Home

Prompting with AVA

In the AI era, "prompting" has gained new significance. It's how we communicate instructions and information to AI agents for solving specific problems. At its simplest, prompting can be as basic as "Create an RFP," but advanced prompting is much more than asking questions—it's a powerful tool that, when used effectively, unlocks a world of possibilities. In skilled hands, prompting transforms vague ideas into clear, actionable content, streamlines complex tasks, and drives innovation. This section will provide you with effective strategies for prompting AVA, helping you harness its full potential.

Tips for Beginners

• Be Clear and Concise
• Break Down Complex Requests
• Provide a Style Example
• Use Prompt Patterns

Prompt Patterns

Prompting patterns are structured approaches to crafting prompts that enhance the quality and relevance of AVA's responses. By using these patterns, you can create more effective prompts and get the most out of your interactions. AVA itself uses the RAG pattern within AVA Tasks.

RAG Prompting

RAG Prompting (or Role-Action-Goal), is a technique that sets up your prompt in different categories, to set clear roles, actions, and goals.

• Role and Instructions
• Action
• Goal and Format

Alternative Patterns

RISE

• Request: Clearly state what you need.
• Information: Provide any necessary background information.
• Simplify: Break down complex requests into simpler, smaller tasks.
• Examples: Include examples or templates to guide the desired output.

CLEAR

• Context: Offer context around the task or question.
• Length: Specify the desired length or detail of the response.
• Expectation: Describe what a successful outcome looks like.
• Audience: Identify who the document or information is for.
• Revision: Request a specific number of revisions or iterations if needed.

SMART

• Specific: Be specific about what you're asking for.
• Measurable: Define how you will measure success or completion.
• Actionable: Ensure the request is something the AI can act on.
• Relevant: Make sure the request aligns with your current needs or goals.
• Time-bound: If applicable, set a deadline for when you need the response.

GUIDE

• Goal: State the goal of your request.
• Understand: Make sure the request is understandable and clear.
• Identify: Identify any key points or criteria that need to be addressed.
• Detail: Provide details that can help refine the AI's response.
• Explain: If necessary, explain why you're making the request or why it's important.

SuperPrompting

SuperPrompting is an advanced technique that leverages detailed and structured prompts to achieve highly specific and nuanced responses from AVA. This method is particularly useful for complex tasks where precision and depth are crucial. By breaking down tasks into granular components and providing comprehensive context, SuperPrompting maximizes the effectiveness of AVA's capabilities.

What is SuperPrompting?

SuperPrompting involves crafting prompts that are:

• Highly Detailed: Including all relevant information and context.
• Structured: Following a logical and organized format.
• Iterative: Allowing for follow-up prompts to refine and enhance the output.

Benefits of SuperPrompting

1. Enhanced Precision: SuperPrompting ensures that AVA understands the exact requirements, leading to more accurate and relevant responses.
2. Greater Depth: By providing extensive context and details, SuperPrompting enables AVA to generate more comprehensive and insightful outputs.
3. Improved Efficiency: SuperPrompting reduces the need for multiple revisions and back-and-forth communication, streamlining the task execution process.

Example?

Knowledge Search Prompting

Need quick facts, research, or answers to specific queries? AVA is at your service. Here's how to conduct an effective knowledge search:

• Ask Precise Questions: Instead of "Tell me about our health plan," ask, "What are the benefits of the Gold Standard Plan for full time Employees?"
• Context Is Key: If you're looking for industry-specific information, mention it, like, "Explain the GDPR implications for healthcare data storage."
• Review and Refine: If the first answer isn't quite right, refine your question based on the information provided, or ask for more details on a specific aspect.

Table of Contents