What You'll Learn

Prompt Engineering is a cutting-edge course designed for those who wish to master the art of interacting with and manipulating large language models. Through a series of workshops, participants will learn to create complex prompts, develop benchmarks, jailbreak models, automate conversations, and much more. The course emphasizes practical skills alongside theoretical knowledge, preparing students for advanced applications in AI.

- Develop complex prompts and rubrics for AI artifacts - Benchmark testing for prompts and templates - Techniques for 'jailbreaking' large language models - Automating and hosting conversations with AI - Using no-code tools for AI automation and scheduling - Coding alongside large language models - Running open source large language models - Aligning AI outputs to human values - Creating metalanguages for symbolic reasoning and narrative design

Course Schedule

6 Weeks
16.5 Classroom Hours

Week 1 2 sessions

Complex Prompts and Benchmarks

Tuesday, April 23 at 5:00 PM - 6:30 PM PDT

Develop a complex prompt and rubric for artifacts you commonly produce with AI. Develop a benchmark to test a prompt or prompt template. Use Self-consistency to improve model performance

1.5h

Jailbreaks

Thursday, April 25 at 5:00 PM - 6:30 PM PDT

Jailbreak a large language model out of its alignment guidance. Review jailbreaking techniques, practice them with some jailbreaking games. Add red-team prompts to your benchmark from Workshop 1

1.5h

Week 2 2 sessions

Thought Architectures and Augmented Skills

Tuesday, April 30 at 5:00 PM - 6:30 PM PDT

Define, Write, and Deploy an entire application with a large language model. Decompose the above process into a Swarm of Agents

1.5h

Tools

Thursday, May 02 at 5:00 PM - 6:30 PM PDT

Use (code or) no-code tools to automate actions a large language model can take. Use (code or) no-code tools to trigger a large language model on a schedule

1.5h

Week 3 2 sessions

Society of Mind

Tuesday, May 07 at 5:00 PM - 6:30 PM PDT

Host a conversation between multiple personas using a large language model. Decompose an agent into a series of smaller agents. Use Autogen to host a conversation between an actor and a critic

1.5h

Autogen

Thursday, May 09 at 5:00 PM - 6:30 PM PDT

Automatically host a conversation between multiple personas using a large language model. Re-Implement the SDLC from the third workshop using an agent hierarchy. Implement a multi-agent swarm

1.5h

Week 4 2 sessions

Swarm Architecture

Tuesday, May 14 at 5:00 PM - 6:30 PM PDT

Implement Actor-Critic using Autogen. Implement a multi-stage swarm using Autogen. Implement Code Execution in Autogen

1.5h

Alignment

Thursday, May 16 at 5:00 PM - 6:30 PM PDT

Align a large language model's outputs to human values using prompt engineering techniques according to state-of-the-art research

1.5h

Week 5 2 sessions

Meta-languages & Meta Narratives

Tuesday, May 21 at 5:00 PM - 6:30 PM PDT

Develop a metalanguage to allow a language model to reason at a symbolic level about a specific problem domain. Develop a metalanguage to allow for narrative design that can be held in available conversational context windows, allowing for the generation of novels and longer-form objects

1.5h

Final Project

Thursday, May 23 at 5:00 PM - 6:30 PM PDT

Integration and application of learned skills.

1.5h

Week 6 1 session

Flexible Session

Thursday, May 30 at 5:00 PM - 6:30 PM PDT

Flexible session for overflow or additional content.

1.5h

All times shown in Pacific Time (PT)

Who Is This Course For

Professionals and enthusiasts with a foundational understanding of large language models looking to expand their skill set in prompt engineering and AI interaction.

Join the Course

Pay what you can - accessible learning for all

We use a suggested price to prevent abuse, but if you need a larger discount, email us at liz@themultiverse.school. We offer 100% scholarships - no one is turned away for lack of funds.

$ 220

Suggested price • Pay what you can

Join Now

Secure payment via Stripe

$ 299

Suggested price • Pay what you can

Join Now

Secure payment via Stripe

Want to schedule this course for your team?

Contact us: liz@themultiverse.school