In today's newsletter:

• Web version of our MCP Guidebook is now live [FREE]!
• MCP vs Traditional API Architecture
• Scale ML Models to Billions of Parameters.

TODAY'S ISSUE

update

​Web version of our MCP Guidebook is now live [FREE]!​

Our four guidebooks (MCP, Agents, DS, and AI Engineering) were only accessible in PDF format so far, which made it difficult for us to update and re-distribute them to you.

To fix this, we have started rolling them out in web versions as well to improve accessibility.

​The MCP Guidebook is now live, and you can read it for free here →​

We’ll release the other three Guidebooks as well over the next few days and keep updating them as we release new resources for you in the future.

Reply to this email to let us know if you have any specific requests on what you would like to see next on the website (like roadmaps, features, blueprints, etc.)

Also, in case you missed it…

In just 2 days, the price of lifetime access to DailyDoseofDS will increase by 50%.

It gives you lifetime access to DailyDoseofDS at just 2x the yearly price instead of 3x.

​Secure your Lifetime Access before pricing increases here →​

Pay once and get lifetime access to our existing all-in-one hands-on AI Engineering blueprints + everything we’ll release in the future:

Here's what you'll get:

• The 17-part course that covers how to build Agentic systems.
• Our 18-part MLOps course that goes from first principles to production.
• The full 9-part course on MCPs.
• Our 7-part course on building RAG systems.
• LLM fine-tuning techniques and implementations.
• Our courses on graph neural networks, PySpark, model interpretability, model calibration, causal inference, and more.
• Scaling ML models with implementations.
• Building privacy-preserving ML systems.
• Mathematical deep dives on core DS topics, clustering, etc.
• From-scratch implementations of several core ML algorithms.
• Building 100% reproducible ML projects.
• 50+ more existing industry-relevant topics.

You will get all 100+ existing resources plus every new weekly deep dive for life.

​Secure your Lifetime Access at a discount here →​

P.S. Our last sale was over 12 months ago. We don’t do Black Friday. We don’t do Cyber Monday. This discount disappears in 2 days, and we have no plans to offer it again.

​Join 100k+ people that we helped get promoted, get a better job, or start their own company →​

P.S. If you are an existing monthly or yearly member and wish to upgrade to lifetime, please reply to this email.

MCP

​MCP vs Traditional API Architecture​

Traditional APIs were built for apps to talk to servers.

You have a client (web or mobile app), which sends HTTP requests through an API gateway, and the gateway routes to different services.

This works great for applications. But AI agents aren’t apps.

Here’s the problem:

When you want an AI agent to use a tool, like querying a database, accessing files, or calling an API, you have to write custom integration code for each one. Every tool is different, and every integration is bespoke.

MCP solves this, and the visual below differentiates the architectural difference.

Instead of building custom integrations, MCP provides a universal protocol that sits between AI clients (Claude, IDEs, agents) and tools/APIs.

• One protocol to connect to any tool
• The AI doesn’t care what’s behind the server, like a database, file system, web API
• Tool providers build one MCP server, and it works with any AI client.

The visual above shows this clearly: instead of an API gateway routing traffic to individual services, MCP creates a universal layer between AI agents and backend resources.

If you don’t know MCPs, read the guidebook shared above.

And if you want to dive into core MCP engineering, we covered all these details (with implementations) in the MCP course:

• ​​Part 1 covered MCP fundamentals, the architecture, context management, etc. →​​​​​
• ​​Part 2 covered core capabilities, JSON-RPC communication, etc. →​​​​​
• ​​Part 3 built a fully custom and local MCP client →​​​​​
• ​​Part 4 built a full-fledged MCP workflow using tools, resources, and prompts →​​​​​
• ​​​​​Part 5 taught how to integrate Sampling into MCP workflows →​​​​​
• ​​Part 6 covered testing, security, and sandboxing in MCP Workflows →​​​​​
• ​​Part 7 covered testing, security, and sandboxing in MCP Workflows →​​​​​
• ​​Part 8 integrated MCPs with the most widely used agentic frameworks: LangGraph, LlamaIndex, CrewAI, and PydanticAI →​​​​​
• ​​​​​P​​​​​​art 9 covered using LangGraph MCP workflows to build a comprehensive real-world use case →​​

👉 Over to you: What is your perspective on MCP vs Traditional API?

DEep learning

​From PyTorch to PyTorch Fabric​

PyTorch gives so much flexibility and control. But it leads to a ton of boilerplate code.

​PyTorch Lightning lets you massively reduce the boilerplate code, and it allows us to use distributed training features like DDP, FSDP, DeepSpeed, mixed precision training, and more, by directly specifying parameters:

But it isn’t as flexible as PyTorch to write manual training loops, etc.

Lately, we have been using Lightning Fabric, which brings together:

• The flexibility of PyTorch.
• And distributed training features that PyTorch Lightning provides.

You only need to make 4 minor changes to your existing PyTorch code to easily scale it to the largest billion-parameter models/LLMs.

All this is summarized below:

First, create a Fabric object and launch it:

While creating the Fabric object above, you can specify:

• the accelerator and the number of devices
• the parallelism strategy to use
• the floating point precision, etc.

Next, configure the model, the optimizer, and the dataloader:

Next, you can remove all .to() and .cuda() calls since Fabric takes care of it automatically:

Finally, replace loss.backward() with fabric.backward(loss):

Done!

Now, you can train the model as you usually would.

These 4 simple steps allow you to:

• Easily switch from running on CPU to GPU (Apple Silicon, CUDA, …), TPU, multi-GPU or even multi-node training
• Use state-of-the-art distributed training strategies (DDP, FSDP, DeepSpeed) and mixed precision out of the box

Moreover, you can also build your own custom Trainer using Fabric for training checkpointing, logging, and more.

​Here’s the GitHub repo →​

👉 Over to you: What are some issues with PyTorch?

Thanks for reading!

THAT'S A WRAP

SPONSOR US

ADVERTISE TO 900k+ Data Professionals

Our newsletter puts your products and services directly in front of an audience that matters — thousands of leaders, senior data scientists, machine learning engineers, data analysts, etc., around the world.

Get in touch today by replying to this email.

Today’s email was brought to you by Avi Chawla and Akshay Pachaar.

​Update your profile | Unsubscribe​

Looking for more? Unlock our premium DS/ML resources.

© 2026 Daily Dose of Data Science