Home / Glossary
AI Coding Glossary
Key terms in AI-assisted development, explained clearly with practical context.
Agentic Coding
Agentic coding adalah pendekatan pengembangan perangkat lunak di mana agen AI secara mandiri membaca codebase Anda, menulis kode, menjalankan perintah, dan mengiterasi hasil tanpa copy-paste manual. Berbeda dengan AI berbasis chat, agen mengambil tindakan langsung di lingkungan pengembangan Anda untuk menyelesaikan tugas multi-langkah.
Claude Code
Claude Code adalah agen coding AI berbasis terminal dari Anthropic yang beroperasi langsung di lingkungan pengembangan Anda. Ia membaca seluruh proyek Anda, menulis kode di berbagai file, menjalankan perintah shell, mengelola alur kerja git, dan mengiterasi kesalahan secara mandiri — semua dari command line.
Model Context Protocol (MCP)
Model Context Protocol (MCP) adalah standar terbuka yang dibuat oleh Anthropic yang menyediakan cara universal untuk menghubungkan model AI ke alat eksternal, sumber data, dan API. Ia berfungsi sebagai antarmuka terstandarisasi — seperti USB untuk AI — sehingga alat apapun yang kompatibel dengan MCP dapat bekerja dengan agen AI apapun yang kompatibel dengan MCP.
CLAUDE.md
CLAUDE.md adalah file konfigurasi markdown yang ditempatkan di root proyek Anda yang memberikan Claude Code instruksi persisten dan spesifik proyek. Ia memberi tahu agen tentang konvensi coding, arsitektur, perintah umum, dan aturan Anda — bertindak sebagai bentuk memori jangka panjang yang berlaku untuk setiap sesi dalam proyek tersebut.
AI Pair Programming
AI pair programming adalah alur kerja pengembangan di mana developer manusia bekerja berdampingan dengan alat AI untuk menulis kode secara kolaboratif dan real-time. Developer memberikan arahan, konteks, dan penilaian sementara AI memberikan saran kode, menangkap bug, dan menangani tugas implementasi yang berulang.
Context Window
Context window adalah jumlah maksimum token (kata, karakter kode, dan simbol) yang dapat diproses model AI dalam satu interaksi. Ia mendefinisikan batas atas seberapa banyak informasi — termasuk prompt Anda, kode, dan respons model — yang dapat disimpan AI dalam memori sekaligus.
Coding Agent
Coding agent adalah alat bertenaga AI yang dapat secara mandiri membaca file, menulis kode, mengeksekusi perintah terminal, dan mengiterasi hasil untuk menyelesaikan tugas pemrograman. Berbeda dengan alat saran kode yang pasif, coding agent mengambil tindakan mandiri di lingkungan pengembangan Anda untuk mencapai tujuan yang dinyatakan.
Vibe Coding
Vibe coding adalah pendekatan informal pengembangan perangkat lunak di mana developer mendeskripsikan apa yang mereka inginkan dalam bahasa alami dan membiarkan alat AI menangani detail implementasinya. Alih-alih menulis spesifikasi yang tepat, developer mengomunikasikan maksud melalui percakapan santai dan mengiterasi berdasarkan hasil.
AI Code Review
AI code review adalah proses menggunakan kecerdasan buatan untuk secara otomatis menganalisis kode sumber terhadap bug, kerentanan keamanan, inkonsistensi gaya, dan masalah kualitas. Peninjau AI dapat memeriksa pull request, menyarankan perbaikan, dan menangkap masalah yang mungkin dilewatkan peninjau manusia karena kelelahan atau tekanan waktu.
Prompt Engineering untuk Kode
Prompt engineering untuk kode adalah praktik menyusun instruksi yang jelas dan spesifik yang membantu alat coding AI menghasilkan output yang akurat dan relevan. Ini melibatkan penstrukturan permintaan Anda dengan tingkat konteks, batasan, dan contoh yang tepat sehingga AI memahami apa yang Anda inginkan dan bagaimana cara yang Anda inginkan.
Headless AI Agent
Headless AI agent adalah coding agent yang berjalan tanpa antarmuka yang menghadap manusia atau interaksi real-time. Ia mengeksekusi tugas secara mandiri dalam proses latar belakang, pipeline CI/CD, atau pekerjaan terjadwal — membaca kode, melakukan perubahan, menjalankan tes, dan melaporkan hasil tanpa menunggu input manusia di setiap langkah.
Sub-Agent
Sub-agent adalah proses anak paralel yang dibuat oleh agen coding AI utama untuk menangani bagian independen dari tugas yang kompleks secara bersamaan. Alih-alih memproses segalanya secara berurutan, agen utama mendelegasikan sub-tugas ke agen anak khusus yang berjalan secara paralel dan melaporkan hasilnya kembali ke induk.
AI Code Completion
AI code completion is a feature in development tools that uses machine learning models to predict and suggest code as you type. It ranges from single-line autocomplete to multi-line function generation, analyzing the surrounding code context to offer relevant suggestions that match your intent and coding style.
