CRAFT™️ Experiment: Claude 3.7: Rethinking A.I. Data Types (4 of 5)

The CRAFT™️ Experiment

May 5

Written By Richard Ketelsen

THE CRAFT™️ EXPERIMENT :: WEEK 3 :: POST 4

Claude 3.7: Rethinking A.I. Data Types

PROMPT:
Please read the attached project files.
# 01 - INITIAL PROMPT
PROMPT: "Hi, we will work together to brainstorm some content for my website. To begin, I will provide a 10-part prompt that will describe the following:
1. Personal Introduction: Who I am.
2. Content/Website Purpose: The website for which the content will be created and its intended purpose. This provides context for the chat.
3. About the Audience and Website : Target Audience, Pain Points & Unique Value Proposition, Competitive Edge and Elevator Pitch.
4. Content Goals: The objectives to achieve with the content.
5. Role of the A.I.: The expected role that you , the A.I. chat service, should assume in this process.
6. Content Source: The source from which the content will be derived.
7. Inspirations: Inspirations to guide you , the A.I. chat service, in understanding the type of content to create.
8. Constraints: Any specific constraints or aspects to avoid in the content creation process.
9. Ideas for visuals: Any ideas that I have for visuals that may be included in this content. Please do not create these visuals unless specifically asked to do so.
10. Related Stories/Content: If this content is part of a series, this will list and briefly explain the series and list any helpful URLS.
1) Personal Background and Site Overview - Based in Minneapolis, MN, USA, I am a professional in Computer Science and Graphic Design. I work for a Fortune 100 Company as a Senior Cybersecurity Incident Responder where I work with a team to keep people safe from cybersecurity attacks. In addition to 6 years in cybersecurity, my professional history includes 10 years as an Identity Designer and 10 years as an entrepreneur.
2) Website Content Purpose : the website is located at www.ketelsen.ai and is part of the blog section. Ketelsen.ai is An Ongoing AI prompt crafting Experiment. Ketelsen.ai is where the raw brainstorming and AI prompt engineering happens. Think of it as a lab where you consistently test out new prompt ideas, integrate various AI tools (ChatGPT, Midjourney, etc.), and see what sticks. The website features an Exclusive Prompt Collection with over 1,000 in-depth AI prompts covering real-world problems. These prompts are generated each week by multiple AI services, each with its own strengths. The website's Focus is on Breadth & Innovation. The site showcases new and creative ways to use AI—often pushing boundaries by running repeated “what if” experiments with different AI models. Because the goal is to innovate, Ketelsen.ai’s prompts can be very detailed (and at times, a bit overwhelming for newcomers).
3) About the Website:
Important details about Ketelsen.ai:
Step 1: Target Audience
• Demographics: Ages 25–45, global (English-speaking), professionals or entrepreneurs with moderate to high discretionary income.
• Psychographics:
○ Enthusiastic about AI-driven innovation and efficiency.
○ Enjoy experimenting with new technology but can feel overwhelmed by the sheer volume of AI options.
○ Prefer transparent “behind-the-scenes” exploration of prompt engineering.
• Persona Snapshot:
○ “Alex the AI Trailblazer”: 33-year-old product manager at a startup, craves cutting-edge AI prompts and advanced experimentation, wants to stay ahead with minimal wasted time.
Step 2: Pain Points & Unique Value Proposition
Top 3 Pain Points
1. Overwhelm by AI Options: Too many prompts/models to choose from, causing decision fatigue.
2. Difficulty Crafting Effective Prompts: Need guidance to avoid mistakes and harness AI fully.
3. Time Constraints for Testing: Users want quick, reliable feedback on what works without lengthy trial and error.
UVP (1–2 Sentences)
“Ketelsen.ai delivers a constantly evolving library of advanced AI prompts—over 1,000 and counting—so tech-savvy entrepreneurs can rapidly experiment without wasting time on guesswork. By focusing on real-world testing and transparent experimentation, it offers a more expansive and in-depth resource than other popular prompt-engineering websites.”
Step 3: Competitive Edge
1. Massive Prompt Library (over 1,000 and growing).
2. Real-Time Experimentation: Transparent and ongoing updates.
3. Behind-the-Scenes Insight: Detailed explanations of how and why prompts work.
4. Efficiency-Focused: Built around minimal time investment, demonstrating how to achieve more with less.
5. Constant Innovation: Early adoption of new AI models and features.
Step 4: Elevator Pitch
“At Ketelsen.ai, we empower tech-savvy entrepreneurs and AI enthusiasts to unlock cutting-edge automation with minimal time investment. By offering a massive, ever-growing library of high-impact prompts—backed by real-world experimentation and robust behind-the-scenes insights—we help you stay ahead in AI innovation without sacrificing your schedule. It’s your sandbox for AI exploration.”
