nerdai

Announcing the launch of my book's website: masfromscratch.com 🚀 A companion resource to Build a Multi-Agent System (From Scratch), with @ManningBooks, featuring: - API Reference - Chapter Notebooks - More Examples - Capstone Projects - Community Showcase (coming soon!) Capstone 1 is already live - uses Monte Carlo π estimation to demonstrate concurrent runs, agent evals, and trajectory analysis. Includes Jupyter notebook + RunPod templates for Qwen3-Code-480B. Check it out: masfromscratch.com/capstones/one/ More capstones coming soon! 📚 Book: hubs.la/Q03Q0h4p0 #AI #LLMAgents #MCP #MultiAgentSystems

Very excited for this!

@PolicyLayer @ManningBooks Very cool. I'll check it out!

Chapter 5 of Build a Multi-Agent System (From Scratch) is now live in MEAP with @ManningBooks! 🎉 This chapter covers MCP integration: turning our LLM agent into an MCP host so it can tap into hundreds of third-party tools without building everything from scratch. What you'll learn: - MCP architecture and core concepts - Building MCPTool and MCPToolProvider - Connecting to MCP servers and managing sessions Chapter materials: 📓 Notebook: masfromscratch.com/notebooks/ch05/ 🔧 GitHub MCP example: masfromscratch.com/more-examples/… 📰 GoodNews MCP example: masfromscratch.com/more-examples/… 🔗 Learn MCP: modelcontextprotocol.io Up next: Chapter 6 on Agent Skills — code is done, writing now! 📚 Book (available via @ManningMEAP): hubs.la/Q03Q0h4p0 #AI #LLMAgents #MCP

@rasbt Amazing!

The Redbubble poster version just arrived (redbubble.com/i/poster/LLM-A…)! This is the Medium (26.9 x 23.4 in). Font looks good and sharp, but I probably wouldn't go smaller.

I (finally) put together a new LLM Architecture Gallery that collects the architecture figures all in one place! sebastianraschka.com/llm-architectu…

The hard part of AI isn't always the model anymore. It's the system around it. Agent workflows, tool use, verification loops, orchestration — all the pieces needed to make multi-step AI tasks actually work in production. @rasbt digs into this shift on @twimlait: hubs.la/Q046F0wR0 Explore his books and more in the Future of AI bundle: hubs.la/Q046F1G60

Learning the theory is the first step. Then you building the system. Finally, you gotta use it. And, arguably, that's the real test. @_nerdai_'s companion site for Build a Multi-Agent System (From Scratch) includes free capstone projects so you can apply the agent framework you build in the book to real problems. The first one is now live: hubs.la/Q046n5jy0 Check out the book: hubs.la/Q046nf1J0

We've been working on the Waxal dataset project since 2021, aiming to enhance the amount of data available for African languages. This public speech dataset initially covers 27 Sub-Saharan African languages spoken by over 100 million speakers across more than 26 countries. 🌍

Claude Code wiped our production database with a Terraform command. It took down the DataTalksClub course platform and 2.5 years of submissions: homework, projects, and leaderboards. Automated snapshots were gone too. In the newsletter, I wrote the full timeline + what I changed so this doesn't happen again. If you use Terraform (or let agents touch infra), this is a good story for you to read. alexeyondata.substack.com/p/how-i-droppe…

Agents aren't just prompts & tools. To build well, you need to understand the layers. Build an AI Agent (From Scratch) is control loops, memory, & tooling. Build a Multi-Agent System (From Scratch) by @_nerdai_ is distributed reasoning & collaboration patterns. Together, they read less like competitors and more like a sequence. Daniel Costea's review connects the dots: hubs.la/Q043-8rz0 Books: • Build an AI Agent (From Scratch): hubs.la/Q043-4kc0 • Build a Multi-Agent System (From Scratch): hubs.la/Q043-4mK0

I will teach OpenClaw. no hype. by hand✍️ luma.com/dnc2h9ao

Agent books are trending. Reusable architecture isn't. Build a Multi-Agent System (From Scratch) by @_nerdai_ focuses on what lasts: • A foundational LLM agent • MCP readiness • Human-in-the-loop design • Agent2Agent coordination It's about building systems you can extend — not just demos you can ship once. 50% off today: hubs.la/Q042ZH2H0 BOGO & 20% off Manning Online Pro also live.

@_nerdai_ Adding a Skills chapter after MCP makes a lot of sense. That's the part most people skip when building agents and then wonder why their tool calls are unreliable.

Book update! 📚 Just wrapped up the MCP chapter - covers turning your LLM agent into an MCP host to tap into the vast MCP tools ecosystem. Big structural updates: - New "Skills" chapter added (after MCP) - Capstone projects moving to a dedicated website (launching soon!) The site will feature my capstone projects + community showcases. Projects referenced throughout the book so you know what to explore next. 💝 Valentine's Sale (thru Feb 16): Book is part of @ManningBooks top seller promo Grab it: hubs.la/Q03ByrFR0 #AI #LLMAgents #MCP

Agents aren't just prompts, tools, & RAG glued together. You need a reference architecture. @openclaw makes the design decisions behind modern AI agents visible — orchestration, memory, tooling, and how it all fits. See it unpacked live with @_nerdai_ & @ProfTomYeh on 2/19, 1pm EST: hubs.la/Q042N6F_0 Dive deeper with Build a Multi-Agent System (From Scratch): hubs.la/Q042N7sl0

@windley @ManningBooks Thanks for sharing - so very happy that you find the book useful!

My latest blog post starts a series on authz and Ai agents. If you're interested in how multi-agent systems work (and building your own), this book by Val Andrei Fajardo from @ManningBooks is a good place to start. manning.com/books/build-a-…

Build LLM agents from scratch! Taught using open models via @ollama. #NVIDIAGTC

AI agent books aren’t one-size-fits-all. One thing @debasishg called out in his review of Build a Multi-Agent System (From Scratch) by @_nerdai_: it lets you code along, not just read theory which makes the concepts stick. Read his full take: hubs.la/Q040YnN90 Book details: hubs.la/Q040YkM60