chore: sync content to repo (#9581)

Co-authored-by: kamranahmedse <4921183+kamranahmedse@users.noreply.github.com>

src/data/roadmaps/backend/content/agents@w1D3-bSg93ndKK9XJTu7z.md

@@ -0,0 +1,11 @@
+# AI Agents in AI-Assisted Coding
+
+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:
+
+- [@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@What are AI Agents?](https://www.youtube.com/watch?v=F8NKVhkZZWI)
+- [@video@From Zero to Your First AI Agent in 25 Minutes (No Coding)](https://www.youtube.com/watch?v=EH5jx5qPabU)
+- [@video@AI Agents, Clearly Explained](https://www.youtube.com/watch?v=FwOTs4UxQS4)

src/data/roadmaps/backend/content/ai-assisted-coding@fA3yi9puMbTFmbPpo6OjN.md

@@ -4,9 +4,9 @@ AI-assisted coding involves using artificial intelligence tools to help develope
 
 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)
-- [@book@AI-Assisted Programming](https://www.hkdca.com/wp-content/uploads/2025/06/ai-assisted-programming-oreilly.pdf)
 - [@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@What Is Vibe Coding? Building Software with Agentic AI](https://www.youtube.com/watch?v=Y68FF_nUSWE)

src/data/roadmaps/backend/content/anthropic@Lw2nR7x8PYgq1P5CxPAxi.md

@@ -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@Antropic](https://www.anthropic.com/)
+- [@official@Antropic Academy](https://www.anthropic.com/)
+- [@official@Antropic Tutorial](https://claude.com/resources/tutorials)
+- [@article@Anthropic: What We Know About the Company Behind Claude AI](https://builtin.com/articles/anthropic)

src/data/roadmaps/backend/content/antigravity@E7-LveK7jO2npxVTLUDfw.md

@@ -0,0 +1,11 @@
+# Antigravity
+
+Antigravity is an AI-powered code completion tool designed to enhance developer productivity. 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)

src/data/roadmaps/backend/content/claude-code@RcC1fVuePQZ59AsJfeTdR.md

@@ -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)

src/data/roadmaps/backend/content/copilot@HQrxxDxKN8gizvXRU5psW.md

@@ -0,0 +1,11 @@
+# Copilot
+
+Copilot is an AI-powered coding assistant developed by GitHub and OpenAI. It suggests lines of code and entire functions in real-time as you type, based on the context of your code and comments. It learns from a massive dataset of publicly available code, allowing it to offer relevant and accurate suggestions.
+
+Visit the following resources to learn more:
+
+- [@official@Quickstart for GitHub Copilot](https://docs.github.com/en/copilot/quickstart)
+- [@article@What is GitHub Copilot?](https://www.codecademy.com/article/what-is-github-copilot)
+- [@video@Getting started with GitHub Copilot | Tutorial](https://www.youtube.com/watch?v=n0NlxUyA7FI)
+- [@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)

src/data/roadmaps/backend/content/cursor@CKlkVK_7GZ7xzIUHJqZr8.md

@@ -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)
+- [@course@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)

src/data/roadmaps/backend/content/function-calling@Uve-UObgOBfrd-cLayVWe.md

@@ -0,0 +1,10 @@
+# Function Calling
+
+LLM native “function calling” lets a large language model decide when to run a piece of code and which inputs to pass to it. You first tell the model what functions are available. For each one, you give a short name, a short description, and a list of arguments with their types. During a chat, the model can answer in JSON that matches this schema instead of plain text. Your wrapper program reads the JSON, calls the real function, and then feeds the result back to the model so it can keep going. This loop helps an agent search the web, look up data, send an email, or do any other task you expose. Because the output is structured, you get fewer mistakes than when the model tries to write raw code or natural-language commands.
+
+Visit the following resources to learn more:
+
+- [@article@A Comprehensive Guide to Function Calling in LLMs](https://thenewstack.io/a-comprehensive-guide-to-function-calling-in-llms/)
+- [@article@Function Calling with LLMs | Prompt Engineering Guide](https://www.promptingguide.ai/applications/function_calling)
+- [@article@Function Calling with Open-Source LLMs](https://medium.com/@rushing_andrei/function-calling-with-open-source-llms-594aa5b3a304)
+- [@video@LLM Function Calling - AI Tools Deep Dive](https://www.youtube.com/watch?v=gMeTK6zzaO4)

src/data/roadmaps/backend/content/gemini@Bic4PHhz-YqzPWRimJO83.md

@@ -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's Gemini Documentation](https://workspace.google.com/solutions/ai/)
+- [@video@Welcome to the Gemini era](https://www.youtube.com/watch?v=_fuimO6ErKI)

