Home / Glossary
AI Coding Glossary
Key terms in AI-assisted development, explained clearly with practical context.
Agentic Coding
Agentic coding सॉफ्टवेयर डेवलपमेंट का वह तरीका है जिसमें एक AI एजेंट स्वायत्त रूप से आपका कोडबेस पढ़ता है, कोड लिखता है, कमांड चलाता है और बिना manual copy-paste के परिणामों पर iterate करता है। Chat-based AI के विपरीत, एजेंट multi-step कार्यों को पूरा करने के लिए आपके development environment में सीधे कार्रवाई करता है।
Claude Code
Claude Code, Anthropic का terminal-based AI coding agent है जो सीधे आपके development environment में काम करता है। यह आपका पूरा project पढ़ता है, multiple files में code लिखता है, shell commands चलाता है, git workflows manage करता है और errors पर स्वायत्त रूप से iterate करता है — सब कुछ command line से।
Model Context Protocol (MCP)
Model Context Protocol (MCP) एक open standard है जिसे Anthropic ने बनाया है और जो AI models को बाहरी टूल्स, data sources और APIs से connect करने का universal तरीका प्रदान करता है। यह एक standardized interface की तरह काम करता है — AI के लिए USB की तरह — ताकि कोई भी MCP-compatible टूल किसी भी MCP-compatible AI एजेंट के साथ काम कर सके।
CLAUDE.md
CLAUDE.md एक markdown configuration file है जिसे आपके project root में रखा जाता है और जो Claude Code को persistent, project-specific निर्देश प्रदान करती है। यह एजेंट को आपके coding conventions, architecture, common commands और rules के बारे में बताती है — long-term memory के एक रूप की तरह जो उस project के हर session पर लागू होती है।
AI Pair Programming
AI pair programming एक development workflow है जिसमें एक human developer real-time में code लिखने के लिए AI टूल के साथ collaboratively काम करता है। Developer direction, context और judgment प्रदान करता है जबकि AI code suggestions देती है, bugs पकड़ती है और repetitive implementation कार्य संभालती है।
Context Window
Context window वह अधिकतम tokens (शब्द, code characters और symbols) की संख्या है जो एक AI model एक single interaction में process कर सकता है। यह उस information की upper limit define करता है — आपका prompt, code और model की response सहित — जो AI एक बार में memory में रख सकती है।
Coding Agent
Coding agent एक AI-powered टूल है जो स्वायत्त रूप से files पढ़ सकता है, code लिख सकता है, terminal commands execute कर सकता है और programming कार्यों को complete करने के लिए results पर iterate कर सकता है। Passive code suggestion टूल्स के विपरीत, coding agent एक stated goal achieve करने के लिए आपके development environment में independent action लेता है।
Vibe Coding
Vibe coding software development का एक informal approach है जहाँ एक developer natural language में describe करता है कि वे क्या चाहते हैं और AI टूल को implementation details handle करने देता है। Precise specifications लिखने के बजाय, developer casual conversation के माध्यम से intent communicate करता है और results के आधार पर iterate करता है।
AI Code Review
AI code review bugs, security vulnerabilities, style inconsistencies और quality issues के लिए source code automatically analyze करने के लिए artificial intelligence का उपयोग करने की प्रक्रिया है। AI reviewers pull requests examine कर सकते हैं, improvements suggest कर सकते हैं और ऐसी problems पकड़ सकते हैं जो human reviewers थकान या time pressure के कारण miss कर सकते हैं।
Prompt Engineering for Code
Code के लिए prompt engineering clear, specific instructions तैयार करने की practice है जो AI coding टूल्स को accurate, relevant output produce करने में help करती है। इसमें right level of context, constraints और examples के साथ requests structure करना शामिल है ताकि AI समझे कि आप क्या चाहते हैं और कैसे चाहते हैं।
Headless AI Agent
Headless AI agent एक coding agent है जो human-facing interface या real-time interaction के बिना चलता है। यह background processes, CI/CD pipelines या scheduled jobs में tasks autonomously execute करता है — किसी भी step पर human input का wait किए बिना code पढ़ना, बदलाव करना, tests चलाना और results report करना।
Sub-Agents
Sub-agents parallel child processes हैं जिन्हें एक main AI coding agent एक complex task के independent हिस्सों को simultaneously handle करने के लिए spawn करता है। सब कुछ sequentially process करने के बजाय, main agent specialized child agents को sub-tasks delegate करता है जो parallel में चलते हैं और parent को results report करते हैं।
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.