Akshay 🚀 Profile picture
Simplifying LLMs, AI Agents, RAGs and Machine Learning for you! • Co-founder @dailydoseofds_• BITS Pilani • 3 Patents • ex-AI Engineer @ LightningAI
24 subscribers
May 20 9 tweets 3 min read
5 levels of Agentic AI systems, clearly explained (with visuals): Agentic AI systems don't just generate text; they can make decisions, call functions, and even run autonomous workflows.

The visual explains 5 levels of AI agency—from simple responders to fully autonomous agents.

Let's dive to learn more about them.
May 17 11 tweets 5 min read
9 MCP, LLM, and AI Agent cheat sheets for AI engineers (with visuals): 1️⃣ Model context Protocol

MCP is like a USB-C port for your AI applications.

Just as USB-C standardizes device connections; MCP standardizes AI app connections to data sources and tools.

Here's my detailed thread about it👇
May 16 14 tweets 4 min read
Let's build an MCP-powered synthetic data generator (100% local): Today, we're building an MCP server that every data scientist will love to have.

Tech stack:

- @cursor_ai as the MCP host
- @datacebo's SDV to generate realistic tabular synthetic data

Let's go! 🚀
May 15 14 tweets 5 min read
Let's build a multi-agent book writer, powered Qwen3 (100% local): Today, we are building an Agentic workflow that writes a 20k word book from a 3-5 word book title.

Tech stack:
- @firecrawl_dev for web scraping.
- @crewAIInc for orchestration.
- @ollama to serve Qwen 3 locally.
- @LightningAI for development and hosting

Let's go! 🚀
May 9 7 tweets 3 min read
Traditional RAG vs. Agentic RAG, clearly explained (with visuals): Traditional RAG has many issues:

- It retrieves once and generates once. If the context isn't enough, it cannot dynamically search for more info.

- It cannot reason through complex queries.

- The system can't modify its strategy based on the problem.
May 5 13 tweets 4 min read
How LLMs work, clearly explained: Before diving into LLMs, we must understand conditional probability.

Let's consider a population of 14 individuals:

- Some of them like Tennis 🎾
- Some like Football ⚽️
- A few like both 🎾 ⚽️
- And few like none

Here's how it looks 👇 Image
May 4 7 tweets 3 min read
5 amazing Jupyter Notebook tricks not known to many: 1️⃣ Retrieve a cell's output in Jupyter

If you often forget to assign the results of a Jupyter cell to a variable, you can use the `Out` dictionary to retrieve the output. Image
Apr 30 9 tweets 3 min read
Let's fine-tune DeepMind's latest Gemma 3 (100% locally): Before we begin, here's what we'll be doing.

We'll fine-tune our private and locally running Gemma 3.

To do this, we'll use:
- @UnslothAI for efficient fine-tuning.
- @ollama to run it locally.

Let's begin! Image
Apr 26 16 tweets 5 min read
Let's build an MCP-powered multi-agent deep researcher (100% local): Before we dive in, here's a quick demo of what we're building!

Tech stack:

- @Linkup_platform for deep web research
- @crewAIInc for multi-agent orchestration
- @Ollama to locally server DeepSeek
- @cursor_ai as MCP host

Let's go! 🚀
Apr 21 10 tweets 4 min read
Transformer vs. Mixture of Experts in LLMs, clearly explained (with visuals): Mixture of Experts (MoE) is a popular architecture that uses different "experts" to improve Transformer models.

The visual below explains how they differ from Transformers.

Let's dive in to learn more about MoE!
Apr 17 12 tweets 5 min read
10 MCP, AI Agents, and RAG projects for AI Engineers (with code): 1️⃣ Real-time Voice RAG Agent

In this project you'll learn how to build a real-time Voice RAG Agent.

You will also learn how to clone your voice in just 5 seconds.

Check the full breakdown (with code) below 👇
Apr 15 8 tweets 3 min read
MCP vs A2A (Agent2Agent) protocol, clearly explained: Agentic applications require both A2A and MCP.

- MCP provides agents with access to tools.
- While A2A allows agents to connect with other agents and collaborate in teams.

Today, I'll clearly explain what A2A is and how it can work with MCP.
Apr 13 8 tweets 3 min read
Traditional RAG vs. Graph RAG, clearly explained (with visuals): top-k retrieval in RAG rarely works.

Imagine you want to summarize a biography where each chapter details a specific accomplishment of an individual.

Traditional RAG struggles because it retrieves only top-k chunks while it needs the entire context. Image
Apr 11 12 tweets 4 min read
MCP is on fire.

AI agents can now talk to real world tools, apps and actually get stuff done.

This changes everything.

Here are 10 amazing examples: 1️⃣ WhatsApp MCP

Exchange images, videos, and voice notes on WhatsApp!

Pair it with the ElevenLabs MCP server for AI-powered transcription & audio messages with 3,000+ voices.

Check this out👇
Apr 10 14 tweets 5 min read
Let's build a multi-agent brand monitoring system using DeepSeek-R1 (100% local): Today, we're building a brand monitoring app that scraps web mentions and produces insights about a company.

Tech stack:

- Bright Data to scrape data at scale
- @crewAIInc for orchestration
- @ollama to serve DeepSeek locally

Let's go! 🚀
Apr 6 13 tweets 4 min read
Let's compare Llama 4 and DeepSeek-R1 using RAG: Today, we're building a Streamlit app to compare MetaAI's Llama 4 against DeepSeek-R1 using RAG.

Tech stack:

- @Llama_Index workflows for orchestration
- @Cometml Opik for evaluation
- @GroqInc for blazing-fast inference (FREE)

Let's go! 🚀
Mar 28 15 tweets 4 min read
Let's build our own reasoning LLM using Reinforcement fine-tuning: RFT allows you to transform any open-source LLM into a reasoning powerhouse.

No labeled data needed.

Today we'll use:

- @predibase for reinforcement fine-tuning (RFT)
- @Alibaba_Qwen-2.5:7b as the base model

Let's go! 🚀
Mar 23 7 tweets 2 min read
Eigenvalues and eigenvectors, clearly explained: The concept of eigenvalues & eigenvectors is widely known yet poorly understood!

Today, I'll clearly explain their meaning & significance.

Let's go! 🚀 Image
Mar 21 4 tweets 2 min read
Effortlessly trace and monitor multi-agent LLM applications!

With just two lines of code, Opik tracks everything happening inside your AI application, including costs. See the CrewAI example below.

100% open-source, self-hosted. Opik offers integrations for nearly all popular frameworks.

But if you don't find what you need, don't worry!

A single decorator will handle it for you.

Check this out👇 Image
Mar 18 9 tweets 3 min read
Multithreading in Python clearly explained: Ever felt like your Python code could run faster❓

Multithreading might be the solution you're looking for!

Today, I'll simplify it for you in this step-by-step guide.

Let's go! 🚀 Image
Mar 13 11 tweets 3 min read
Model Context Protocol (MCP), clearly explained: MCP is like a USB-C port for your AI applications.

Just as USB-C offers a standardized way to connect devices to various accessories, MCP standardizes how your AI apps connect to different data sources and tools.

Let's dive in! 🚀