mirror of
https://github.com/kamranahmedse/developer-roadmap.git
synced 2026-03-12 17:51:53 +08:00
chore: sync content to repo (#9586)
Co-authored-by: kamranahmedse <4921183+kamranahmedse@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
committed by
GitHub
GitHub
parent
c2b2f8dc0a
commit
74e2a71058
@@ -0,0 +1,12 @@
|
||||
# AI Agents
|
||||
|
||||
AI agents are autonomous programs designed to help developers write code more efficiently. These agents can automate repetitive tasks, suggest code completions, identify errors, and even generate entire code blocks based on natural language descriptions or existing code patterns. They leverage machine learning models to understand code syntax, semantics, and context, enabling them to provide intelligent and relevant assistance throughout the software development lifecycle.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@roadmap@Visit the Dedicated AI Agents Roadmap](https://roadmap.sh/ai-agents)
|
||||
- [@article@What are AI Agents? - IBM](https://www.ibm.com/think/topics/ai-agents)
|
||||
- [@article@AI Agents Explained in Simple Terms for Beginners](https://www.geeky-gadgets.com/ai-agents-explained-for-beginners/)
|
||||
- [@video@From Zero to Your First AI Agent in 25 Minutes (No Coding)](https://www.youtube.com/watch?v=EH5jx5qPabU)
|
||||
- [@video@What are AI Agents?](https://www.youtube.com/watch?v=F8NKVhkZZWI)
|
||||
- [@video@I Agents, Clearly Explained](https://www.youtube.com/watch?v=FwOTs4UxQS4)
|
||||
@@ -0,0 +1,12 @@
|
||||
# AI-Assisted Coding
|
||||
|
||||
AI-assisted coding involves using artificial intelligence tools to help developers write code more efficiently and effectively. These tools can provide real-time suggestions, automate repetitive tasks, identify potential errors, and even generate code snippets based on natural language descriptions, ultimately speeding up development and improving code quality.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@book@AI-Assisted Programming](https://www.hkdca.com/wp-content/uploads/2025/06/ai-assisted-programming-oreilly.pdf)
|
||||
- [@article@How to Become an Expert in AI-Assisted Coding – A Handbook for Developers](https://www.freecodecamp.org/news/how-to-become-an-expert-in-ai-assisted-coding-a-handbook-for-developers/)
|
||||
- [@article@Best Practices I Learned for AI Assisted Coding](https://statistician-in-stilettos.medium.com/best-practices-i-learned-for-ai-assisted-coding-70ff7359d403)
|
||||
- [@video@How to elevate software development with AI-assisted coding](https://www.youtube.com/watch?v=S2GqQ4gJAH0)
|
||||
- [@video@Everything You Need to Know About Coding with AI // NOT vibe coding](https://www.youtube.com/watch?v=5fhcklZe-qE)
|
||||
- [@video@hat Is Vibe Coding? Building Software with Agentic AI](https://www.youtube.com/watch?v=Y68FF_nUSWE)
|
||||
@@ -0,0 +1,12 @@
|
||||
# AI vs. Traditional Software Development
|
||||
|
||||
Traditional software development relies on developers explicitly writing code to instruct computers on how to perform tasks. This involves defining every step and logic manually. AI-assisted coding, however, leverages machine learning models trained on vast amounts of code to automate parts of the development process. Instead of writing all the code from scratch, developers can use AI to generate code snippets, suggest improvements, and even debug errors, potentially leading to faster development cycles and reduced human error.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@Unlocking the value of AI in software development](https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/unlocking-the-value-of-ai-in-software-development)
|
||||
- [@article@What is vibe coding?](https://www.ibm.com/think/topics/vibe-coding)
|
||||
- [@article@How AI is transforming work at Anthropic](https://www.anthropic.com/research/how-ai-is-transforming-work-at-anthropic)
|
||||
- [@video@I Systems vs Traditional Coding](https://www.youtube.com/watch?v=P7lryCIvxgA)
|
||||
- [@video@ibe Coding Fundamentals In 33 minutes](https://www.youtube.com/watch?v=iLCDSY2XX7E)
|
||||
- [@video@hat is Vibe Coding?](https://www.youtube.com/watch?v=5OWurmg41tI)
|
||||
@@ -0,0 +1,10 @@
|
||||
# Anthropic
|
||||
|
||||
Anthropic is an AI safety and research company focused on developing reliable, interpretable, and steerable AI systems. They create AI models, like Claude, that are designed to be helpful, harmless, and honest, prioritizing safety through techniques like Constitutional AI, where the AI is guided by a set of principles during its training and operation. They can be integrated via APIs to add functionality to applications.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Anthropic](https://www.anthropic.com/)
