Prompt Engineering for LLMs
8.5
(35 ratings)
2 Weeks
·Cohort-based Course
Use the latest prompt engineering techniques and tools to improve the capabilities, performance, and reliability of LLMs.
Prompt Engineering for LLMs
8.5
(35 ratings)
2 Weeks
·Cohort-based Course
Use the latest prompt engineering techniques and tools to improve the capabilities, performance, and reliability of LLMs.
Hosted by
Elvis Saravia
Founder & Lead AI Scientist @ DAIR.AI, Prev: Meta AI, Galactica LLM, Elastic
Course overview
Effectively building and exploring with LLMs
LLMs (Large Language Models) show powerful capabilities, but not knowing how to effectively and efficiently use them often leads to unexpected behaviors. Prompt engineering helps to reduce failure cases and computing costs when building with LLMs.
Prompt Engineering for LLMs is a 4-day hands-on course that teaches how to efficiently and effectively use LLMs. It covers the best and latest prompting techniques that you can apply to a variety of use cases that range from building long article summarizers to prompt injection detectors all the way to LLM-powered evaluators.
We are excited to launch two new cohorts!
Cohort 3 (Beginners) is for beginners. You will learn how to properly design and optimize your prompts for a variety of use cases using no-code tools.
Cohort 4 (Intermediate to Advanced) is for advanced participants who already have basic knowledge of machine learning and LLM concepts and are comfortable coding in Python.
Regardless of the level, be ready to dive deep and acquire advanced skills to create and build with LLMs. To provide the best value, we cover roughly the same syllabus for both cohorts, the only differences are the tools used and the level of exercises, technical explanations, and projects. By the end of the course, the goal is NOT to teach you the "10 best prompts". The goal is for you to learn how to apply advanced prompting techniques to help you grow in your career, build personal projects, or build advanced LLM-powered products.
Make sure to pick the right cohort based on your experience. Find the schedule for each cohort below.
Elvis, the instructor for this course, has vast experience doing research and building with LLMs. He is a co-creator of the Galactica LLM and author of the popular Prompt Engineering Guide. He has worked with world-class teams like Papers with Code, PyTorch, FAIR, Meta AI, Elastic, and many other AI startups.
This course has helped AI founders, freelancers, and professionals at companies like Microsoft, Google, LinkedIn, Amazon, Coinbase, Inuit, JPMorgan Chase & Co, and many others.
Who is this course for
01
Developers building applications on top of LLMs
02
Builders wanting to improve LLM reliability and reduce LLM failure cases using advanced prompting techniques.
03
Professionals interested in leveling up on how to better use and apply 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 different tasks such as text summarization and information extraction
Apply advanced prompt engineering techniques and AI safety
- Review and apply the latest and most advanced prompt engineering techniques (few-shot learning, ReAct, chain-of-thought, RAG, tree of thought, self-reflection, etc.)
- Design a robust framework for evaluating and measuring the quality, diversity, safeness, and robustness of LLMs
Study use cases and applications
- Apply prompting techniques with LLMs for a series of common use cases and applications
- Cover advanced use cases such as combining knowledge with conversational assistants and using LLMs with external tools
Learn prompt engineering tools
- Review the latest prompt engineering tools such as LangChain, DUST, Scale AI's Spellbook, and many more
- Discuss current trends and future directions in prompt engineering
Prompt Engineering for LLMs
Meet your instructor
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.
Be the first to know about upcoming cohorts
Prompt Engineering for LLMs
Course syllabus
01
Structuring Effective Prompts
- Discuss the key elements of designing an effective prompt
- Format prompts for common tasks using a taxonomy of prompting techniques like in-context learning and chain-of-thought prompting
- Use prompt engineering tools such as LangChain and OpenAI Python client to test prompt engineering techniques and tactics
02
Advanced Prompting Techniques & LLM Reliability
- Apply advanced prompting techniques like ReAct to improve the performance of LLMs
- Improve model reliability and enhance LLM performance
- Learn cost-effective and efficient prompting tactics
- Learn from a case study about a data-augmented question-answering tool
03
Evaluating LLMs & AI Safety
- Discuss prompting techniques and approaches for assessing model safety, toxicity analysis, mitigating bias, reducing hallucination, and testing prompt injections
- Applying different approaches for evaluating LLMs for tasks such as text classification and summarization
- Evaluate and compare prompt engineering techniques with fine-tuned models
04
Prompting Tools, Advanced Use Cases, & Applications
- Review the latest tools and best practices for prompt engineering to effectively build with language models
- Discuss end-to-end, real-world use cases and applications, such as combining knowledge with conversational bots and using LLM with external tools
- Discuss current papers, trends, recommendations, and future directions
8.5
(35 ratings)
What people are saying
Yevgeniy S. Meyer, Ph.D.
Miguel Won
Yashwanth (Sai) Reddy
Lawrence Wu
Course schedule
4-6 hours per week
Cohort 3 - Mondays & Thursdays
Aug 21, 24, 28, 31 - 12:00-2:30 PM PST
Level: Beginner
Cohort 4 - Tuesdays & Thursdays
Sep 5, 7, 12, 14 - 12:00-2:30 PST
Level: Intermediate to Advanced
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
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