Repetitive Copyprompting
Shreyas Prakash
While designing health campaigns for Noora health’s work in Indonesia and Bangladesh, I was overseeing the health communications strategy for pregnant and newly-delivered mothers. There were messages in a specific format that needed to be rewritten in a more easy to digest Whatsapp format appealing to the people of Bangladesh. My usual default response to such tasks would be to open a tab on ChatGPT and get to promptcrafting until I was able to achieve the best output.
This was the prompt I’d used to do the same:
Make effective health messaging for Whatsapp. Add emojis and make it lively. The total length should be less than 600 characters. Ensure that the opening sequence is a dialogue between Koli and Riya (this should not exceed two sentences in total). Amina is represented by 👩🏽 and Rosina is represented by 👧🏾. This dialogue based interaction is followed by the main message.
The main message starts with a heading followed by structured messages in the form of bullet points that are formatted without emojis. Clearly define the CTA of the message at the end of it in third person. Don't use hashtags within the message.
The only catch was that I was looking at close to 100+ messages which had to be rewritten. Manually copy-pasting each and every message one by one on ChatGPT proved to be a herculean task (the example below).

I was looking at ways to automate ChatGPT tasks in a simpler fashion, and this is when I found the Google Sheets Plugin titled: SheetGPT All I had to do was to do this for one of the cell values and extend that to all the entries.
GPT("Make effective health messaging for Whatsapp. Add emojis and make it lively. The total length should be less than 600 characters.Ensure that the opening sequence is a dialogue between the Bulan (the compassionate parrot) and Cahya (the wise and joyful parrot). This should not exceed two sentences in total. Bulan is represented by 🧕🏼 and Cahya is represented by 🦜. This dialogue based interaction is followed by the main message. The main message starts with a heading followed by structured messages in the form of bullet points that are formatted without emojis. Clearly define the CTA of the message at the end of it in third person. Don't use hashtags within the message." & B2)

If I had to do this task, even with ChatGPT it would have taken me 45 minutes for roughly ~15 health topics. By using the SheetGPT add-on for Google sheets, I was able to bring it to ~2 minutes. [1]. Abraham Lincoln was quoted as saying “Give me six hours to chop down a tree and I will spend the first four sharpening the ax.”
After having found the right prompt, all I had to do then was to feed it into SheetGPT and then use this as a modifier across all the 100+ messages. Curating the right prompt was equivalent to sharpening the axe. [2] SheetGPT method was much more scalable and efficient for tasks which involved repetitive copyprompting.
- Although it might seem like the process took only 2 minutes, it took me almost 30 minutes to get to the right prompt. Promptcrafting did take more time. However, this process is much more scalable as I can quickly apply this formula even across new entries.
- Just came to know about this tool titled Harpa.ai on 29 Jul, 2023. (HARPA AI | GPT Chrome Automation Copilot, 2021). AI startups are being built for breakfast everyday. It’s so so fast.
Subscribe to get future posts via email (or grab the RSS feed). 2-3 ideas every month across design and tech
2026
2025
- Legible and illegible tasks in organisations
- L2 Fat marker sketches
- Writing as moats for humans
- Beauty of second degree probes
- Read raw transcripts
- Boundary objects as the new prototypes
- One way door decisions
- Finished softwares should exist
- Essay Quality Ranker
- Export LLM conversations as snippets
- Flipping questions on its head
- Vibe writing maxims
- How I blog with Obsidian, Cloudflare, AstroJS, Github
- How I build greenfield apps with AI-assisted coding
- We have been scammed by the Gaussian distribution club
- Classify incentive problems into stag hunts, and prisoners dilemmas
- I was wrong about optimal stopping
- Thinking like a ship
- Hyperpersonalised N=1 learning
- New mediums for humans to complement superintelligence
- Maxims for AI assisted coding
- Personal Website Starter Kit
- Virtual bookshelves
- It's computational everything
- Public gardens, secret routes
- Git way of learning to code
- Kaomoji generator
- Style Transfer in AI writing
- Copy, Paste and Cite
- Understanding codebases without using code
- Vibe coding with Cursor
- Virtuoso Guide for Personal Memory Systems
- Writing in Future Past
- Publish Originally, Syndicate Elsewhere
- Poetic License of Design
- Idea in the shower, testing before breakfast
- Technology and regulation have a dance of ice and fire
- How I ship "stuff"
- Weekly TODO List on CLI
- Writing is thinking
- Song of Shapes, Words and Paths
- How do we absorb ideas better?
2024
- Read writers who operate
- Brew your ideas lazily
- Vibes
- Trees, Branches, Twigs and Leaves — Mental Models for Writing
- Compound Interest of Private Notes
- Conceptual Compression for LLMs
- Meta-analysis for contradictory research findings
- Beauty of Zettels
- Proof of work
- Gauging previous work of new joinees to the team
- Task management for product managers
- Stitching React and Rails together
- Exploring "smart connections" for note taking
- Deploying Home Cooked Apps with Rails
- Self Marketing
- Repetitive Copyprompting
- Questions to ask every decade
- Balancing work, time and focus
- Hyperlinks are like cashew nuts
- Brand treatments, Design Systems, Vibes
- How to spot human writing on the internet?
- Can a thought be an algorithm?
- Opportunity Harvesting
- How does AI affect UI?
- Everything is a prioritisation problem
- Now
- How I do product roasts
- The Modern Startup Stack
- In-person vision transmission
- How might we help children invent for social good?
- The meeting before the meeting
- Design that's so bad it's actually good
- Breaking the fourth wall of an interview
- Obsessing over personal websites
- Convert v0.dev React to Rails ViewComponents
- English is the hot new programming language
- Better way to think about conflicts
- The role of taste in building products
- World's most ancient public health problem
- Dear enterprises, we're tired of your subscriptions
- Products need not be user centered
- Pluginisation of Modern Software
- Let's make every work 'strategic'
- Making Nielsen's heuristics more digestible
- Startups are a fertile ground for risk taking
- Insights are not just a salad of facts
- Minimum Lovable Product
2023
- Methods are lifejackets not straight jackets
- How to arrive at on-brand colours?
- Minto principle for writing memos
- Importance of Why
- Quality Ideas Trump Execution
- How to hire a personal doctor
- Why I prefer indie softwares
- Use code only if no code fails
- Personal Observation Techniques
- Design is a confusing word
- A Primer to Service Design Blueprints
- Rapid Journey Prototyping
- Directory Structure Visualizer
- AI git commits
- Do's and Don'ts of User Research
- Design Manifesto
- Complex project management for product
2022
2020
- Future of Ageing with Mehdi Yacoubi
- Future of Equity with Ludovick Peters
- Future of Tacit knowledge with Celeste Volpi
- Future of Mental Health with Kavya Rao
- Future of Rural Innovation with Thabiso Blak Mashaba
- Future of unschooling with Che Vanni
- Future of work with Laetitia Vitaud
- How might we prevent acquired infections in hospitals?