How to Turn Shorts Analytics Into a What to Make Next Memo With AI

The problem and who this is for

Analytics exports are full of numbers, but most creators still choose next week's clips by instinct. This workflow is for creators, channel managers, social strategists, agencies, and editors who want a practical weekly decision memo. The goal is to get to a plain-English memo that tells you what clip patterns to repeat, what to stop doing, and what to test next with the fewest steps possible.

Prerequisites

• Access to Gemini
• A source file or capture workflow that matches the article
• A place to save the final output, such as a Google Doc, notes app, spreadsheet, or editor brief
• An editing or publishing workflow for your final short-form asset

How to capture or gather the source material

1. Export your short-form performance data as CSV if your platform allows it. If not, build a manual spreadsheet with one row per clip.
2. Include columns that actually matter for creative decisions. Useful fields include title, publish date, topic, hook type, length, views, average view duration, retention, saves, shares, comments, and call to action style.
3. Add one or two human-coded columns before you upload the sheet. Examples: clip format, camera style, topic bucket, emotional angle, or whether the clip used text-heavy captions.
4. Clean the sheet so each column has one meaning. Rename vague fields such as metric1 or notes2 before analysis.

Step-by-step workflow

1. Upload the spreadsheet to Gemini and explain that you want a weekly creative memo, not a statistics lecture.
2. Ask Gemini to identify patterns across top performers, weak performers, and outliers. Push it to compare hook style, topic, length, and format, not just raw view counts.
3. Ask for a memo with three sections: do more, do less, and test next. This structure is faster to act on than a long narrative summary.
4. Have Gemini list the specific rows or clip IDs that support each conclusion so you can verify the pattern against the sheet.
5. Before you trust the memo, manually inspect a few of the cited clips. The spreadsheet can show correlations, but you still need to see whether the creative read is right.

Tool-specific instructions

Primary tool: Gemini

• Gemini is a good primary fit when the workflow starts from a spreadsheet and you want a fast file-based analysis path that can compare rows and patterns.
• Give the model human-coded columns when possible. It is much easier to learn from clips when the sheet says what each clip actually was.
• Ask for a memo, not just trends. A memo forces the model to turn the analysis into decisions.

Alternative: ChatGPT

• Use ChatGPT if you prefer its spreadsheet analysis workflow or want a second opinion on the same export.
• It is a strong option for turning the analysis into a clean strategy memo or testing plan after the numeric review.

Alternative: Claude

• Claude is useful when you want a more careful written memo and you already know the main findings from the sheet.
• It works especially well for turning the analysis into a team-facing weekly update.

Copy and paste prompts

Gemini analytics pattern prompt

{
  "role": "You are analyzing a short-form video performance spreadsheet.",
  "goal": "Find the most useful creative patterns in the uploaded sheet.",
  "rules": [
    "Do not focus on raw views alone.",
    "Compare hook style, topic, length, format, and call to action patterns where the sheet supports them.",
    "Point back to the rows or examples behind each conclusion."
  ],
  "output_fields": [
    "top_patterns",
    "weak_patterns",
    "outliers_worth_reviewing",
    "missing_data_that_would_improve_the_analysis"
  ]
}

Gemini weekly memo prompt

{
  "role": "You are writing a weekly creative decision memo from spreadsheet evidence.",
  "goal": "Turn the uploaded analytics sheet into an action memo for next week's short-form production.",
  "memo_sections": [
    "Do more",
    "Do less",
    "Test next"
  ],
  "requirements": [
    "Keep the memo practical and short.",
    "Base each point on evidence from the sheet.",
    "Include the rows or examples behind each conclusion."
  ]
}

Quality checks

• The memo points to actual rows, not vague claims.
• The recommendations compare creative variables, not only vanity metrics.
• At least one conclusion can be acted on in the next production cycle.
• The sheet contains enough descriptive columns to support the claimed pattern.

Common failure modes and fixes

• The sheet has only platform metrics and no creative descriptors: Add manual columns for topic, hook, format, or angle before analysis.
• The memo overreacts to one viral outlier: Ask for median or cluster patterns and require separate treatment for outliers.
• The conclusions sound true but too generic: Force every recommendation to cite specific clips or rows.
• The export is too small: Analyze a larger sample or frame the output as early directional learning rather than a hard strategy.

Sources Checked

• Gemini Help: Upload and analyze files in Gemini Apps on Android: https://support.google.com/gemini/answer/14903178?co=GENIE.Platform%3DAndroid&hl=en (accessed 2026-03-25)
• Gemini Help: Upload and analyse files in Gemini Apps on Computer: https://support.google.com/gemini/answer/14903178?hl=en-NA&visit_id=639100585389477783-308453270&p=code_upload&rd=1 (accessed 2026-03-25)
• OpenAI Help: File Uploads FAQ: https://help.openai.com/en/articles/8555545-file-uploads-faq (accessed 2026-03-25)
• OpenAI Help: ChatGPT Image Inputs FAQ: https://help.openai.com/en/articles/8400551-chatgpt-image-inputs-faq (accessed 2026-03-25)
• Claude Help: Uploading files to Claude: https://support.claude.com/en/articles/8241126-uploading-files-to-claude (accessed 2026-03-25)
• Claude Help: What are projects?: https://support.claude.com/en/articles/9517075-what-are-projects (accessed 2026-03-25)

Quarterly Refresh Flag

Review by 2026-06-23. Re-check the current tool interface, upload behavior, supported source types, and any changes that affect this workflow before republishing or refreshing the article.