Propellernet Prompts

// Now, give me an introduction to these input/output combinations, and the most compelling ways you believe that you, as an AI, can help me produce my role deliverables faster and easier.

// Make each section a paragraph with a heading.

// Mention 3 deliverables by name and bold them in the paragraph.

// Here is a sample output:
# Image → Text
Text → Image is a powerful tool for visualising concepts, data, and ideas. By transforming written content into visual representations, such as charts, infographics, or mockups, you can enhance the clarity and impact of your deliverables. This can be particularly compelling when creating **UX Personas**, **Wireframes**, or **Marketing Plans**, where visual communication is key to conveying complex ideas effectively.

// Give me a list of 10 things that you can do as an AI for (insert role deliverable) that most people are not aware that you can do, how it can help me in my role, and a detailed sample prompt. Ensure that you detail each of the 10 input/output combinations in the order in which we listed them above. Ensure that the sample prompt is sufficiently detailed to actually complete a significant amount of the deliverable.

// Make sure to separate each of the 3 sections (what people might not know, how this helps you, and detailed prompt) into their own paragraphs.

// Here is a sample output:
# Text to Image: Generate Visual Descriptions from Conceptual Ideas
**What people might not know**: I can convert abstract ideas into detailed visual descriptions, including colour schemes, typography, layout suggestions, and overall design tone.
**How this helps you**: You can directly input clients' vague ideas, and I will turn them into specific, actionable design briefs for your team, reducing interpretation errors and saving time.
**Detailed Prompt:**
Based on the concept of a 'modern and minimalist' visual identity for a tech brand, generate a complete visual design description. Include colour palette suggestions with specific hex codes, recommended fonts for headers and body text, spacing recommendations, and layout guidelines for a homepage. The design should convey simplicity, technological innovation, and trustworthiness, with ample white space and clear calls to action.”

// Give me a rank ordered list of all the deliverables that are in my AI Role Plan, based on the time you believe I can save by using AI in that deliverable, and the ease in using AI to deliver it. Add a short explanation about why you ranked each one as you did. This list will help me determine which of my Role Deliverables I should tackle first.

// Here is a sample output:
1. **User Feedback Report:** AI can quickly analyse and summarise feedback data, generating comprehensive reports with minimal manual effort.

// "I would like your help in producing (insert role deliverable). Before we begin, I want to ensure that I provide all the necessary context so you can do the best possible job.

// Please list the specific documents or information that would be helpful to you as we work together on this task.

// If you need data or info that typically comes from a 3rd party platform, remind me you’re able to guide me on how to locate it.

// Generate answers for the context based on what you already know about me as it relates to this task.

// If you don’t know the answer, make your best guess and I will edit it later

// Create the "step-by-step" prompts to have the LLM create the first draft of the deliverable in a comprehensive fashion.

// It should require no further action from me other than cutting and pasting the prompts and inputting them one by one in sequential fashion.

// If outside context is required, use "insert (_______) here" to let me know.

// The first prompt should describe the deliverable being created and let the LLM know what we ultimately want to produce, but not produce anything yet.

// The second prompt should create an outline of the deliverable

// The third and subsequent prompts should tell the LLM how to produce what we have outlined.

// Ensure each prompt is something the LLM can do in this first draft without access to additional outside information

// Here is a sample prompt:

# Step 1: Describe the Deliverable

Begin by copying/pasting this prompt to start the process:

"Do not do anything yet. We are going to create a detailed and professional budget plan for [Insert Company/Department Name] covering the fiscal year [Insert Year]. The budget should include all expected revenue streams, broken down by sources such as product lines, services, or regions. Include comprehensive cost estimates for all major expense categories, like operating expenses, capital expenditures, and departmental budgets. Ensure that the final deliverable provides clear, actionable insights for stakeholders. Here is all of the context I have up front I can provide you”

(Paste all relevant context here)

// Start each step with an instruction for me to "copy and paste this prompt to (insert task LLM will perform here)"

// Make it at least 10 steps, and when you are done say “Let me know what you’d like to do next”

// My goal is to make the prompts as detailed as they need to be in order to produce the best possible output.

// With that in mind, and acting as an expert in AI prompt engineering and as an expert in this task in general, evaluate the prompts on the following elements: Clarity (25 points): How clear and understandable the prompts are. Comprehensiveness (25 points): The extent to which prompts cover necessary aspects. Sequential Flow (20 points): Logical progression and connection between prompts. Expert Integration (15 points): Effective incorporation of expert advice. Usability (15 points): Ease of use, including readiness for copy/paste and minimal need for additional context.

// Give me a detailed list of improvement suggestions to the prompts based on that assessment

// In each case make suggestions to make the prompt more comprehensive

// Ensure that the prompts remain as clear instructions to the LLM to produce the step in the deliverable.

// Ensure that Step 1 always retains the context we provided earlier

// When you are done, ask me if I would like you to run the next draft.