|
||||
- [@official@Anthropic Academy](https://www.anthropic.com/learn)
|
||||
- [@official@Anthropic Tutorials](https://claude.com/resources/tutorials)
|
||||
- [@article@Anthropic: What We Know About the Company Behind Claude AI](https://builtin.com/articles/anthropic)
|
||||
@@ -0,0 +1,11 @@
|
||||
# Antigravity
|
||||
|
||||
Antigravity is an AI-powered code completion tool designed to enhance developer productivity. Created by Google, it learns from your coding style and project context to provide intelligent suggestions, autocompletions, and code generation snippets directly within your integrated development environment (IDE). This allows developers to write code faster and more efficiently, reducing errors and streamlining the development process.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Google Antigravity](https://antigravity.google/)
|
||||
- [@official@Getting Started with Google Antigravity](https://codelabs.developers.google.com/getting-started-google-antigravity#0)
|
||||
- [@article@Hands-On With Antigravity: Google’s Newest AI Coding Experiment](https://thenewstack.io/hands-on-with-antigravity-googles-newest-ai-coding-experiment/)
|
||||
- [@video@Welcome to Google Antigravity 🚀](https://www.youtube.com/watch?v=SVCBA-pBgt0)
|
||||
- [@video@Antigravity + Stitch MCP: AI Agents That Build Complete Websites](https://www.youtube.com/watch?v=7wa4Ey_tCCE)
|
||||
@@ -0,0 +1,9 @@
|
||||
# AI Applications in Frontend Development
|
||||
|
||||
AI is increasingly being used to automate tasks, improve user interfaces, and enhance the overall development process in frontend. It can help with code generation, intelligent suggestions, automated testing, and creating personalized user experiences through features like dynamic content and adaptive layouts. This integration aims to make development faster, more efficient, and more user-centric.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@AI in software development](https://www.ibm.com/think/topics/ai-in-software-development)
|
||||
- [@article@AI in software development: How to use it, benefits, and key trends](https://appfire.com/resources/blog/ai-in-software-development)
|
||||
- [@article@AI-Assisted Software Development: A Comprehensive Guide with Practical Prompts (Part 1/3)](https://aalapdavjekar.medium.com/ai-assisted-software-development-a-comprehensive-guide-with-practical-prompts-part-1-3-989a529908e0)
|
||||
@@ -0,0 +1,12 @@
|
||||
# Claude Code
|
||||
|
||||
Claude Code is a family of large language models designed for code generation and understanding. It excels at tasks like code completion, bug finding, documentation, and even translating code between different programming languages. Essentially, it's a tool that helps developers write, understand, and maintain code more efficiently by leveraging artificial intelligence.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Claude Code Overview](https://code.claude.com/docs/en/overview)
|
||||
- [@article@Claude Code: From Zero to Hero](https://medium.com/@dan.avila7/claude-code-from-zero-to-hero-bebe2436ac32)
|
||||
- [@article@Claude Code: A Guide With Practical Examples](https://www.datacamp.com/tutorial/claude-code)
|
||||
- [@video@Introducing Claude Code](https://www.youtube.com/watch?v=AJpK3YTTKZ4)
|
||||
- [@video@Claude Code Tutorial for Beginners](https://www.youtube.com/watch?v=eMZmDH3T2bY)
|
||||
- [@video@Claude Code Clearly Explained (and how to use it)](https://www.youtube.com/watch?v=zxMjOqM7DFs&t=82s)
|
||||
@@ -0,0 +1,11 @@
|
||||
# AI-Powered Code Reviews
|
||||
|
||||
AI-powered code reviews leverage machine learning models to analyze source code and identify potential issues, such as bugs, security vulnerabilities, code style violations, and performance bottlenecks. These tools can automate parts of the code review process, freeing up developers to focus on more complex problems and improving the overall quality and maintainability of the codebase.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Common workflows - Claude Code](https://code.claude.com/docs/en/common-workflows)
|
||||
- [@article@AI Code Reviews](https://github.com/resources/articles/ai-code-reviews)
|
||||
- [@article@AI Code Review: How to Make it Work for You](https://www.startearly.ai/post/ai-code-review-how-to-make-it-work-for-you)
|
||||
- [@video@Automatic code reviews with OpenAI Codex](https://www.youtube.com/watch?v=HwbSWVg5Ln4&t=83s)
|
||||
- [@video@You've Been Using AI the Hard Way (Use This Instead)](https://www.youtube.com/watch?v=MsQACpcuTkU)
|
||||
@@ -0,0 +1,11 @@
|
||||
