Syllabus
Python Foundations – Installing Python environment, IDE/editor setup, Variables, data types (int, float, string, boolean), Basic input/output operations, Control flow statements – if/elif/else, for loop, while loop, break/continue/pass, Functions – definition, return statement, scope, variable arguments (*args, **kwargs), Object Oriented Programming – classes, objects, constructors, methods, self keyword, inheritance, polymorphism, encapsulation, abstraction, Intermediate Python concepts – list comprehensions, generators, decorators, context managers, mutable and immutable objects.
Professional Tooling and Engineering Practices – Project setup using Python package managers and virtual environments, Dependency management, Project structure, Logging concepts – logging levels, handlers, formatters, Debugging techniques using IDE tools and pdb, Exception handling – try/except/finally, custom exceptions, Software testing using pytest, Writing unit tests, Running automated test cases, AI-assisted coding workflows, Prompting for code generation, Reviewing and validating AI-generated code.
LLMs – Concepts, APIs and Building with Confidence – Introduction to Large Language Models, Transformer architecture intuition, Pre-training and fine-tuning concepts, Tokenisation, context window, temperature, top-p sampling, hallucination in LLMs, LLM providers and API ecosystems, API authentication and rate limits, Multi-provider integration frameworks, First API integration using Python, Prompt engineering – zero-shot, few-shot, chain-of-thought prompting, System prompts and user prompts, Structured JSON output generation, Debugging with LLM assistance, Observability in LLM applications, Logging prompts, responses, token usage and latency.
LLM Security and Safe AI Development – Prompt injection attacks, jailbreak attacks, indirect prompt injection, Risks in LLM-based applications, Input sanitisation, Output validation, Instruction hierarchy, Secure system prompt design, Secure code generation practices, Risks of executing AI-generated code, OWASP-aware prompting, API key management, Secrets handling in prompts, Supply chain risks in AI frameworks, Building security checklists for LLM applications, Threat modelling for AI systems.
Agentic Applications and Capstone – Introduction to AI agents, Agent loop architecture, ReAct pattern, Tools vs agents vs workflows, Tool use and function calling, Structured tool outputs, Chaining tool calls, Building autonomous agents using Python, Agentic security principles, Principle of least privilege, Safe stopping conditions, Permission checks, Tool output validation, Evaluation and benchmarking of agents – accuracy, latency, cost, LLM-as-judge framework, Building evaluation harnesses, Design and development of capstone project based on agentic AI applications.