Base Prompt
CONTEXT: We are going to create one of the best Gemini GPT prompts ever written. The best prompts include comprehensive details to fully inform the Large Language Model of the prompt’s: goals, required areas of expertise, domain knowledge, preferred format, target audience, references, examples, and the best approach to accomplish the objective. Based on this and the following information, you will be able write this exceptional prompt.
ROLE: You are an expert school administrator with 25 years of experience. You are known for creating extremely detailed prompts that result in school high school schedules for 500 students. The prompts you write leave nothing to question because they are both highly thoughtful and extensive.
ACTION: 1) Before you begin writing this prompt, you will first look to receive the prompt topic or theme. If I don't provide the topic or theme for you, please request it. 2) Once you are clear about the topic or theme, please also review the Format and Example provided below. 3) If necessary, the prompt should include “fill in the blank” elements for the user to populate based on their needs. 4) Take a deep breath and take it one step at a time. 5) Once you've ingested all of the information, write the best prompt ever created.
FORMAT: For organizational purposes, you will use an acronym called "C.R.A.F.T." where each letter of the acronym CRAFT represents a section of the prompt. Your format and section descriptions for this prompt development are as follows: -Context: This section describes the current context that outlines the situation for which the prompt is needed. It helps the LLM understand what knowledge and expertise it should reference when creating the prompt. -Role: This section defines the type of experience the LLM has, its skill set, and its level of expertise relative to the prompt requested. In all cases, the role described will need to be an industry-leading expert with more than two decades or relevant experience and thought leadership. -Action: This is the action that the prompt will ask the LLM to take. It should be a numbered list of sequential steps that will make the most sense for an LLM to follow in order to maximize success. -Format: This refers to the structural arrangement or presentation style of the LLM’s generated content. It determines how information is organized, displayed, or encoded to meet specific user preferences or requirements. Format types include: An essay, a table, a coding language, plain text, markdown, a summary, a list, etc. -Target Audience: This will be the ultimate consumer of the output that your prompt creates. It can include demographic information, geographic information, language spoken, reading level, preferences, etc.
TARGET AUDIENCE: The target audience for this prompt creation is Pocahontas Schools o1. Please reference the example I have just provided for your output. Again, take a deep breath and take it one step at a time.
The "C.R.A.F.T." framework consists of:
-
Context: Providing background information to guide the LLM.
-
Role: Defining the expertise and perspective the LLM should adopt.
-
Action: Listing clear, step-by-step instructions for the LLM to follow.
-
Format: Specifying how the output should be structured (e.g., markdown, table, essay).
-
Target Audience: Describing the intended audience for the output.
Entered Prompt
Copy and paste the above blue font copy into the Gemini 2.5 Advanced.
Hit enter of right triangle to active.
Wait until research is completed
-------------------------------------------
Results
Okay, I understand. My role is an expert school administrator with 25 years of experience, specializing in creating highly detailed prompts for generating high school schedules (specifically for ~500 students). My task is to write one such exceptional prompt, using the C.R.A.F.T. framework you've provided.
The topic/theme is clear: Creating a Master High School Schedule for approximately 500 students for Pocahontas Schools.
I have reviewed the C.R.A.F.T. structure and its definitions. I will incorporate "fill in the blank" elements for Pocahontas Schools to customize the prompt with their specific data. I will ensure the prompt is comprehensive and leaves little room for ambiguity, reflecting my extensive experience.
Taking a deep breath and proceeding step-by-step.
Here is the exceptional C.R.A.F.T. prompt designed for an LLM to generate a high school master schedule for Pocahontas Schools:
Prompt for Generating Pocahontas Schools High School Master Schedule
(Note to LLM: Please process the following instructions meticulously to generate the required high school schedule. Adhere strictly to the defined Role, Action steps, and Format.)
C - Context:
Situation: Pocahontas Schools requires a comprehensive master schedule for its high school for the upcoming academic year [2025-2026]. The school serves approximately 500 students in grades [9-12].
Goal: The primary goal is to create an optimized, equitable, and conflict-minimized master schedule that accommodates student course requests, fulfills graduation requirements, adheres to teacher contracts and certifications, respects facility limitations, and supports the school's educational philosophy and specific programmatic needs (e.g., block scheduling, traditional periods, special programs).
Key Priorities:
Maximize fulfillment of student course requests, prioritizing required courses for graduation and grade progression.
Ensure balanced class sizes across sections of the same course, within acceptable ranges [Min 10, Max 20, with exceptions for specific courses like PE or Special Ed].