src/data/roadmaps/backend/content/integration-patterns@iatQ3RCxESHt1CwN3PSfx.md

@@ -0,0 +1,9 @@
+# Integration Patterns
+
+Integration patterns are reusable solutions to commonly occurring problems when connecting different software systems or applications. They provide a structured approach for ensuring data is correctly exchanged, services are seamlessly accessed, and overall system behavior is predictable and reliable when integrating AI-powered functionalities. This allows developers to handle complexities like data transformations, error handling, security, and message routing in a standardized way.
+
+Visit the following resources to learn more:
+
+- [@article@Emerging Patterns in Building GenAI Products](https://martinfowler.com/articles/gen-ai-patterns/)
+- [@article@5 Patterns for Scalable LLM Service Integration](https://latitude.so/blog/5-patterns-for-scalable-llm-service-integration/)
+- [@video@AI Design Patterns - LLM Integration: Choosing Between Direct Calls, Agents, RAG, MCP & Workflows](https://www.youtube.com/watch?v=_amJOKrM0XU)

src/data/roadmaps/backend/content/mcp@mHnI19RgZ57XDEIDaHxD0.md

@@ -0,0 +1,12 @@
+# Machine Code Programming (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)
+- [@video@MCP: Build Rich-Context AI Apps with Anthropic](https://www.deeplearning.ai/short-courses/mcp-build-rich-context-ai-apps-with-anthropic/)

src/data/roadmaps/backend/content/openai@-ye5ZtYFDoYGpj-UJaBP8.md

@@ -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 Platform](https://platform.openai.com/docs/overview)
+- [@official@OpenAI Models](https://platform.openai.com/docs/models)
+- [@official@OpenAI Academy](https://academy.openai.com/)

src/data/roadmaps/backend/content/prompting-techniques@xL8d-uHMpJKwUvT8z-Jia.md

@@ -5,8 +5,8 @@ Prompt engineering is the process of crafting effective inputs (prompts) to guid
 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)
-- [@course@Introduction to Prompt Engineering](https://learnprompting.org/courses/intro-to-prompt-engineering)
 - [@video@What is Prompt Engineering?](https://www.youtube.com/watch?v=nf1e-55KKbg)

src/data/roadmaps/backend/content/skills@IWubGe3oquSj882QVnhLU.md

@@ -0,0 +1,13 @@
+# Skills for AI Coding Assistants
+
+AI coding assistants can now 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)

src/data/roadmaps/backend/content/streaming@9f-aWi3_7USy4XpNzrTL6.md

@@ -0,0 +1,11 @@
+# Streamed Responses
+
+Streamed and unstreamed responses describe how an AI agent sends its answer to the user. With a streamed response, the agent starts sending words as soon as it generates them. The user sees the text grow on the screen in real time. This feels fast and lets the user stop or change the request early. It is useful for long answers and chat-like apps.
+
+An unstreamed response waits until the whole answer is ready, then sends it all at once. This makes the code on the client side simpler and is easier to cache or log, but the user must wait longer, especially for big outputs. Choosing between the two depends on the need for speed, the length of the answer, and how complex you want the client and server to be.
+
+Visit the following resources to learn more:
+
+- [@article@Streaming Responses in AI: How AI Outputs Are Generated in Real Time](https://dev.to/pranshu_kabra_fe98a73547a/streaming-responses-in-ai-how-ai-outputs-are-generated-in-real-time-18kb)
+- [@article@AI for Web Devs: Faster Responses with HTTP Streaming](https://austingil.com/ai-for-web-devs-streaming/)
+- [@article@Master the OpenAI API: Stream Responses](https://www.toolify.ai/gpts/master-the-openai-api-stream-responses-139447)

src/data/roadmaps/backend/content/structured-outputs@GMxPmyatxYmIPRFHfRAnr.md

@@ -0,0 +1,10 @@
+# Structured Outputs
+
+Structured outputs involve prompting LLMs to return responses in specific formats like JSON, XML, or other organized structures rather than free-form text. This approach forces models to organize information systematically, reduces hallucinations by imposing format constraints, enables easy programmatic processing, and facilitates integration with applications. For example, requesting movie classification results as JSON with specified schema ensures consistent, parseable responses. Structured outputs are particularly valuable for data extraction, API integration, and applications requiring reliable data formatting.
+
+Visit the following resources to learn more:
+
+- [@article@Diving Deeper with Structured Outputs](https://medium.com/data-science/diving-deeper-with-structured-outputs-b4a5d280c208)
+- [@article@Structured model outputs - OpenAI](https://platform.openai.com/docs/guides/structured-outputs)
+- [@article@Structured outputs - Claude](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)
+- [@video@How to Measure LLM Confidence: Logprobs & Structured Output](https://www.youtube.com/watch?v=THsGizLHrTs)