utilizing language models as a stringent senior engineer for automated code audits (Code Review). It identifies hidden security vulnerabilities, memory leaks, and architectural bugs before the software rollout.
AI Code Provenance & Legal Auditing
A system for tracking code authorship and provenance (human vs specific AI model), monitoring license purity (Open Source Compliance), and preparing repositories for legal audits.
AI Code Smells
Typical antipatterns and markers of synthetic code ('code smells' from AI). Excessive obvious comments, utility duplication in every file, fake mocks, and nonsensical try-catch blocks that indicate unchecked generation.
AI Pair Programming Etiquette
Psychological and communication patterns for effective daily collaboration between engineers and language models. Understanding why aggression and yelling at the bot are ineffective, how to provide constructive feedback during errors (Feedback Loop), and treating AI as a patient partner.
AI Refactoring: Safely Refreshing Legacy Code Without Changing Its Logic
A methodology for improving the internal structure, readability, and performance of existing Legacy Code using language models without altering its external behavior. It enables breaking down large spaghetti functions into neat modules and converting old JavaScript to modern TypeScript.
Atomic Git Commits with AI
The discipline of frequent and isolated change commits in Git version control while working with AI code generators. Each successfully functioning micro-feature is saved as a separate commit, ensuring immediate rollback of failed model experiments without losing working progress.
Autonomous Loop (/goal Mode)
An architectural pattern of a closed-loop task execution where an agent autonomously alternates between code generation, command execution, and result verification until a specified goal is fully achieved.
Autonomous PR Reviews & Risk Assessment
Utilization of specialized AI agents in GitHub Actions / GitLab CI for deep semantic analysis of diffs, detection of security vulnerabilities, architectural impact assessment, and changelog generation.
C
ENChatGPT Canvas
The ChatGPT Canvas is a dual-panel interface designed for iterative collaboration on code and text. It allows users to highlight specific paragraphs, adjust length, modify readability, and debug code without rewriting the entire document.
Claude Artifacts (Interactive Live Apps in Chat)
A revolutionary feature of Anthropic's Claude interface. It extracts generated code, diagrams, and interactive React applications into a separate window on the right, rendering them on-the-fly and allowing usage without environment installation.
Claude Code
The official terminal agent from Anthropic, operating directly in the command line via Claude 3.7 Sonnet with native support for Bash, Git, file systems, and the MCP protocol.
Cline (Previously Claude Dev)
An open-source autonomous development agent for VS Code that supports Bring Your Own Key (BYOK) APIs, direct integration with the MCP protocol, terminal, and an embedded browser.
Codebase Indexing
A comprehensive process involving syntax parsing (AST), symbol extraction, call graph construction, and vector-lexical indexing of the repository for ultra-fast relevant contextual search.
Codebase Knowledge Graphs (Graphify)
Building semantic AST graphs of calls, classes, types, and relationships within a project (Graphify) enables the agent to pinpoint only relevant files without prompt spam.
Context Curation & Rules Hygiene
An engineering practice focused on the design, regular auditing, and cleansing of agent behavior configuration files (.cursorrules, .clinerules, AGENTS.md) to prevent model attention degradation.
Context Mentions (@file, @folder, @codebase)
A precise context management mechanism in modern AI editors (Cursor, Windsurf). It allows rapid attachment of specific files (@file), entire folders (@folder), documentation (@docs), or the entire project (@codebase) to a query using the @ symbol.
Continuous AI Refactoring
The practice of regular background updates to the codebase by autonomous AI agents: cleaning dead code, migrating outdated APIs, optimizing performance, and addressing technical debt.
Creating MVP From Description (Prompt-to-App)
A rapid prototyping methodology for Minimum Viable Products (MVP) using AI tools (Cursor, v0.dev, Bolt.new, Lovable). It enables non-technical founders or developers to transform a business idea description into a fully functional web interface with a database in mere minutes.
Cursor Composer (Multi-File Agentic Editing)
The flagship agentic mode of the Cursor code editor (Ctrl+I / Cmd+I). It enables AI to simultaneously create, modify, and link dozens of project files, execute commands in the terminal, and check for errors.
Cursor IDE
Leading AI-first development environment based on the VS Code core, integrating a multi-file generator Composer, predictive autocomplete Cursor Tab, and vector indexing of the codebase.
D
ENDiff Review & Reject
A critical engineering discipline and mechanism for granular auditing of code differences (git diff) before acceptance, preventing codebase degradation, silent removal of error handlers, and security leaks.
Diff-First Mindset: The Art of Reviewing Changes
A fundamental paradigm shift for developers in the AI era (Diff-First Mindset). Transitioning from mechanical text entry to rapid visual assessment of red and green highlighted code changes (git diff) before approval.
Dual-Track Human-AI Development
An organizational and engineering model for labor distribution where humans focus on problem exploration, architecture, and UX, while a parallel fleet of AI agents implements technical modules, tests, and migrations.
E
ENG
ENGitHub Copilot (Code Autocompletion with the Tab Key)
The most renowned intelligent code autocompletion service from GitHub and Microsoft. It operates within VS Code and JetBrains, analyzing developer cursor movements and suggesting entire lines and functions with a Tab key press.
GitHub Copilot Workspace
GitHub's cloud-based agent development environment transforms GitHub Issues into fully specified and tested Pull Requests without the need for local repository cloning.