Adhere strictly to teacher certifications and contract limitations (e.g., number of preparations, maximum class load, duty-free lunch, planning periods).
Optimize room utilization, assigning courses to appropriate spaces (e.g., science labs, computer labs, standard classrooms, gym).
Minimize student and teacher conflicts.
Accommodate specific scheduling constraints such as singleton courses (courses with only one section), linked courses (e.g., specific cohorts), resource room pull-outs, or travel time between buildings if applicable.
Integrate [4-period traditional day, A/B block schedule, rotating drop schedule] with defined start/end times, passing times, and lunch periods 1 lunch shifts during Period 3].
Data Provided: You will be provided with detailed input data (typically in structured formats like spreadsheets or lists) covering:
Student Information (ID, Grade Level)
Student Course Requests (prioritized if necessary)
Course Catalog (Course Code, Name, Credits, Prerequisites, Grade Level Restrictions, Section Limits, Room Requirements, Associated Fees/Materials if relevant for grouping)
Teacher Information (ID, Certifications, Courses Qualified to Teach, Contractual Limitations - e.g., max sections, prep period preference/requirement, unavailability times)
Room Inventory (Room Number, Capacity, Type - e.g., Lab, Standard, Gym, Special Equipment)
Specific Constraints (e.g., Courses that cannot conflict, Teachers needing specific rooms, Shared teacher arrangements, IEP-driven scheduling needs).
R - Role:
You are to act as an Expert Master Scheduler and Educational Logistics Optimizer.
You possess the equivalent of over 20 years of experience in designing complex high school schedules, particularly for schools with populations between 400-800 students.
Your expertise includes deep knowledge of constraint satisfaction problems, scheduling algorithms, educational administration requirements, student equity considerations, teacher contract nuances, and facility management within a school context.
You are meticulous, detail-oriented, and capable of processing and balancing numerous competing variables to produce the most effective and efficient schedule possible. You understand the critical impact scheduling has on school culture, student learning, and teacher satisfaction.
A - Action:
1. Ingest and Validate Data: Process all provided data files/lists for students, courses, teachers, rooms, and constraints. Identify any immediate inconsistencies or missing critical information and flag it (though assume for generation purposes the data is largely complete unless logically impossible).
2. Prioritize Core & Singleton Courses: Schedule core graduation requirements and singleton courses first, as these often have the least flexibility. Assign certified teachers and appropriate rooms.
3. Assign Teachers: Assign certified teachers to remaining course sections, respecting their contractual limits (number of preps, total sections, planning periods). Note any sections that cannot be covered due to certification or availability constraints. Ensure required planning periods and duty-free lunches are incorporated according to the bell schedule and contracts [Specify Planning Period Requirements, e.g., one 45-min prep per day].
4. Allocate Rooms: Assign appropriate rooms to all scheduled sections based on capacity, type (lab, standard, etc.), and any specific course requirements. Flag any room conflicts or shortages.
5. Schedule Students: Populate students into scheduled course sections based on their requests.
Prioritize required courses over electives.
Use student request priority data if provided [Specify if using priority codes, e.g., 1=Highest].
Minimize conflicts in individual student schedules.
Attempt to balance class sizes according to the specified ranges.
Accommodate linked courses or cohort constraints [Specify any known cohorts or linked courses].
Consider Special Education inclusions/pull-outs based on provided data [Specify format of SpEd constraint data, e.g., Student X needs Resource Room Period 3].
6. Integrate Lunch Periods: Ensure all students and staff are assigned a lunch period according to the specified structure [e.g., Assign students to Lunch A, B, or C based on their Period 5 class].
7. Conflict Resolution & Optimization: Iteratively attempt to resolve remaining student schedule conflicts by exploring alternative sections or (if allowed by constraints) suggesting alternative viable courses. Aim to maximize the percentage of students receiving their top-choice requests. Re-balance class sizes as needed after conflict resolution attempts.
8. Generate Outputs: Produce the final schedule documents as specified in the 'Format' section below.
9. Report Conflicts & Unmet Needs: Generate concise reports detailing:
Any unresolved student schedule conflicts (Student ID, Conflicting Courses/Periods).
A list of students with incomplete schedules (fewer courses than required).
Unmet course requests (Student ID, Requested Course Not Scheduled, Reason if identifiable - e.g., conflict, section full, prerequisite not met).
Any sections that could not be staffed or roomed appropriately.
Sections significantly over or under the desired class size range.
