RevOpsInfluencer Marketing Analystbeginner 20 min saved

Creator Engagement Standardization Engine

Standardize creator performance metrics using a uniform follower-count basis for accurate, side-by-side analytical comparisons.

Customise & copy

Add the context you have. The prompt updates as you work.

Baseline Follower Denominator *

The uniform follower count basis to use for all engagement rate calculations.

Creator Data *

Raw performance metrics for the group of content creators.

Output Format *

Select the structural format for the final observations and calculations.

Live prompt

3 fields

Analyze the following creator performance dataset and calculate standardized engagement metrics. Strict separation between raw data observations and mathematical calculations must be maintained.

Baseline Follower Denominator: 10000
Creator Dataset:
Creator: @tech_guru | Followers: 45000 | Avg Likes: 1200 | Avg Comments: 85
Creator: @design_daily | Followers: 12000 | Avg Likes: 650 | Avg Comments: 40
Output Format Preferences:
Markdown Table

Instructions:
1. Observations Section: List the raw input data provided for each creator exactly as supplied without mixing calculation steps.
2. Calculations Section: Compute average likes, average comments, and the engagement rate for each creator using the exact uniform baseline follower count provided (10000). Show the formula application clearly.
3. Do not include any conversational filler, introductory remarks, or step-by-step reasoning theatre.

Proof before you use it

A real example

Tested on gemini-3.1-flash-lite on 2026-09-05

{
  "creator_data": "Creator: @enterprise_ciso | Followers: 5200 | Avg Likes: 310 | Avg Comments: 45\nCreator: @cloud_architect | Followers: 8900 | Avg Likes: 520 | Avg Comments: 65",
  "output_format": "Structured Bullet Points",
  "baseline_denominator": "50000"
}

A small ritual that works

How to use it

01Input your raw creator data (username, followers, likes, comments) into the dataset field.
02Define the baseline follower denominator (e.g., 10,000) to normalize the engagement rates.
03Select your preferred output format (Markdown Table or Bullet Points).
04Run the prompt to generate a clean, separated report of raw observations and calculated metrics.

Why it works

The prompt enforces a strict separation between raw data observations and mathematical calculations. By mandating a uniform baseline follower denominator ({{baseline_denominator}}) across all creators, it prevents skewed comparisons caused by varying follower counts. Explicit instructions to display formula applications eliminate reasoning theatre and conversational filler, ensuring reproducible, objective analytical output.

Where it fails

INSUFFICIENT_EVIDENCE

Customisation tips

You can adjust the baseline follower denominator variable to match different normalization standards, or modify the output format variable to change how the observations and calculations are structured.

Watch-outs

Outputs may incorrectly substitute individual creator follower counts for the uniform baseline denominator during calculations.
Raw creator data inputs must be listed exactly as supplied without altering numeric formatting or mixing in calculation steps.
Calculations must include all required metrics (average likes, average comments, and engagement rates) rather than omitting individual components.

Works in

ChatGPTClaudeGemini

Was this useful?

Submit your variation

If your version helps, it may be published with your name and a link back to you.

Want to make AI useful across your team? Explore Atul's training.