4) Content Goals - The AI chat responses should result in real prompts that a real entrepreneur can use to achieve a real task. The task will be explained following this.
5) Role of the A.I. - You are “an expert in creating prompts for ChatGPT, Google GEMINI, Anthropic Claude and other similar Gen AI Tools” . You are creative and can use these Gen AI Tools in creative ways.
6) Content Source - Use any resource that is needed to achieve the objectives.
7) Inspirations for Content - The content style should be fun, entertaining and informative. Since the target audience for this site is entrepreneurs , the style should be similar to content found in popular media created for this market such as Forbes, Fortune, and the Wall Street Journal.
8) Constraints -
- Please do not make up any fake information, if there is no data or actual factual information, please respond with "NOT APPLICABLE"
9) Ideas for visuals - More information to come on this
10) Related Stories/Content - This article is part of the ketelsen.ai series on CRAFT™️ is an acronym for Configurable Reusable AI Framework Technology. CRAFT™️ is an on-going weekly experiment where I will be working together with the world’s most advanced commercially available A.I.s to develop a new way way to communicate with A.I. while adapting the principals of Object Orientated Programming to AI Chats. The goal is deeper, more intuitive and more meaningful interactions with A.I. chat tools.
Before continuing the next set of instructions, please list any items that need clarification. If there are no questions, please respond with ""READY"".
RESPONSE: READY
PROMPT:
Based on analysis of modern AI engineering needs, I am considering new specialized data types. These data types will make CRAFT code more expressive and easier to understand while reducing boilerplate. They are concepts that any A.I. can understand without defining them (for example: users do not need to explain to a A.I. Chat what a prompt is because the A.I. knows this term and what a prompt is and what it cannot be). Here are some ideas that I have:
Communication & Context Data Types
Intent: Represents a user's goal or purpose in an interaction
Example: Intent("book_flight", confidence=0.92)
Value: Helps AI understand what users want to accomplish without explicit instructions
Entity: Named pieces of information extracted from text
Example: Entity("destination", "Paris", category="location")
Value: Identifies key information points without complex parsing code
Sentiment: Emotional tone in text or speech
Example: Sentiment("positive", confidence=0.87)
Value: Enables emotional intelligence in AI responses
DialogueContext: Maintains conversation state with history and reference points
Example: DialogueContext(turns=5, current_topic="booking_details")
Value: Simplifies building conversational flows
Content & Media Data Types
RichContent: Text with formatting, links, and media
Example: RichContent("Check this important [resource](https://example.com)")
Value: Represents formatted content without HTML/Markdown boilerplate
MediaReference: Standardized reference to image, audio, or video
Example: MediaReference("image", url="https://example.com/img.jpg", alt="Product photo")
Value: Consistent handling of media across different AI platforms
Summary: Condensed version of longer content
Example: Summary("Long meeting transcript...", max_length=100)
Value: Standardizes content summarization without repetitive prompting
Business & Analytics Data Types
UserProfile: Collection of user preferences and behaviors
Example: UserProfile(industry="healthcare", role="manager", interests=["AI", "automation"])
Value: Provides context for personalized AI interactions
Metric: Named value with unit and context
Example: Metric("conversion_rate", 3.2, unit="percent", trend="increasing")
Value: Standardized business KPI representation
TimeSeries: Temporal sequence of data points
Example: TimeSeries([{date: "2025-04-01", value: 120}, ...], metric="sales")
Value: Simplifies trend analysis and forecasting
Annotation: Comments or notes attached to content
Example: Annotation("This paragraph needs revision", severity="suggestion")
Value: Standardizes feedback and collaboration
Functional Data Types
ActionTemplate: Reusable pattern for AI actions
Example: ActionTemplate("email_customer", parameters=["name", "order_id"])
Value: Creates standardized workflows for common business processes
DataValidator: Rules for validating input
Example: DataValidator(type="email", required=true, format="corporate")
Value: Ensures data quality without complex validation code
Transformation: Data conversion specification
Example: Transformation("csv_to_table", options={"headers": true})
Value: Standardizes data processing steps
Why These Align With CRAFT Objectives
These data types align with your objectives because they:
