Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

Large language models (LLMs) and prompt design form the foundation of every generative AI application. This course explains how LLMs work and how to write prompts that produce accurate, consistent, and safe output. Through follow-along demos in Python, you will generate text with pretrained models, explore tokenization and attention, and apply prompting techniques to question answering, summarization, and classification tasks. By the end of this course, you will be able to: • Explain how transformers, tokens, embeddings, and attention drive LLM output. • Compare proprietary and open-source LLMs and assess responsible AI risks. • Design prompts using zero-shot, few-shot, and structured output techniques. • Apply chain-of-thought, tree-of-thought, and self-consistency prompting. • Defend prompted applications against prompt injection with human review. • Engineer context and manage token budgets for reliable responses. This course is designed for software developers, Python programmers, data analysts, and technical professionals beginning to build with generative AI. Basic Python skills will help you follow the demos, and no prior machine learning experience is required. Enroll now to build a working foundation in LLMs and prompt engineering.

Syllabus

Generative AI and Large Language Model Fundamentals
- Examine the foundations of generative AI by distinguishing it from discriminative AI and analyzing how LLMs generate text. Develop foundational skills by configuring a generative AI environment and generating text with a pretrained LLM. Build practical capabilities by evaluating the strengths and limitations of generative AI for real-world use.
Transformers, the Model Landscape, and Responsible AI
- Differentiate the core components of LLMs by examining transformers, embeddings, attention, and the training lifecycle. Develop foundational skills by exploring tokenization, visualizing attention, and comparing proprietary and open-source LLMs. Build practical capabilities by assessing model outputs for bias, safety, and misuse risks.
Prompt Anatomy, Shot-Based, and Task-Specific Prompting
- Analyze the anatomy of an effective prompt by examining role, task, context, format, and constraints. Develop foundational skills by constructing structured prompts and implementing zero-shot, one-shot, and few-shot prompting. Build practical capabilities by adapting prompts for common tasks, diagnosing weak prompts, and designing reusable templates.
Advanced Reasoning and Compositional Prompting Techniques
- Compare advanced reasoning strategies by examining chain-of-thought, tree-of-thought, self-consistency, generated-knowledge, and least-to-most prompting. Develop foundational skills by implementing each technique and contrasting direct and chain-of-thought answers. Build practical capabilities by combining techniques for complex tasks and justifying strategy selection.
Prompt Injection, Defences, and Human-in-the-Loop
- Evaluate the risks of adversarial prompting by examining how prompt injection attacks exploit LLM applications. Develop foundational skills by simulating an injection attack and implementing defences against it. Build practical capabilities by integrating human-in-the-loop review into an end-to-end prompted application.
Structuring, Retrieving, and Budgeting Context
- Evaluate the shift from prompt engineering to context engineering by examining the context window, retrieved context, and conversational memory. Develop foundational skills by structuring context, incorporating retrieved information, and maintaining memory across turns. Build practical capabilities by optimizing token budgets, compressing context, and composing context-engineered LLM solutions.

Taught by

Edureka

Reviews

Start your review of Getting Started with LLMs and Prompt Design

Taught by

Never Stop Learning.