In partnership with
Hey there,
If you’ve been meaning to really understand LLMs and finally ship an agent, here’s a tight, weekend-friendly pat
h with handpicked resources and direct links.
Let’s get into it.
88% resolved. 22% stayed loyal. What went wrong?
That's the AI paradox hiding in your CX stack. Tickets close. Customers leave. And most teams don't see it coming because they're measuring the wrong things.
Efficiency metrics look great on paper. Handle time down. Containment rate up. But customer loyalty? That's a different story — and it's one your current dashboards probably aren't telling you.
Gladly's 2026 Customer Expectations Report surveyed thousands of real consumers to find out exactly where AI-powered service breaks trust, and what separates the platforms that drive retention from the ones that quietly erode it.
If you're architecting the CX stack, this is the data you need to build it right. Not just fast. Not just cheap. Built to last.
Step 1: Get a Solid LLM + Deep Learning Foundation
Start with an approachable deep learning + LLM foundation so the rest actually makes sense:
Understanding Deep Learning (Book, free online)
A clear, modern deep learning textbook you can browse chapter-by-chapter.
https://udlbook.github.io/udlbook/Building an LLM from Scratch (Book)
Walks through implementing your own LLM so you truly get what’s happening under the hood.
https://lnkd.in/g2YGbnWSLLM Course (Hands-on GitHub repo)
A practical course repo to connect concepts to code.
https://github.com/mlabonne/llm-course
If you only have a few hours: skim “Understanding Deep Learning” for intuition, then pick one hands-on repo and run at least one notebook.
Step 2: Learn How AI Agents Actually Work
Next, zoom out from “just a model” to agents: systems that reason, use tools, and act.
High-impact videos:
LLM Introduction (video)
https://www.youtube.com/watch?v=zjkBMFhNj_gLLMs from Scratch (video)
https://www.youtube.com/watch?v=9vM4p9NN0TsAgentic AI Overview (Stanford, video)
https://www.youtube.com/watch?v=kJLiOGle3LwBuilding and Evaluating Agents (video)
https://www.youtube.com/watch?v=d5EltXhbcfA
Pick one “theory” talk (like the Stanford overview) and one “how to build” talk to see agents from both angles.
Step 3: Build a Real Agent with Open-Source Repos
Now it’s time to actually build.
GenAI Agents (end-to-end agents repo)
Comprehensive tutorials and implementations from simple to advanced agents. Great for copying patterns and modifying them.
https://github.com/NirDiamant/GenAI_AgentsAI Agents for Beginners – Microsoft (structured course)
A 10–12 lesson course on design patterns, tool use, agentic RAG, multi-agent design, and going to production.
GitHub course: https://github.com/microsoft/ai-agents-for-beginners
Course site: https://microsoft.github.io/ai-agents-for-beginners/
Suggested weekend challenge:
Start from a simple tutorial in GenAI Agents (for example, a data-analysis or tool-using agent).
Use one or two patterns from AI Agents for Beginners (like Tool Use or Planning design pattern) and upgrade that agent.
By Sunday night, you’ll have an agent that does something concrete for you (summarizing docs, analyzing CSVs, planning tasks, etc.).
Step 4: Level Up with the Hugging Face Agents Course
If you want something more structured with a certificate and real deployments:
Hugging Face AI Agents Course
Learn agent concepts, then build and publish agents to Hugging Face Spaces using libraries like smolagents, LlamaIndex, and LangGraph.
Intro: https://huggingface.co/learn/agents-course/en/unit0/introduction
Agents basics: https://huggingface.co/learn/agents-course/en/unit1/introduction
Use this to:
Take what you built from the repos above.
Rebuild or refine it in their ecosystem.
Publish it as a Space so you can share a live URL with your team or clients.
Optional: Go Deeper on Design Patterns and RAG
If you still have time (or want to extend into next week), skim these:
Google’s Agent Whitepaper – High-level concepts and architectures.
https://lnkd.in/gFvCfbSNBuilding Effective Agents – Anthropic
Practical guidance on making agents reliable and useful.
https://lnkd.in/gRWKANS4OpenAI’s Practical Guide to Building Agents
Concrete implementation tips and pitfalls.
https://lnkd.in/guRfXsFKRetrieval-Augmented Generation (RAG) Survey
A broad overview of RAG techniques and trade-offs.
https://lnkd.in/gGUqkkyR
Focus on one question as you read: “How can I apply this to the agent I just built?”
If you follow this flow: foundations → agent concepts → build from a repo → refine with a course you’ll go from “I’ve saved a bunch of links” to “I shipped my first real AI agent” in a single weekend.
Most coverage tells you what happened. Fintech Takes is the free newsletter that tells you why it matters. Each week, I break down the trends, deals, and regulatory shifts shaping the industry — minus the spin. Clear analysis, smart context, and a little humor so you actually enjoy reading it. Subscribe free.