Today’s Practice
From your recent AI conversations — coding, writing, analysis — pick 5 prompts that actually worked well. Record them using the template from Part 4: original prompt + effectiveness rating + iteration notes.
Where you record them doesn’t matter — a notes app, Notion, a plain text file. Don’t overthink the tool.
If you can’t find your chat history, spend 20 minutes creating 5 prompts you’ll definitely use at work. For example: “Check the edge cases in this code,” “Rewrite this technical article for beginners,” “Extract the 3 main issues from these 100 user feedbacks.”
Group them by scenario: writing, analysis, daily tasks — or whatever works for you. The point is getting 5 written down first. Directory structure comes later.
Prompt Record Template (from Part 4):
Original Prompt: [The exact text you sent to AI]
Effectiveness: [What worked, what didn’t]
Iteration: [A more stable revised version]
What to Observe
- Do these 5 Prompts naturally cluster by scenario, or are they all mixed together? This tells you how you think about problems.
- Are there any you can’t remember why they worked? If so, next time write down a quick effectiveness note right after using a Prompt — even just three words like “fast, accurate, thorough.”
- After writing them down, which category has the most prompts? That’s your high-frequency scenario.
💡 Tip: You can do this organizing manually, or let AI help. Paste your chat history and say “Find 5 effective prompts from these conversations and organize them using the template” — then review and filter the results yourself.
Why This Matters
This connects to Part 4’s Prompt library concept. Going from 0 to 5 is the hardest step — an empty library feels pointless, but with 5 entries, the structure starts to emerge. 5 curated prompts beat 50 unorganized ones.
Today’s Takeaway
A Prompt library isn’t about collecting — it’s about curating.
📖 Series Navigation