Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Shubham Saboo Profile picture
@Saboo_Shubham_
Aug 15, 2025 • 15 tweets • 10 min read • Read on X
Scrolly
I started building Opensource AI Agents and RAG Apps 8 months ago.

It turned out to be the fastest way to learn AI engineering.

If you want to start today, here’s a step-by-step roadmap:
1. Python Programming for AI

• Harvard CS50's Introduction to AI with Python
pll.harvard.edu/course/cs50s-i…

• DeepLearning AI's AI Python for Beginners
deeplearning.ai/short-courses/… DeepLearning.AI
2. Machine Learning Fundamentals

• Machine Learning Specialization (Stanford)
coursera.org/specialization…

• Hands-on Practice: github.com/tirthajyoti/Ma…
3. Understanding LLMs and their role in building AI Agents

• Introduction to Large Language Models (Google Cloud): coursera.org/learn/introduc…

• Hands-on LLM App examples (Opensource with 57k+ stars): github.com/Shubhamsaboo/a… Image
4. Prompt Engineering for AI Agents

• Prompt 101 (By Anthropic): youtu.be/ysPbXH0LpIE?si…
• Prompt Engineering Guide: promptingguide.ai/techniques
• Prompting for AI Agents: youtu.be/XSZP9GhhuAc?si…
• Prompting engineering Guide (Google Cloud): cloud.google.com/discover/what-… Image
5. AI Agent frameworks

Here are top Agent Frameworks:
• Google ADK:
github.com/Shubhamsaboo/a…
• Agno: docs.agno.com
• Crew AI: docs.crewai.com
• OpenAI Agents SDK: openai.github.io/openai-agents-… pic.x.com/H2ehGXeOLPImage
6. AI-Powered IDEs for Agent Development

• Windsurf: docs.windsurf.com/windsurf/getti…
• Replit Agent: blog.replit.com/agent
• Cursor: youtube.com/watch?v=gqUQbj…
7. Intelligent Terminal AI Coding Agents

• Claude Code (Anthropic): docs.anthropic.com/en/docs/claude…
• Gemini CLI (Google): github.com/google-gemini/…
8. Build Starter AI Agents with step-by-step tutorials

📌 Step-by-step tutorials: theunwindai.com/archive?tags=A…
🌟 GitHub Repo: github.com/Shubhamsaboo/a… Image
9. Multi-agent Apps with step-by-step tutorials

📌 Step-by-step tutorials: theunwindai.com/archive?tags=A…
🌟 GitHub Repo: github.com/Shubhamsaboo/a… Image
10. AI Agent teams with step-by-step tutorials

📌 Step-by-step tutorials: theunwindai.com/archive?tags=A…
🌟 GitHub Repo: github.com/Shubhamsaboo/a… Image
10. MCP AI Agent with step-by-step tutorials

Introduction to MCP: modelcontextprotocol.io/docs/getting-s…

📌 Step-by-step tutorials: theunwindai.com/archive?tags=A…
🌟 GitHub Repo: github.com/Shubhamsaboo/a…

11. RAG Apps with step-by-step tutorials

📌 Step-by-step tutorials: theunwindai.com/archive?tags=A…
🌟 GitHub Repo: github.com/Shubhamsaboo/a… Image
100+ free step-by-step tutorials with code covering:

🚀 AI Agents
📀 RAG Systems
🗣️ Voice AI Agents
🌐 MCP AI Agents
🤝 Multi-agent Teams
🎮 Autonomous Game Playing Agents

P.S: Don't forget to subscribe for FREE to access future tutorials.

theunwindai.com
Stay tuned for more such interesting posts → @Saboo_Shubham_

I have created 100+ AI Agents and RAG tutorials, 100% free and opensource.

P.S: Don't forget to star the repo to show your support 🌟

github.com/Shubhamsaboo/a…

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Shubham Saboo

Shubham Saboo Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @Saboo_Shubham_

Shubham Saboo Profile picture
Jan 3
Agentic Design Patterns 101

8 agentic patterns to build multi-agent systems with Google ADK:

1. Sequential Pipeline

Agent A → Agent B → Agent C

Each agent does ONE job, passes the baton. Linear. Predictable. Easy to debug.Image
2. Coordinator/Dispatcher Agentic Design Pattern

One smart agent routes requests to specialists.

User asks about billing? → Billing Agent User has a bug? → Tech Support AgentImage
3. Parallel Fan-Out Agentic Design Pattern

Why run tasks one-by-one when they're independent?

Spawn multiple agents simultaneously. Gather results. Synthesize.

Speed wins.Image
Read 9 tweets
Shubham Saboo Profile picture
Dec 2, 2025
Day 2 of Advent of Agents is now live.

Build AI Agents with Gemini 3 in less than 5 mins with YAML without writing a single line of Python code.

Add Google Search, MCP tools, and sub-agents to that.
Tutorial 1: Build an AI Agent with Google Search without writing a single line of Python Code, in simple YAML.

Tutorial 2: Build a Multi-agent app with MCP using Google ADK without writing a single line of Python Code, in simple YAML.

Read 4 tweets
Shubham Saboo Profile picture
Sep 29, 2025
Google ADK meets the AG-UI protocol.

You can now easily connect your ADK AI Agents with interactive frontends using AG-UI in minutes.

100% Opensource. Image
You can build generative UI for your agents with ADK as the agent backend and AG-UI as the communication layer between agent and the UI.

Generative UI goes beyond text and let your agent generate and render UI components directly in the chat.
Learn more about connecting beautiful frontends with your ADK AI Agents.

developers.googleblog.com/en/delight-use…
Read 4 tweets
Shubham Saboo Profile picture
Sep 27, 2025
Build a Multi-agent app with MCP using Google ADK without writing a single line of Python Code, in simple YAML.

All of this in ~5 mins. Step-by-step tutorial with opensource code:
1. Install the @Google ADK Python Package and @firecrawl_dev for MCP Image
2. Create an Agent Template with this single command by following the terminal prompts and entering your Gemini API Key.

It will create a my_agent/ folder, containing a root_agent.yaml file and an .env file to store the API keys. Image
Read 10 tweets
Shubham Saboo Profile picture
Sep 14, 2025
China's Alibaba just dropped a Python framework for building multi-agent apps.

AgentScope lets you build AI agents visually with MCP tools, memory, rag, and reasoning capabilities.

Works with any LLM and supports real-time steering.

100% Opensource. Image
100+ free step-by-step tutorials with code covering:

🚀 AI Agents
📀 RAG Systems
🗣️ Voice AI Agents
🌐 MCP AI Agents
🤝 Multi-agent Teams
🎮 Autonomous Game Playing Agents

P.S: Don't forget to subscribe for FREE to access future tutorials.

theunwindai.com
GitHub Repo: github.com/agentscope-ai/…
Read 4 tweets
Shubham Saboo Profile picture
Sep 12, 2025
JSON prompting for LLMs, explained with examples:
What is JSON prompting?

JSON prompting is a way of asking an LLM using a clear, structured format (with keys and values) and expecting the response in the same structured style.

Text prompts → inconsistent, messy outputs
JSON prompt → consistent, parseable data Image
The Problem With Text Prompts

Natural language is strong, but in AI it’s loose.

“Summarize this email” or “give key takeaways” leaves room for guesswork.

You wouldn’t tell a junior: “Make it better. Do what feels right.”

Yet we do that with AI all the time. Image
Read 12 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(