LLMs for Everyone
Learn to apply the latest prompting techniques and tools to build use cases and applications with LLMs.
This course is no longer available.
Explore other coursesTRUSTED BY
Course overview
Effectively prompting and building with LLMs
OVERVIEW OF THE COURSE
LLMs (Large Language Models) show powerful capabilities, but not knowing how to effectively and efficiently use them often leads to reliability and poor performance. Prompt engineering helps to improve discover capabilities, improve reliability, reduce failure cases, and save on computing costs when building with LLMs.
This hands-on course expands your prompting skills to effectively use and build with LLMs. It covers the latest prompting techniques (e.g., few-shot, chain-of-thought, RAG, prompt chaining) that you can apply to a variety of complex use cases such as building personalized chatbots, LLM-powered agents, prompt injection detectors, LLM-powered evaluators, and much more.
Topics include:
• Taxonomy of Prompting Techniques
• Tactics to Improve Reliability
• Structuring LLM Outputs
• Zero-shot Prompting
• Few-shot In-Context Learning
• Chain of Thought Prompting
• Self-Reflection & Self-Consistency
• ReAcT Prompting Framework
• Retrieval Augmented Generation (RAG)
• Fine-Tuning & RLHF
• Function Calling & Tool Usage
• LLM-Powered Agents
• LLM Evaluation & Judge LLMs
• AI Safety & Moderation Tools
• Adversarial Prompting (Jailbreaking and Prompt Injections)
• Common Real-World Use Cases of LLMs
• Prompt Engineering for models like GPT-3.5/4, Mixtral, Gemini, and others
... and much more
PREREQUISITES
• We will explore and build with no-code tools.
• No knowledge of programming is required.
• Basic knowledge of LLMs is beneficial but not required.
If you have experience using Python, we recommend our advanced course: https://maven.com/dair-ai/prompt-engineering-llms
ABOUT THE INSTRUCTOR
Elvis, the instructor for this course, has vast experience doing research and building with LLMs and Generative AI. He is a co-creator of the Galactica LLM and author of the popular Prompt Engineering Guide. He has worked with world-class AI teams like Papers with Code, PyTorch, FAIR, Meta AI, Elastic, and many other AI startups.
Reach out to training@dair.ai for any questions, corporate training, and group/student discounts.
WHO THE COURSE HAS HELPED
This course has helped AI startups freelancers, and professionals at companies like Microsoft, Google, LinkedIn, Amazon, Coinbase, Asana, Airbnb, Intuit, JPMorgan Chase & Co, and many others.
Who is this course for
01
Professionals who want to explore and build with LLMs.
02
Developers who want to improve LLM reliability, efficiency, and performance for their use cases and applications.
03
Leaders who want to lead their teams to build innovative products with LLMs.
What you’ll get out of this course
Design and optimize prompts
- Learn key elements and tactics for designing effective prompts
- Design, test, and optimize prompts to improve model performance and reliability for useful and common tasks such as code generation, text summarization, and information extraction
Build a robust framework to effectively apply advanced prompt engineering techniques
- Review and apply the latest and most advanced prompt engineering techniques (few-shot learning, chain-of-thought, RAG, prompt chaining, self-consistency, self-verification, etc.)
- Familiarize and build with approaches like ReAct, RAG, and LLM-powered agents.
Develop use cases and build applications
- Develop use cases such as tagging systems, personalized chatbots, evaluation systems, product review analyzers, and more
- Build advanced applications that involve combining conversational assistants with external tools and knowledge bases
Perform evaluations for your applications
- Design a framework for evaluating and measuring the quality, diversity, safety, and robustness of LLMs
- Compare prompt engineering, RAG, and fine-tuning
- Cover AI safety topics like prompt injection and moderation tools
Learn prompt engineering tools
- Review the latest prompt engineering and LLM tools such as ChatGPT, Llama Index, Comet, LangChain, Flowise, Scale AI's Spellbook, and others
- Discuss current trends, papers, and future directions in prompt engineering
What’s included
Live sessions
Learn directly from Elvis Saravia in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
6 live sessions • 4 lessons • 4 projects
Week 1
Discuss the key elements of designing an effective prompt
Design prompts for common tasks such as question answering and information extraction
Apply a taxonomy of popular prompting techniques such as role-playing, zero-shot, and few-shot learning
- 📄
Slides and Materials
- ✍️
Session 1 Exercises
Submit by Sep 17 Effectively apply advanced prompting techniques like prompt chains, chain-of-thought, ReAct, and RAG to improve the performance of LLMs
Improve model reliability, consistency, efficiency, and performance
Learn common LLM use cases
- 📄
Slides and Materials
- ✍️
Session 2 Project
Submit by Sep 18 Learn about techniques and approaches for assessing model safety, toxicity analysis, mitigating bias, reducing hallucination, and evaluating prompt injections
Apply different approaches for evaluating LLMs for tasks such as text classification, information extraction, and summarization
Review the latest tools and best practices for prompt engineering to effectively build with language models
Compare prompt engineering techniques with fine-tuned models and RAG
Cover end-to-end, real-world use cases and applications, such as combining conversational bots with external tools and knowledge
Discuss current papers, trends, recommendations, predictions, and future directions
- 📄
Slides and Materials
- ✍️
Final Project
Submit by Sep 20
Sep
16
LLMs for Everyone - Session 1
Sep
17
LLMs for Everyone - Session 2
Sep
17
Optional: LLMs for Everyone - Office Hour 1
Sep
18
LLMs for Everyone - Session 3
Sep
18
Optional: LLMs for Everyone - Office Hour 2
Sep
19
LLMs for Everyone - Session 4
Session 1 - Structuring Effective Prompts
Session 2 - Advanced Prompting & Improving LLM Reliability
Session 3 - LLM Evaluation & AI Safety
Session 4 - LLM Tools & Applications
What students are saying
Meet your instructor
Elvis Saravia
Elvis Saravia
Elvis is a co-founder of DAIR.AI, where he leads all AI research, education, and engineering efforts. His primary interests are training and evaluating large language models and developing applications on top of them. He is the co-creator of the Galactica LLM and was a technical product marketing manager at Meta AI where he supported and advised world-class teams like FAIR, PyTorch, and Papers with Code. Prior to this, he was an education architect at Elastic where he developed technical curriculum and courses.
Course schedule
3-5 hours per week
Live Sessions
4 x 1.5 hour sessions
Live sessions, demos, exercises, and projects
Live Office Hours
1 hour
Optional office hours to ask questions and receive guidance related to the course topics
Bonus Content
2 hours per week
Includes additional readings and self-paced tutorials + bonus exercises to practice prompt engineering techniques and tools for different use cases and applications
1-on-1 Sessions
30 mins
Book a free 1-on-1 session with the instructor to further discuss careers, products, use cases, or anything related to building with LLMs.
Learning is better with cohorts
Active hands-on learning
This course builds on live workshops and hands-on projects
Interactive and project-based
You’ll be interacting with other learners through breakout rooms and project teams
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you