6th Semester
Applied AI & Agentic Systems
Design AI systems that retrieve, reason, and act
This advanced program focuses on Generative AI, LLM-based systems, retrieval-augmented generation, and agent workflows, aligned with current industry practices.
Overview
This advanced course focuses on building modern AI systems using Generative AI, Large Language Models (LLMs), retrieval-augmented generation (RAG), and agent-based workflows. Students learn how real-world AI products are designed by combining LLMs with external knowledge sources, tools, and structured machine learning pipelines. The program emphasizes practical system design, controlled AI behavior, and responsible deployment, culminating in a portfolio-ready applied AI project aligned with current industry practices.
Course Outcome
By the end of the course, students will be able to:
- Explain the architecture and working of modern AI systems built using LLMs and generative models.
- Design and implement prompt-driven and API-based AI applications with controlled outputs.
- Build retrieval-based AI systems using embeddings, semantic search, and RAG architectures.
- Develop agent-based workflows that integrate tools, APIs, and external knowledge sources.
- Understand the role of supporting ML pipelines, evaluation, and deployment considerations.
- Design and demonstrate a functional applied AI system suitable for real-world use cases.
FORMAT : Hybrid
DURATION : 12 Weeks
HOURS PER WEEK : 2 HOURS
NO OF VIDEO CONTENT : 12
NO OF ASSIGNMENTS : 6
Syllabus
Course Syllabus
AI Foundations & Modern AI Systems
Week 1
Students are introduced to the evolution of AI and the structure of modern AI systems. The session covers key concepts behind generative models and how AI is used in real products today.
Large Language Models & Applications
Week 2
This week explores Large Language Models, their capabilities, and limitations. Students study real-world use cases such as chatbots, copilots, and AI assistants.
Prompt Engineering & Output Control
Week 3
Students learn prompt engineering techniques to guide and control LLM behavior. The focus is on structured prompts, constraints, and reliable output generation.
Multimodal AI & Image Generation
Week 4
This module introduces multimodal AI concepts, including text-to-image systems. Students explore workflows involving image generation and multimodal reasoning.
Text Intelligence Using LLM APIs
Week 5
Students work with LLM APIs to build text-based intelligence systems. Topics include summarization, classification, extraction, and conversational interfaces.
Embeddings & Semantic Search
Week 6
This week focuses on embeddings and vector representations. Students build semantic search systems to retrieve relevant information based on meaning rather than keywords.
Retrieval-Augmented Generation (RAG)
Week 7
Students learn RAG architectures that combine retrieval with generation. The session covers document ingestion, retrieval pipelines, and response grounding.
AI Systems with External Knowledge Sources
Week 8
This module focuses on integrating AI systems with databases, files, and APIs. Students learn how AI systems access and reason over external knowledge.
Agent-Based Workflows & Tool Use
Week 9
Students explore agentic systems where AI models plan, decide, and take actions using tools. Topics include task decomposition, tool calling, and multi-step workflows.
Supporting ML Pipelines for AI Systems
Week 10
This week introduces machine learning pipelines that support AI systems, including data flows, evaluation, and monitoring concepts essential for production readiness.
Responsible AI & Deployment Basics
Week 11
Students learn responsible AI principles such as bias, safety, and reliability. The session also introduces basic deployment considerations for applied AI systems.
Capstone Project Demonstration
Week 12
The course concludes with capstone project demonstrations. Students present applied AI systems showcasing retrieval, reasoning, and agent-based capabilities.
learning experience
WHAT STUDENTS TAKE AWAY
- Practical exposure to modern AI system design
- Understanding of LLM, RAG, and agent workflows
- Portfolio-ready applied AI project
Learners targeting applied AI and GenAI roles.
Build AI systems used in real products.
