Agentic AI Engineering with Anthropic Claude Technologies Course

• Ways of working with LLMs/ SLMs (Small Language models)
• Prompt Engineering/ Prompting LLMs
• Metaprompting with examples
• Building apps with Claude code- Overview

Lab 2: Advanced Prompt Engineering

• Context Engineering vs Prompt Engineering
• Finetuning LLMs and Finetuning vs Context Engineering

Lab 3, 4- Context Engineering

• Demo- Claude APIs- Responses API, Chat Completion API, Realtime API, Assistants API, Batch API

Lab 5- Working with Claude APIs

• Retrieval Augmented Generation (RAG) for knowledge/ information querying/ availability (static & dynamic, real-time)
• AI Agents with examples
• Overview of agent skills to build specialized agents.
• Demo: General AI Agent (Manus AI)
• Reasoning in AI Agents and use of Reasoning models
• Claude model pricing

• Data pipeline for RAG
• Demo/ Code walkthrough- Naïve RAG with Claude LLM
• Breakout Room Activity- Understanding code/ flow of an E2E RAG pipeline
• Business use cases of RAG Apps across Industries and Horizontals/ Functions, including Vertical AI Agents
• Chunking Strategies
• Creating Vector embeddings and storing them in a Vector database, with examples
• Retrieval Mechanics & Similarity/ Vector search techniques
• Langchain, Llamaindex/ coding frameworks for RAG Development
• Techniques for improving RAG accuracy- Reranking, chunk optimization, others
• Langflow for low-code, no-code visual modeling-based RAG development
• Advanced RAG techniques – Agentic RAG, GraphRAG
• Demo: Code walkthrough of a RAG App

Lab 6- Building RAG App with Langflow- low-code no-code tool

Lab 7- Building RAG App with Python-based coding framework

• Building RAG App with Claude Code

Lab 8- Building RAG App with Claude Code

• AI Agent Architectures and how to select SLM/ LLM for agents
• Claude Agent SDK
• Architectures & demos – Design patterns of AI Agentic workflows- Reflection, Tool use/ function calling, Planning, Multi-agent collaboration
• Business use cases of AI Agents across Industries and Horizontals/ Functions, including Vertical AI Agents
• Technical use cases of AI Agents (in SDLC automation)
• Step-by-step – Designing an AI Agent (with examples)
• Agentic Memory – Long-term, short-term, with demos
• Claude Computer Control and Agents controlling browser, keystrokes, and mouse clicks/ computer control (Claude Desktop tool)
• AI Agent/ Agentic AI Pricing models & how they are disruptive to existing SAAS models
• Breakout Room Activity: Building use case and specs for an AI Agent
• Agent Skills & Agents.md

Lab 9: Building an Analytics dashboard with graphs & charts using Claude Agent Skills.

Lab 10: Building Agents with Agents.md

• Technical architectures for AI Agent development – General and on AWS/ GCP/ Azure
• Model Context protocol (MCP), MCP Server, Host & Client
• Connecting Agents with 3rd party apps using MCP Servers
• Demo- Setting up MCP Servers on Cline and GitHub Copilot in VSCode
• Demo- Working with MCP Servers from Zapier, Composio, Azure
• MCP Server Security
• Agentic coding with Claude Code
• Getting website data using MCP-B and llms.txt
• Real-time web data access with tools like Tavily, Serper, etc

Lab 11- Building an AI Agent with Tool use/ function calling and MCP Server integration

• Introduction to Langgraph for building AI Agents
• Demo- Building an AI Agent with Langgraph

Lab 12 – Building an AI Agent with AWS Strands SDK

• Introduction to AWS Strands SDK for building AI Agents
• Demo- Building an AI Agent with AWS Strands SDK

Lab 13 – Building an AI Agent with AWS Strands SDK

• Introduction to Google Agent Development Kit for building AI Agents
• Demo- Building an AI Agent with the Google Agent Development Kit

Lab 14- Building an AI Agent with the Google Agent Development Kit

• Demo- Building an AI Agent with Langflow

Lab 15- Building an AI Agent with Langflow- no-code, low-code tool

• LLM/SLM selection for AI Agents/ Agentic AI
• Demo: Reflection in AI Agents
• Building multi-agent systems
• Google Agent2Agent (A2A) Protocol for multi-agent collaboration with demo
• Demo: Multi-agent collaboration

Lab 16- Multi-agent collaboration with Google A2A Protocol

Lab 17, 18- Building Agent with Langgraph & Long-term, short-term memory

• Working with Claude Co-work
• Examples of Agentic systems/subcomponents in Claude Co-work

• Agent Performance evaluation & observability
• Agent Security
• Agent deployment & scaling options on Cloud
• Agent deployment on local servers/ edge
• Post-production considerations for AI Agents
• AI Safety via Guardrailing

Lab 19, 20: Agent Evaluation/ LLM-as-a-judge

• BreakOut Room Activity – Design Cloud architecture for AI Agent Deployment

• AI Ethics, Risk & Governance via Responsible AI framework
• AI Regulations- EU AI Act, California AI Bill, others
• Constitutional AI and Sovereign AI incl European AI Cloud