H
ENHallucinated Dependencies in Code
A dangerous variant of neural network hallucinations in programming. The model fabricates plausible yet non-existent libraries and npm/PyPI packages, creating critical security vulnerabilities (Slopsquatting).
Hallucination Triage & Root Cause
A systematic engineering process for analyzing AI model errors: diagnosing context defects, identifying prompt conflicts, and establishing systemic rules instead of mindless query repetition.
Hard Compiler & Linter Gates
The practice of immediate and irreversible rollback or blocking of changes by the AI agent if the compiler (tsc, rustc) or fast linter (Biome, Ruff) returns a non-zero exit code.
Headless Agent Execution (Overnight Coding)
Autonomous execution of AI agents in the background (CLI/Docker/Cloud) without an open IDE graphical interface to tackle long engineering tasks, refactoring, and testing.
Human-in-the-Loop (HITL)
A fundamental safety and architectural pattern where autonomous process execution is interrupted at defined checkpoints for mandatory human expertise, verification, and approval.
L
ENO
ENP
ENS
ENShadow Git Worktrees & Branching
A methodology for isolating AI agent work in parallel git worktree directories, allowing the model to experiment and build projects without blocking the engineer's open editor.
Shadow Workspace & Git Worktrees
A methodology for complete physical isolation of agent processes in parallel worktrees (Git Worktrees), eliminating mutual blocking and allowing AI to modify and test code without risk to the developer's current branch.
Spec-Driven Development (SDD)
A leading software engineering methodology of the AI era, where the creation, alignment, and formalization of a structured machine-readable specification must precede code generation.
Spec-First Coding
An engineering methodology for AI development (Spec-Driven Development). Instead of chaotic code generation, the developer first composes a structured `SPEC.md` file outlining architecture, data types, and implementation steps.
Spec-First Engineering (RFC-Driven AI Dev)
A development methodology leveraging AI, where 80% of the developer's efforts focus on creating a crystal-clear technical specification (PRD/RFC) before generating the first line of code.
Subagent Fan-out & Map-Reduce Coding
A parallel development pattern where the main agent decomposes a massive task into N independent subtasks, launching N isolated subagents simultaneously and aggregating their results into a single diff.
Superwhisper (Voice-to-Code)
A local voice input utility based on Whisper models and Apple Silicon ANE, optimized for rapid dictation of technical prompts, code, and architectural specifications without delays or cloud leaks.
Synthetic Boilerplate
The practice of fully generating routine boilerplate code using LLMs. This includes automatic creation of TypeScript interfaces, Zod validation schemas, database migrations (SQL/Drizzle/Prisma), API clients, and configuration files without manual typing.
Synthetic Tests Generation (AI Writes Checks for Its Code)
A methodology for automatically generating verification tests (Unit, Integration, E2E using Vitest or Playwright) with artificial intelligence. Ensures deterministic quality control and prevents regressions in code.
T
ENTerminal Agent
A class of autonomous agents whose operational space is the command line (CLI/POSIX Shell), designed for direct interaction with the file system, OS processes, Git, and remote servers.
Terminal AI Agents (Project Management from the Console)
A class of console-based AI tools (Claude Code, Aider, OpenCode, ShellGPT) that operate directly in the Linux or macOS terminal: autonomously searching files, editing repositories, running tests, and making Git commits.
The One-Shot Myth of Application Development
A common misconception among newcomers in vibe coding, fueled by TikTok marketing videos. Attempting to describe a massive, fully-fledged marketplace or CRM system in a single prompt inevitably leads to context loss, missing files, non-functional buttons, and fragile architecture.
Token Budgeting & Cost Governance
A financial management system that establishes strict limits on token expenditures (Hard Limits) and optimizes the cost of successful task execution when working with AI models.
Token Burn Rate
A critical engineering and financial metric for the rate of consumption of contextual and generative tokens (and dollars per hour) in agent-based development sessions, factoring in prompt caching.
V
ENVibecoding
A new paradigm in software engineering where humans act as architects and verifiers of intent, while AI agents autonomously handle syntax, testing, compilation, and debugging.
Voice Coding with Superwhisper (Speed of Thought)
A methodology for formulating engineering tasks and prompts vocally using local speech recognition utilities (Superwhisper, MacWhisper). It enables conveying extensive context at a speed of 150 words per minute without wrist pain.
Voice-Driven Coding & Dictation Pipelines
A methodology for rapid engineering task formulation through local voice recognition (Superwhisper / Whisper.cpp) with automatic transformation of thought streams into structured PRDs and specifications.
W
ENWindsurf Cascade (Agentic Engine by Codeium)
An innovative agentic environment from Codeium, implementing the continuous 'Flow' concept: it combines deep project indexing, autonomous execution of shell commands in the terminal, and on-the-fly error correction.
Windsurf IDE & Cascade
AI-first integrated development environment from Codeium based on the Cascade agent engine, focused on the concept of continuous context flow (Flows) and synchronous pair interaction.
#
Full Stack of Tools, Tier Lists, and AI Skills
Beyond the glossary, GOTBURNOUT provides frontier AI benchmarks, a catalog of over 100,000 AI Agent Skills, production-ready VPS hardening scripts, and an exclusive Pro developer community.