Large Language Model (LLM)
A large language model (LLM) is a deep learning system with billions of parameters, trained on vast datasets of text and code to understand, generate, and reason about natural language and programming languages. LLMs like Claude, GPT-4, and Gemini are the foundation of modern AI coding tools.
Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation (RAG) is an AI architecture that improves the accuracy of language model responses by retrieving relevant information from external knowledge sources before generating an answer. Instead of relying solely on what the model memorized during training, RAG fetches up-to-date, domain-specific data and includes it in the model's context.
Tool Use
Tool use (also called tool calling) is the capability of a large language model to invoke external functions, APIs, or system commands as part of generating a response. Instead of being limited to producing text, a model with tool use can read files, run code, query databases, and interact with services—making it the foundation of agentic AI systems.
Function Calling
Function calling is an AI model capability where the model generates structured JSON arguments to invoke external functions instead of producing plain text. This enables LLMs to interact with APIs, databases, file systems, and other tools in a reliable, programmatic way—turning a conversational model into one that can take real-world actions.
System Prompt
A system prompt is a set of instructions provided to an AI model before the user's message that defines the model's behavior, persona, constraints, and capabilities. It acts as a configuration layer that shapes every response the model produces, without the user needing to repeat these instructions in each message.
Temperature
Temperature is a parameter in large language models that controls the randomness of the output. A temperature of 0 makes the model deterministic, always choosing the most probable next token. Higher temperatures (up to 1.0 or 2.0) increase randomness, making less probable tokens more likely to be selected. For coding tasks, lower temperatures generally produce more reliable, consistent code.
Token
A token is the fundamental unit of text that a large language model processes. Tokenization splits text into chunks—sometimes whole words, sometimes subwords, sometimes individual characters—that the model can work with. In English text, one token is roughly 3-4 characters or 0.75 words. In code, tokens map to keywords, operators, variable names, and whitespace.
Fine-Tuning
Fine-tuning is the process of further training a pre-trained large language model on a smaller, task-specific dataset to adapt its behavior for a particular use case. The model's weights are updated to specialize in a domain—such as a specific programming language, codebase, or output format—while retaining its general capabilities from pre-training.
Code Generation
AI code generation is the process of using artificial intelligence to produce source code from natural language descriptions, specifications, or existing code context. Modern code generation powered by LLMs can write entire functions, classes, tests, and even full applications from high-level instructions, across virtually any programming language.
AI Refactoring
AI refactoring is the use of artificial intelligence to automatically restructure, simplify, and improve existing source code without changing its external behavior. AI refactoring tools analyze code for complexity, duplication, poor naming, and anti-patterns, then apply transformations that make the code cleaner, more maintainable, and easier to understand.
AI Testing
AI testing is the application of artificial intelligence to software testing workflows—including generating unit tests, integration tests, and end-to-end tests from source code; identifying untested edge cases; analyzing test failures; and suggesting fixes. AI testing tools understand code semantics to write meaningful tests that go beyond basic coverage.
Multi-Modal AI
Multi-modal AI refers to artificial intelligence systems that can process, understand, and generate multiple types of data—text, images, audio, video, and code—within a single model. Unlike single-modal models that only handle text, multi-modal models can analyze a screenshot of a UI, read the associated code, and generate modifications based on both visual and textual understanding.
Chain-of-Thought
Chain-of-thought (CoT) prompting is a technique that encourages a large language model to break down complex problems into intermediate reasoning steps before producing a final answer. Instead of jumping to a conclusion, the model "thinks out loud," explaining each step of its logic. This significantly improves accuracy on tasks that require multi-step reasoning, including debugging, algorithm design, and code architecture decisions.
Few-Shot Prompting
Few-shot prompting is a technique where you include a small number of example input-output pairs in your prompt to demonstrate the pattern you want the AI to follow. By showing the model 2-5 examples of the desired behavior, it learns the format, style, and logic you expect—without any model training or fine-tuning. This is one of the most effective techniques for getting consistent, formatted output from LLMs.
Zero-Shot Prompting
Zero-shot prompting is a technique where you instruct an AI model to perform a task without providing any examples of the desired input-output format. You describe what you want in natural language, and the model relies entirely on its pre-trained knowledge to produce the output. It is the most natural way to interact with AI—just tell it what to do.
Embeddings
Embeddings are dense numerical vectors (arrays of floating-point numbers) that represent text, code, or other data in a high-dimensional space where semantically similar items are positioned close together. They enable AI systems to measure similarity between pieces of code, search codebases by meaning rather than keywords, and power retrieval-augmented generation (RAG) systems.
Vector Database
A vector database is a specialized database designed to store, index, and search high-dimensional embedding vectors efficiently. Unlike traditional databases that match exact values or keywords, vector databases find the most similar vectors to a query vector—enabling semantic search, recommendation systems, and the retrieval component of RAG (retrieval-augmented generation) architectures.
Technical Debt
Technical debt is the implied cost of future rework caused by choosing a quick, expedient solution now instead of a better approach that would take longer. Like financial debt, it accumulates interest: the longer it remains unaddressed, the more time and effort future changes require. Common sources include rushed features, skipped tests, outdated dependencies, and inconsistent architecture.