Home / Glossary
AI Coding Glossary
Key terms in AI-assisted development, explained clearly with practical context.
Agentic Coding
Agentic coding ialah pendekatan pembangunan perisian di mana ejen AI secara autonomi membaca pangkalan kod anda, menulis kod, menjalankan arahan dan mengulang keputusan tanpa salin-tampal manual. Berbeza dengan AI berasaskan sembang, ejen mengambil tindakan langsung dalam persekitaran pembangunan anda untuk menyelesaikan tugasan berbilang langkah.
Claude Code
Claude Code ialah ejen coding AI berasaskan terminal Anthropic yang beroperasi secara langsung dalam persekitaran pembangunan anda. Ia membaca keseluruhan projek anda, menulis kod merentasi pelbagai fail, menjalankan arahan shell, menguruskan aliran kerja git dan mengulang kesilapan secara autonomi — semuanya dari baris arahan.
Model Context Protocol (MCP)
Model Context Protocol (MCP) ialah standard terbuka yang dicipta oleh Anthropic yang menyediakan cara universal untuk menghubungkan model AI ke alat luaran, sumber data dan API. Ia bertindak sebagai antara muka piawai — seperti USB untuk AI — supaya mana-mana alat yang serasi MCP boleh berfungsi dengan mana-mana ejen AI yang serasi MCP.
CLAUDE.md
CLAUDE.md ialah fail konfigurasi markdown yang diletakkan di akar projek anda yang memberikan Claude Code arahan berterusan khusus projek. Ia memberitahu ejen tentang konvensyen pengekodan, seni bina, arahan biasa dan peraturan anda — bertindak sebagai bentuk memori jangka panjang yang digunakan dalam setiap sesi dalam projek tersebut.
Pengaturcaraan Berpasangan AI
Pengaturcaraan berpasangan AI ialah aliran kerja pembangunan di mana pembangun manusia bekerja bersama alat AI untuk menulis kod secara kolaboratif dalam masa nyata. Pembangun memberikan arah, konteks dan pertimbangan manakala AI menyumbang cadangan kod, menangkap pepijat dan mengendalikan tugasan pelaksanaan berulang.
Tetingkap Konteks
Tetingkap konteks ialah bilangan maksimum token (perkataan, aksara kod dan simbol) yang boleh diproses oleh model AI dalam satu interaksi. Ia menentukan had atas berapa banyak maklumat — termasuk gesaan, kod dan respons model — yang boleh disimpan AI dalam ingatan pada satu masa.
Ejen Pengekodan
Ejen pengekodan ialah alat berkuasa AI yang boleh membaca fail secara autonomi, menulis kod, melaksanakan arahan terminal dan mengulang keputusan untuk menyelesaikan tugasan pengaturcaraan. Berbeza dengan alat cadangan kod pasif, ejen pengekodan mengambil tindakan bebas dalam persekitaran pembangunan anda untuk mencapai matlamat yang dinyatakan.
Vibe Coding
Vibe coding ialah pendekatan tidak formal kepada pembangunan perisian di mana pembangun menerangkan apa yang mereka mahukan dalam bahasa semula jadi dan membiarkan alat AI mengendalikan butiran pelaksanaan. Daripada menulis spesifikasi yang tepat, pembangun menyampaikan niat melalui perbualan santai dan mengulang berdasarkan keputusan.
Semakan Kod AI
Semakan kod AI ialah proses menggunakan kecerdasan buatan untuk menganalisis kod sumber secara automatik bagi pepijat, kerentanan keselamatan, ketidakkonsistenan gaya dan isu kualiti. Penyemak AI boleh memeriksa permintaan tarik, mencadangkan penambahbaikan dan menangkap masalah yang mungkin terlepas pandang oleh penyemak manusia kerana keletihan atau tekanan masa.
Kejuruteraan Gesaan untuk Kod
Kejuruteraan gesaan untuk kod ialah amalan membuat arahan yang jelas dan khusus yang membantu alat coding AI menghasilkan output yang tepat dan relevan. Ia melibatkan penstrukturan permintaan anda dengan tahap konteks, kekangan dan contoh yang betul supaya AI memahami apa yang anda mahukan dan bagaimana anda mahukan ia dilakukan.
Ejen AI Tanpa Kepala
Ejen AI tanpa kepala ialah ejen pengekodan yang berjalan tanpa antara muka menghadap manusia atau interaksi masa nyata. Ia melaksanakan tugasan secara autonomi dalam proses latar belakang, saluran paip CI/CD atau kerja berjadual — membaca kod, membuat perubahan, menjalankan ujian dan melaporkan keputusan tanpa menunggu input manusia pada mana-mana langkah.
Sub-Ejen
Sub-ejen ialah proses kanak-kanak selari yang ditimbulkan oleh ejen pengekodan AI utama untuk mengendalikan bahagian tugasan yang kompleks secara bebas dan serentak. Daripada memproses segala-galanya secara berurutan, ejen utama mendelegasikan sub-tugasan kepada ejen kanak-kanak khusus yang berjalan secara selari dan melaporkan keputusan kembali kepada 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.