# GitHub Copilot
|
||||
|
||||
GitHub Copilot is an AI-powered code-completion tool that helps developers write code faster and with fewer errors. It uses a combination of machine learning algorithms and access to GitHub's vast repository of open-source code to provide context-aware suggestions for coding tasks. Copilot can generate entire functions, methods, or even entire classes based on the context of the code being written. This feature aims to reduce the time spent on coding by providing immediate and relevant suggestions, allowing developers to focus more on high-level design and problem-solving.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Quickstart for GitHub Copilot](https://docs.github.com/en/copilot/quickstart)
|
||||
- [@official@Tutorials for GitHub Copilot](https://docs.github.com/en/copilot/tutorials)
|
||||
- [@article@Github Copilot Tutorial](https://www.tutorialspoint.com/github-copilot/index.htm)
|
||||
- [@video@Intro to GitHob Copilot in Visual Studio](https://www.youtube.com/watch?v=z1ycDvspv8U)
|
||||
- [@video@GitHub Copilot in VSCode: Top 10 Features Explained](https://www.youtube.com/watch?v=2nPoiUJpDaU)
|
||||
@@ -0,0 +1,12 @@
|
||||
# Cursor
|
||||
|
||||
Cursor is an AI-powered code editor designed to enhance developer productivity. It leverages large language models to offer features like code completion, generation, and refactoring suggestions. By understanding code context, Cursor aims to automate repetitive tasks and provide intelligent assistance throughout the development process.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Cursor](https://cursor.com/)
|
||||
- [@official@Cursor Docs](https://cursor.com/docs)
|
||||
- [@official@Cursor Learn](https://cursor.com/learn)
|
||||
- [@article@Cursor AI: A Guide With 10 Practical Examples](https://www.datacamp.com/tutorial/cursor-ai-code-editor)
|
||||
- [@video@Cursor AI Tutorial for Beginners](https://www.youtube.com/watch?v=3289vhOUdKA)
|
||||
- [@video@Cursor Tutorial for Beginners (AI Code Editor)](https://www.youtube.com/watch?v=ocMOZpuAMw4)
|
||||
@@ -0,0 +1,11 @@
|
||||
# Documentation Generation with AI
|
||||
|
||||
AI-powered documentation generation leverages machine learning models to automatically create and maintain software documentation. These tools can analyze code, comments, and other project artifacts to produce API references, tutorials, and other types of documentation, reducing the manual effort required and ensuring accuracy and consistency. This helps developers by freeing them from manual tasks and ensuring that their APIs are well documented.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@AI code documentation: Benefits and top tips](https://www.ibm.com/think/insights/ai-code-documentation-benefits-top-tips)
|
||||
- [@article@AI Code Documentation Generators: A Guide](https://overcast.blog/ai-code-documentation-generators-a-guide-b6cd72cd0ec4)
|
||||
- [@article@Automate Your Documentation with Claude Code & GitHub Actions: A Step-by-Step Guide](https://medium.com/@fra.bernhardt/automate-your-documentation-with-claude-code-github-actions-a-step-by-step-guide-2be2d315ed45)
|
||||
- [@video@How I Built a Tool to Auto-Generate GitHub Documentation with LLMs](https://www.youtube.com/watch?v=QYchuz6nBR8)
|
||||
- [@video@How to Generate API Documentation Using AI](https://www.youtube.com/watch?v=1529XqH50Xs)
|
||||
@@ -0,0 +1,9 @@
|
||||
# Gemini
|
||||
|
||||
Gemini is a family of multimodal large language models (LLMs) developed by Google. These models are designed to handle and understand different types of data, including text, code, images, audio, and video. They are used to build AI-powered features by providing capabilities such as natural language understanding, content generation, and complex reasoning.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Google Gemini](https://gemini.google.com/)
|
||||
- [@official@Google Gemini Docs](https://workspace.google.com/solutions/ai/)
|
||||
- [@video@Welcome to the Gemini era](https://www.youtube.com/watch?v=_fuimO6ErKI)
|
||||
@@ -0,0 +1,12 @@
|
||||
# How LLMs Work
|
||||
|
||||
LLMs, or Large Language Models, are advanced AI models trained on vast datasets to understand and generate human-like text. They can perform a wide range of natural language processing tasks, such as text generation, translation, summarization, and question answering. LLMs function as sophisticated prediction engines that process text sequentially, predicting the next token based on relationships between previous tokens and patterns from training data. They don't predict single tokens directly but generate probability distributions over possible next tokens, which are then sampled using parameters like temperature and top-K. The model repeatedly adds predicted tokens to the sequence, building responses iteratively. This token-by-token prediction process, combined with massive training datasets, enables LLMs to generate coherent, contextually relevant text across diverse applications and domains.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@roadmap@Visit the Dedicated AI Engineer Roadmap](https://roadmap.sh/ai-engineer)
