Overview
This course introduces learners to the evolving field of Agentic AI, focusing on the transition from simple prompt-based interactions to intelligent systems capable of autonomous decision-making. It begins with the fundamentals of artificial intelligence and large language models, followed by practical techniques in prompt engineering.
The course further explores how AI agents are designed, including their core components such as perception, memory, reasoning, and action
Our Trainers
Ratnam Sachan
AI Product Manager with 3+ years building and shipping LLM-powered products across BFSI and creator-economy platforms. Shipped production AI voice agents and agentic automation that improved qualified-lead conversion by 80% for multiple lending clients. Skilled in LLM product strategy, prompt engineering, Retrieval-Augmented Generation (RAG), AI agent orchestration, model evaluation, and translating model outputs into measurable product experiences.
Modules
???? Module 1: Introduction to AI & Agentic AI (Foundation)
- Evolution of Artificial Intelligence
- From rule-based systems to Generative AI
- Concept of Agentic AI
- Difference: Prompt-based AI vs Autonomous AI
- Applications and current trends
Outcome: Understand the basics and need for Agentic AI
???? Module 2: Prompt Engineering & LLM Interaction
- Basics of Large Language Models (LLMs)
- Prompt engineering techniques (zero-shot, few-shot, chain-of-thought
Outcome: Ability to create optimized prompts for desired outputs
???? Module 3: Architecture of AI Agents
- Components of AI agents:
- Perception
- Memory
- Reasoning
- Action
- Types of agents (Reactive, Deliberative, Hybrid)
Outcome: Understand how intelligent agents are structured and operate
???? Module 4: Building Agentic Systems
- Transition from prompt → agent
- Tool usage and API integration
- Multi-step reasoning and task execution
Outcome: Ability to design simple AI agents
???? Module 5: Autonomous Intelligence & Decision Making
- Planning and goal decomposition
- Autonomous task execution
- Feedback loops and self-improvement
- Multi-agent systems
- Case studies (automation, assistants, robotics)
Outcome: Understand how AI systems act autonomously
Outcomes
1.Understand the fundamental concepts of Agentic AI, including the evolution from traditional prompting to autonomous decision-making systems.
2.Apply effective prompt engineering techniques to guide AI models toward desired outputs in real-world scenarios.
3.Demonstrate the ability to integrate AI agents with APIs, tools, and external data sources for building intelligent workflows.
4.
Develop critical thinking on the future of AI, focusing on the transition from human-in-the-loop systems to fully autonomous intelligence.
FAQs
1. What is Agentic AI?
2. How is Agentic AI different from prompt-based AI?
3. What are AI agents?
4. What are the key components of an AI agent?
5. What is prompt engineering?
Contact
Name: Prof. Manoj Shinde
Mobile No: 9827629872
