AI for Tech

Use LLMs to help you code and create intelligent applications

Start the course →

Disclamer

LLMs and MMLLMs are constantly evolving, with new developer-oriented tools and practices continually emerging.

Summary

Module 1: Mastering LLMs throughout the Software Development Lifecycle (SDLC)

a. Introduction

Prerequisites - Key concepts and terminology - A bit of History - The market

b. Prompting usage in apps lifecycle

Understanding prompting techniques, developper usage of LLMs for coding, and the application lifecycle

c. Online/Offline LLMs clients (Librechat & LM Studio)

History, Favorites, Presets, Preformatted prompts, AI providers, Agent, Plugins & mixing, RAG, Installation, Model configuration, enable APIs...

d. Code Assistants in IDEs (Copilot)

GitHub Copilot, and project generation with Bolt, v0

Module 2: Building Intelligent Applications

a. GenAI for services (langchain, llama-index)

LLM API calls, Developpement with LangChain, Python notebooks, Context aware frameworks, RAG, Vector databases, Agents, Model Context Protocol

b. Agentic AI for services

Understanding Agentic AI, Langchain Agents, Model Context Protocol (MCP), MCP clients and servers, skils

c. Agentic AI node-based tools

Node based genAI tools overview, N8N introduction, Agentic architecture with node based tools

d. Agentic AI in the Cloud

Overview of Cloud tools (Vertex AI, Google Colab notebooks, etc.), Utilizing AI Cloud APIs (Text-to-Speech, Translation, etc.), deploying AI solutions in the cloud

About

avatar

We design payments technology that powers the growth of millions of businesses around the world. Engineering the next frontiers in payments technology