Why the Lang Stack?

One Goal. Many Frameworks.

Concepts appear as they come up…

In the previous Vibe, we learned

00:00/01:48

1 / 1

One Goal. Many Frameworks.

Certisured is an Edtech based out of Bangalore and is Co-founding team of Wizori - built to provide quick fundamental clarity in form of short vibes.

www.certisured.com

One Goal. Many Frameworks.

Loading comments…

Continue your learning — your way

Sign in to unlock the full playlist, save your progress, and get a personalized feed.

Up next

AI for Hardware Tinkering
7:02·3 eps
The Shape of Randomness
9:54·4 eps
MODULE 8 — Tools of the Trade: From Concepts to Components
2:09
MODULE 5 — System Prompts: The Hidden Conversation
2:36
MODULE 6 — Tools: When an LLM Learns to Act
2:46
MODULE 2 — What the Model Actually Sees (The Anatomy of Context)
3:30
MODULE 9 — RAG: Teaching the Model to Read Before It Answers
3:17
MODULE 3 — The Context Window: The World the LLM Can See
5:20
MODULE 10 — Vector Databases: Teaching AI to Search by Meaning
2:54
MODULE 4 — Memory Engineering: Teaching AI to Remember You
2:36
MODULE 1 — Introduction to Context Engineering
2:28
MODULE 12 — Long-Term Memory: Helping AI Remember What Matters
2:52

Why the Lang Stack? — full transcript

One Goal. Many Frameworks.

One Goal. Many Frameworks.

In the previous Vibe, we learned that an AI agent is not just a language model. It is an engineered system where we combine reasoning with memory, tools, workflows, and permissions to achieve a goal. But this immediately raises another question. Do we have to build all this from scratch? Fortunately, the answer is no. Over the past few years, several engineering frameworks have emerged to help developers build AI agents. Frameworks like CrewAI, Google's ADK, Microsoft's Semantic Kernel, OpenAI's Agents SDK, LlamaIndex, AutoGen, and many others all solve the same fundamental problem—how to orchestrate intelligent systems. Each framework has its own philosophy, strengths, and ideal use cases. In this series, however, we will focus on the **Lang Stack**—LangChain, LangGraph, and LangSmith. It has become one of the most widely adopted ecosystems for Python developers, offers excellent flexibility for building both simple and complex agentic workflows, has strong community support, integrates with hundreds of models and tools, and scales naturally from prototypes to production systems. More importantly, its design exposes the engineering concepts behind agentic systems instead of hiding them, making it an excellent framework for learning. Remember, our goal is not just to master one library. It is to understand the principles of Agentic Engineering. Once you understand those principles, learning another framework becomes much easier. So let's begin our journey with one of the most influential ecosystems in modern AI—the Lang Stack.