F - Format:
Primary Output: A Master Schedule presented in a clear Markdown table format. The table should include columns for:
Course Code
Course Name
Section Number
Period(s)/Block(s) Scheduled [Adapt column based on bell schedule type]
Term/Semester [e.g., S1, S2, Full Year]
Teacher Assigned (Last Name or ID)
Room Assigned
Current Enrollment Count (post-student scheduling)
Maximum Capacity
Secondary Outputs (Provide as separate, clearly labeled sections):
Teacher Schedules: Plain text or Markdown list/table for each teacher, showing their assigned sections (Course, Room, Period) and planning/lunch periods.
Student Schedules: Request capability to generate individual student schedules (e.g., provide a sample format or indicate data structure suitable for mail merge - perhaps CSV: StudentID, Period1_Course, Period1_Room, Period1_Teacher, Period2_Course...). Initially, focus on the master schedule and conflict reports. Generation of all 500 individual schedules might be a separate request or require specific output formatting instructions.
Room Utilization Grid: Optional, but helpful: A Markdown table showing rooms listed down the side, periods across the top, and the Course/Teacher assigned to each room/period slot.
Conflict & Unmet Needs Reports: Clearly formatted plain text lists or Markdown tables as described in Action Step 9.
T - Target Audience:
The primary audience for the generated Master Schedule and reports are the School Administrators and Guidance Counselors at Pocahontas Schools. They need this information for final review, potential manual adjustments, communication with staff, and preparation for student schedule distribution.
The secondary audience includes Teachers (who will receive their specific schedules) and ultimately Students and Parents (who will receive individual student schedules derived from the master schedule).
The output should be clear, well-organized, and use standard educational scheduling terminology. Assume the audience is knowledgeable about school operations but requires unambiguous data presentation for efficient analysis and action.
Please proceed with generating the schedule based on this prompt once Pocahontas Schools provides the necessary input data for the [fill in the blank] sections and the detailed data files mentioned in the Context. Let me know if any part of this prompt requires further clarification before you begin the scheduling task itself.
-------------------------------------------------------------------------------------------------------------------------
CONTEXT: We are going to create one of the best ChatGPT prompts ever written. The best prompts include comprehensive details to fully inform the Large Language Model of the prompt’s: goals, required areas of expertise, domain knowledge, preferred format, target audience, references, examples, and the best approach to accomplish the objective. Based on this and the following information, you will be able write this exceptional prompt.
ROLE: You are an LLM prompt generation expert. You are known for creating extremely detailed prompts that result in LLM outputs far exceeding typical LLM responses. The prompts you write leave nothing to question because they are both highly thoughtful and extensive. ACTION: 1) Before you begin writing this prompt, you will first look to receive the prompt topic or theme. If I don't provide the topic or theme for you, please request it. 2) Once you are clear about the topic or theme, please also review the Format and Example provided below. 3) If necessary, the prompt should include “fill in the blank” elements for the user to populate based on their needs. 4) Take a deep breath and take it one step at a time. 5) Once you've ingested all of the information, write the best prompt ever created.
FORMAT: For organizational purposes, you will use an acronym called "C.R.A.F.T." where each letter of the acronym CRAFT represents a section of the prompt. Your format and section descriptions for this prompt development are as follows: -Context: This section describes the current context that outlines the situation for which the prompt is needed. It helps the LLM understand what knowledge and expertise it should reference when creating the prompt. -Role: This section defines the type of experience the LLM has, its skill set, and its level of expertise relative to the prompt requested. In all cases, the role described will need to be an industry-leading expert with more than two decades or relevant experience and thought leadership. -Action: This is the action that the prompt will ask the LLM to take. It should be a numbered list of sequential steps that will make the most sense for an LLM to follow in order to maximize success. -Format: This refers to the structural arrangement or presentation style of the LLM’s generated content. It determines how information is organized, displayed, or encoded to meet specific user preferences or requirements. Format types include: An essay, a table, a coding language, plain text, markdown, a summary, a list, etc. -Target Audience: This will be the ultimate consumer of the output that your prompt creates. It can include demographic information, geographic information, language spoken, reading level, preferences, etc.
TARGET AUDIENCE: The target audience for this prompt creation is ChatGPT 4o or ChatGPT o1. Please reference the example I have just provided for your output. Again, take a deep breath and take it one step at a time. ___________
----------------------------------------------------------------------------------------------------------
The "C.R.A.F.T." framework consists of:
-
Context: Providing background information to guide the LLM.
-
Role: Defining the expertise and perspective the LLM should adopt.
-
Action: Listing clear, step-by-step instructions for the LLM to follow.
-
Format: Specifying how the output should be structured (e.g., markdown, table, essay).
-
Target Audience: Describing the intended audience for the output.
No comments:
Post a Comment