|
||||
- [@article@What is a large language model (LLM)?](https://www.cloudflare.com/en-gb/learning/ai/what-is-large-language-model/)
|
||||
- [@article@Understanding AI](https://leerob.com/ai)
|
||||
- [@article@New to LLMs? Start Here](https://towardsdatascience.com/new-to-llms-start-here/)
|
||||
- [@video@How Large Language Models Work](https://www.youtube.com/watch?v=5sLYAQS9sWQ)
|
||||
- [@video@Large Language Models Made Easy (LLMs)](https://www.youtube.com/watch?v=osKyvYJ3PRM)
|
||||
@@ -0,0 +1,7 @@
|
||||
# Implementing AI
|
||||
|
||||
Implementing AI in frontend development involves integrating artificial intelligence capabilities directly into user interfaces and workflows. This can range from simple tasks like intelligent form validation to complex features such as personalized content recommendations or AI-powered chatbots. Several major providers offer generative AI solutions that can be leveraged for frontend implementation, including Google with its AI platform, Antropic with its models like Claude, and OpenAI with its popular GPT series. These tools provide developers with the ability to incorporate AI functionalities to improve user experience and streamline development processes.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@Anthropic vs OpenAI vs Gemini: Which Generative AI Model is Right for Enterprise Use?](https://www.aqedigital.com/blog/anthropic-vs-openai-vs-gemini/)
|
||||
@@ -0,0 +1,10 @@
|
||||
# Generative AI for Frontend Development
|
||||
|
||||
Generative AI uses algorithms to create new content, like code or designs, based on the data it's trained on. This means it can help frontend developers by automatically generating things like UI elements, suggesting code snippets, or even creating entire webpage layouts based on specific requirements and examples. Essentially, it's a tool that can automate repetitive tasks and inspire new ideas in the frontend development workflow.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@AI in software development - IBM](https://www.ibm.com/think/topics/ai-in-software-development)
|
||||
- [@article@AI in software development](https://github.com/resources/articles/ai-in-software-development)
|
||||
- [@article@The right way to implement AI into your frontend development workflow](https://blog.logrocket.com/frontend-ai-tools-for-developers/)
|
||||
- [@article@5 Best AI Models For Frontend Development and UI Design](https://www.index.dev/blog/ai-models-frontend-development-ui-generation)
|
||||
@@ -0,0 +1,12 @@
|
||||
Model Context Protocol (MCP)
|
||||
|
||||
Model Context Protocol (MCP) is a rulebook that tells an AI agent how to pack background information before it sends a prompt to a language model. It lists what pieces go into the prompt—things like the system role, the user’s request, past memory, tool calls, or code snippets—and fixes their order. Clear tags mark each piece, so both humans and machines can see where one part ends and the next begins. Keeping the format steady cuts confusion, lets different tools work together, and makes it easier to test or swap models later. When agents follow MCP, the model gets a clean, complete prompt and can give better answers.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@Model Context Protocol](https://modelcontextprotocol.io/introduction)
|
||||
- [@opensource@modelcontexprotocol](https://github.com/modelcontextprotocol/modelcontextprotocol)
|
||||
- [@article@The Ultimate Guide to MCP](https://guangzhengli.com/blog/en/model-context-protocol)
|
||||
- [@article@A Clear Intro to MCP (Model Context Protocol) with Code Examples](https://towardsdatascience.com/clear-intro-to-mcp/)
|
||||
- [@article@Model Context Protocol (MCP): A Guide With Demo Project](https://www.datacamp.com/tutorial/mcp-model-context-protocol)
|
||||
- [@course@MCP: Build Rich-Context AI Apps with Anthropic](https://www.deeplearning.ai/short-courses/mcp-build-rich-context-ai-apps-with-anthropic/)
|
||||
@@ -0,0 +1,9 @@
|
||||
# OpenAI
|
||||
|
||||