Reduce boilerplate: Replace complex code patterns with simple, declarative structures
Increase expressiveness: Clearly communicate intent without lengthy documentation
Are universally understood by AI: Represent concepts that all modern AI systems understand innately
Are accessible to non-technical users: Use business-friendly terminology rather than technical jargon
Enable practical applications: Focus on common business scenarios that entrepreneurs encounter daily
Each type provides a clear, practical benefit that would be immediately recognizable to your target users, making the CRAFT framework more intuitive and productive for AI-assisted tasks in business contexts.
Beginner-Friendly Data Types for CRAFT Framework
For AI beginners with less than a year of experience, we need data types that are immediately intuitive, self-explanatory, and relate to familiar concepts. Here are data types that would make CRAFT more accessible to newcomers:
Learning & Guidance Data Types
Template: Ready-to-use prompt structures with placeholders
Example: Template("product_description", slots=["product_name", "features", "target_audience"])
Value: Helps beginners follow proven patterns without reinventing prompts
Example: Sample inputs and outputs for reference
Example: Example(input="Summarize climate change", output="Climate change refers to...")
Value: Shows concrete results to help beginners understand what's possible
Feedback: Guidance on improving prompts
Example: Feedback("Add more specific details about your target audience")
Value: Provides built-in coaching to accelerate learning
Simplified Task Data Types
Question: Simple query for information
Example: Question("What are the benefits of solar energy?")
Value: Clarifies that the AI should focus on providing information
Instruction: Clear direction for the AI to follow
Example: Instruction("Write a professional email to a client about a project delay")
Value: Makes it explicit when users want the AI to create something
Comparison: Request to evaluate alternatives
Example: Comparison("electric vs. gas vehicles", aspects=["cost", "environment", "convenience"])
Value: Structures a common task in a format AI can consistently understand
Everyday Content Data Types
Email: Email structure with essential components
Example: Email(subject="Meeting Follow-up", recipient="team", tone="professional")
Value: Simplifies a common business task with natural parameters
SocialPost: Content formatted for social media
Example: SocialPost(platform="LinkedIn", topic="industry trend", hashtags=3)
Value: Handles platform-specific considerations automatically
Note: Quick, informal content for personal use
Example: Note("Remember to check quarterly numbers before the meeting")
Value: Distinguishes casual content from formal documents
Learning Support Data Types
Explanation: Request for concept clarification
Example: Explanation("machine learning", level="beginner", examples=true)
Value: Gets consistent educational content with appropriate depth
HowTo: Step-by-step instructions for a process
Example: HowTo("create a budget spreadsheet", detail_level="medium")
Value: Ensures AI provides actionable, sequential steps
Definition: Simple meaning of a term
Example: Definition("prompt engineering", context="AI")
Value: Quick access to clear explanations without overwhelming detail
Communication Helper Data Types
Tone: Writing style specification
Example: Tone("friendly", "professional", "concise")
Value: Simplifies one of the most common adjustments beginners make
Audience: Target reader description
Example: Audience("marketing professionals", knowledge_level="intermediate")
Value: Helps AI tailor content appropriately without complex instructions
Length: Content size specification
Example: Length("paragraph", count=3) or Length("words", count=200)
Value: Ensures consistent output format without technical parameters
Why These Are Beginner-Friendly
These data types are designed specifically for AI beginners because they:
Use everyday language: No technical jargon or complex concepts
Match how beginners think: Align with natural questions and requests
Provide structure: Guide users toward successful interactions
Focus on common tasks: Address the needs beginners have most frequently
Reduce complexity: Hide advanced parameters behind simple interfaces
Build transferable skills: Teach concepts that apply across all AI systems
For a beginner, being able to say Instruction("Write a blog post").with(Topic("sustainable fashion")).using(Tone("casual", "informative")) is much more intuitive than crafting complex prompts from scratch.
These types create a structured yet flexible way for newcomers to create effective AI interactions while gradually learning deeper prompt engineering concepts.
Do you agree with these suggestions? Please evaluate these data types given the objectives of the CRAFT frameowrk.
Are any of these data types likely to be confusing for either the user or the A.I.?

