Prompt Engineering - Spring (M & W 5PM Pacific)

- **Emotional Priming**: Enhance output quality - **Structured Notes**: From vocal to formal - **Brainstorming Aid**: Ideate with AI - **Data Structuring**: Unstructured to organized - **Summarize Documents**: Condense lengthy texts - **First-Pass Editing**: AI-assisted editing - **Token Recognition**: Understand inference roles - **Model Comparison**: Differentiate AI models - **Limitation Awareness**: Acknowledge AI biases - **Hyperparameter Tuning**: Customize output - **System Prompts**: Set preferences easily - **Data Analysis**: Simplify complex analysis - **Plan Critique**: Evaluate and improve - **Language Efficacy**: Sharpen prompt performance - **Sparse Priming**: Knowledge decomposition - **Value Alignment**: Reflect human ethics - **Thought Chains**: Enhance reasoning - **Critical Skills**: Boost output reliability - **Rubric Creation**: Guide AI responses - **Expert Reviewers**: Refine AI output - **Prompt Optimization**: Expert-level prompts

Learn how to set up and use Claude Model Context Protocol, install multiple servers, configure new servers, and understand security best practices.

Deep dive into embedding models (BERT, Sentence-Transformers), efficient vector search algorithms (FAISS, HNSW), vector database performance optimization, neural re-rankers, and techniques for training custom embedding models tailored to your specific domain.

- 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

- Design and implement request-response agents for various applications - Create retrieval-augmented agents that can access and utilize external knowledge - Develop autonomous agents that can take actions based on goals and environmental context - Implement utility AI with different operational modes for more sophisticated agent behavior - Build multi-process agents that leverage traditional AI tools for stable and predictable performance - Design and prototype agent swarms for collaborative problem-solving - Reuse and adapt existing agents for new applications and contexts - Understand the principles of agent architecture and communication

- Write effective system prompts for regularized outputs or tool use - Design and implement agents capable of using, creating, and managing tools - Develop agents with autonomous action capabilities, including scheduling and event-triggered responses - Utilize open-source tool hubs designed for Large Language Models - Manage and economically host large vector stores - Construct self-improving agents that can evolve their prompts - Create and manage swarms of agents collaborating on complex goals - Design meta-swarms and information hierarchies for advanced agent collaboration and secrecy - Evaluate and create benchmarks for LLM performance analysis