OpenAI provides a suite of artificial intelligence models and tools accessible through an API. These models can perform tasks like generating text, translating languages, writing different kinds of creative content, and answering your questions in an informative way. Developers can integrate these powerful AI capabilities into their applications by sending requests to OpenAI's API endpoints and receiving responses.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@official@OpenAI](https://platform.openai.com/docs/overview)
|
||||
- [@official@OpenAI Models](https://platform.openai.com/docs/models)
|
||||
- [@official@OpenAI Academy](https://academy.openai.com/)
|
||||
@@ -0,0 +1,12 @@
|
||||
# Prompt Engineering
|
||||
|
||||
Prompt engineering is the process of crafting effective inputs (prompts) to guide AI models to generate desired outputs. It involves strategically designing prompts to optimize the model’s performance by providing clear instructions, context, and examples. Effective prompt engineering can improve the quality, relevance, and accuracy of responses, making it essential for applications like chatbots, content generation, and automated support. By refining prompts, developers can better control the model’s behavior, reduce ambiguity, and achieve more consistent results, enhancing the overall effectiveness of AI-driven systems.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@roadmap@Visit Dedicated Prompt Engineering Roadmap](https://roadmap.sh/prompt-engineering)
|
||||
- [@course@Introduction to Prompt Engineering](https://learnprompting.org/courses/intro-to-prompt-engineering)
|
||||
- [@article@What is Prompt Engineering? A Detailed Guide For 2026](https://www.datacamp.com/blog/what-is-prompt-engineering-the-future-of-ai-communication)
|
||||
- [@article@Prompting Techniques](https://www.promptingguide.ai/techniques)
|
||||
- [@article@Prompt engineering techniques](https://www.ibm.com/think/topics/prompt-engineering-techniques)
|
||||
- [@video@What is Prompt Engineering?](https://www.youtube.com/watch?v=nf1e-55KKbg)
|
||||
@@ -0,0 +1,10 @@
|
||||
# Refactoring with AI
|
||||
|
||||
Refactoring, in the context of software development, is the process of restructuring existing computer code—changing its internal structure—without changing its external behavior. AI tools can assist in this process by analyzing code for potential improvements in readability, performance, and maintainability. They can automatically suggest or even implement changes like simplifying complex logic, removing redundant code, and improving code style consistency, ultimately leading to a cleaner and more efficient codebase.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@hat is AI code refactoring? - IBM](https://www.ibm.com/think/topics/ai-code-refactoring)
|
||||
- [@article@What is AI code refactoring?](https://graphite.com/guides/what-is-ai-code-refactoring)
|
||||
- [@video@Using AI to Refactor Legacy Code: A Practical Guide with Scott Wierschem](https://www.youtube.com/watch?v=B7Yt-WmlW2I)
|
||||
- [@video@AI-Driven Code Refactoring: Improving Legacy Codebases Automatically - Jorrik Klijnsma](https://www.youtube.com/watch?v=u8tvVxUOwvY)
|
||||
@@ -0,0 +1,13 @@
|
||||
# Skills
|
||||
|
||||
AI coding assistants can leverage "skills" – pre-defined functions or tools exposed to the AI that allow it to perform specific actions. Instead of relying solely on their internal knowledge and large language models, these assistants can call upon these skills (like running tests, deploying code, or querying databases) when needed. This allows the AI to interact with the development environment and execute tasks directly, improving accuracy and efficiency, all while minimizing the context window required for each action.
|
||||
|
||||
Visit the following resources to learn more:
|
||||
|
||||
- [@article@Agent Skills: The Universal Standard Transforming How AI Agents Work](https://medium.com/@richardhightower/agent-skills-the-universal-standard-transforming-how-ai-agents-work-fc7397406e2e)
|
||||
- [@article@AI Agents or Skills? Why the Answer Is ‘Both’](https://thenewstack.io/ai-agents-or-skills-why-the-answer-is-both/)
|
||||
- [@article@Agent Skills vs Tools: What Actually Matters](https://blog.arcade.dev/what-are-agent-skills-and-tools)
|
||||
- [@course@Agent Skills with Anthropic](https://www.deeplearning.ai/short-courses/agent-skills-with-anthropic/)
|
||||
- [@video@Claude Agent Skills Explained](https://www.youtube.com/watch?v=fOxC44g8vig)
|
||||
- [@video@Agent Skills Explained: Why This Changes Everything for AI Development](https://www.youtube.com/watch?v=Ihoxov5x66k)
|
||||
- [@video@The complete guide to Agent Skills](https://www.youtube.com/watch?v=fabAI1OKKww)
|
||||
Reference in New Issue
Block a user