Thank you for sharing these proposed specialized data types for the CRAFT framework. I'll evaluate them based on the framework's objectives of creating structured, efficient workflows for human-AI interaction.

Evaluation of Proposed Data Types

Overall, your proposed data types align well with CRAFT's objectives. They effectively reduce boilerplate, increase expressiveness, and focus on concepts that are intuitive to both AI systems and users.

Strengths

Conceptual Clarity: Most types represent clear, distinct concepts that AIs naturally understand (Intent, Sentiment, Summary, etc.)
Practical Application Focus: The types address common business scenarios and AI interactions that your target audience (entrepreneurs) would find valuable.
Progressive Learning Path: The beginner-friendly types create an excellent on-ramp for new users while still fitting within the broader framework architecture.
Balance of Simplicity and Power: Types like Template, Tone, and Audience offer significant functionality with minimal syntax complexity.

Potential Confusion Points

A few data types might need refinement to avoid confusion:

Example vs Template: The distinction between these might be unclear to beginners. Consider renaming "Example" to "SampleCase" or "Demonstration" to avoid confusion with code examples.
DialogueContext: This is potentially complex for beginners as it contains multiple properties and state management. Consider simplifying its initial implementation or making it an advanced type.
ActionTemplate vs Instruction: These seem to overlap conceptually. You might want to clarify the distinction or merge them into a single concept.
Annotation vs Feedback: These also have conceptual overlap. Consider making Annotation a more technical type for developers and Feedback more user-focused.

Recommendations

Hierarchical Organization: Group these types into clearer categories based on user experience level and function (Communication, Content, Learning, etc.)
Implementation Priority: Start implementing the beginner-friendly types first, as they'll provide the most immediate value and establish the foundation for more complex types.
Consistent Parameter Naming: Ensure parameter naming is consistent across similar types (e.g., "confidence" for both Intent and Sentiment).
Documentation Examples: For each type, create practical examples showing both the code and the resulting AI interaction to make the benefits concrete.

The dual approach of having both advanced and beginner-friendly data types aligns perfectly with the progressive nature of the CRAFT framework as described in your development roadmap. This allows users to start simple and gradually adopt more powerful abstractions as they grow comfortable with the framework.

Would you like me to explore any particular data type in more depth or suggest implementation patterns for any of them?

Retry

Please suggest new data types that fit this objective.

Edit

Additional Data Types for CRAFT Framework

Based on the CRAFT framework's objectives of creating structured, efficient workflows for human-AI interaction, here are some new specialized data types that would complement your existing ones:

Process & Workflow Data Types

Scenario

Purpose: Represents a specific use case or situation for the AI to understand context
Example: Scenario("customer_support", channel="email", urgency="medium")
Value: Provides complete situational awareness without lengthy descriptions

Iteration

Purpose: Manages progressive refinement of AI outputs
Example: Iteration(step=3, feedback="Add more technical details")
Value: Formalizes the improvement cycle without manual tracking

Session

Purpose: Groups related interactions with persistence
Example: Session("project_brainstorm", duration_minutes=30)
Value: Creates boundaries for focused work without losing context

Knowledge Management Types

Concept

Purpose: Represents a well-defined idea or principle
Example: Concept("prompt_engineering", related=["AI", "NLP"])
Value: Standardizes knowledge representation across conversations

Framework

Purpose: Structured approach to addressing a problem
Example: Framework("SWOT_analysis", components=["strengths", "weaknesses", "opportunities", "threats"])
Value: Encapsulates methodologies without repetitive explanation

Perspective

Purpose: Specific viewpoint for analysis
Example: Perspective("customer", concerns=["cost", "usability"])
Value: Enables multi-angle thinking without verbose instructions

Content Refinement Types

Structure

Purpose: Defines organizational pattern for content
Example: Structure("problem_solution", sections=["challenge", "approaches", "recommendation"])
Value: Ensures consistent, well-organized outputs

Voice

Purpose: Extends tone with personality characteristics
Example: Voice("authoritative", "compassionate", formality_level=8)
Value: Creates nuanced, consistent writing style across interactions

Emphasis

Purpose: Highlights key aspects of content
Example: Emphasis("cost_savings", strength="primary")
Value: Directs AI focus without repetitive instructions

Decision Support Types

Criterion

Purpose: Specific factor for evaluation
Example: Criterion("scalability", weight=0.8, description="Ability to handle growth")
Value: Creates consistent decision frameworks

Alternative

Purpose: Potential option with pros and cons
Example: Alternative("cloud_hosting", pros=["flexibility", "cost"], cons=["complexity"])
Value: Structures decision-making processes

Recommendation

Purpose: Suggested course of action with reasoning
Example: Recommendation("increase_budget", confidence=0.85, rationale="Historical ROI data")
Value: Standardizes advice format

Interaction Enhancement Types

Clarification

Purpose: Request for additional information
Example: Clarification("target_audience", options=["beginners", "experts"])
Value: Formalizes the information-gathering process

Preference

Purpose: User-specific choices that affect output
Example: Preference("detail_level", value="comprehensive", persistence="session")
Value: Maintains consistent user-specific configurations

Priority

Purpose: Importance ranking for multiple elements
Example: Priority(["accuracy", "brevity", "creativity"], top="accuracy")
Value: Resolves potential conflicts in AI objectives

Implementation Considerations

These data types are designed to be:

Intuitive: They represent familiar concepts that both users and AI systems readily understand
Composable: They can be combined to create complex instructions from simple building blocks
Progressive: They support both beginners and advanced users within the same conceptual framework
Practical: They address real business use cases that entrepreneurs encounter regularly

The types also maintain Python-like syntax for consistency with your current CRAFT implementation and follow object-oriented principles for extensibility.