Knowledge and Prompt Engineering

Part 2: Focus on Prompt Design Approaches



Topics We'll Cover

Structured Prompting

Learn how to structure prompts based on use cases, scenarios, and the RACE framework (Role, Action, Context, and Examples).

Aligning with Knowledge Engineering

Explore how the prompt design framework needs to align with and take signals from the knowledge engineering framework.

Customizing the Framework

Learn about the situational factors that affect the prompt framework:

  • Capability – Are you interacting with a chatbot or an assistant?
  • Model – Which LLM are you working with: OpenAI's GPT, Mixtral, Llama2, or another?
  • Use case – Do you need translation, generation, or a Q&A system?
  • Mode – Are you working with text, vision, or voice?
  • Action – Function calling or fine-tuning?

Optimizing Prompts

Find techniques to help you write your best prompts to achieve the best responses from an LLM:

  • Work through problems step-by-step using Tree of Thought (ToT), chain of thought, or iterative prompting techniques
  • Inject emotion to prompt emotionally engaging language
  • Include corporate brand guidelines, terminology, and data sources; user signals from prior interactions; and industry-specific data to improve LLM performance

Media Partner

VKTR (pronounced vector) Logo

VKTR (pronounced vector) is your guide to AI @ work. Sign up today, for free.