Public preview
Few-Shot Examples Before Asking
Show the model 2-5 examples of the desired output style so it mirrors the pattern with high precision.
Goal
Get output in a consistent specific style instead of the model default voice.
Steps
-
1
Pick the output type: title, tweet, summary, classification.
Expected Outcome
Immediate
Output matches the pattern at 80%+ vs 20-40% from a plain prompt.
Evidence base
School: In-Context Learning / Few-Shot Prompting
Founders: Brown et al. · OpenAI (2020)
The original GPT-3 paper (Brown 2020) proved large LMs are in-context learners.
Keywords
Frequently asked questions
How long does "Few-Shot Examples Before Asking" take?
This exercise takes about 12 minutes, practiced solo in a Creative format.
When will I notice the effect of "Few-Shot Examples Before Asking"?
Output matches the pattern at 80%+ vs 20-40% from a plain prompt. In the short term: You build a few-shot library for each repeated task type.
Is "Few-Shot Examples Before Asking" evidence-based?
Yes — it draws on In-Context Learning / Few-Shot Prompting (Brown et al., OpenAI (2020)). The original GPT-3 paper (Brown 2020) proved large LMs are in-context learners.
Is "Few-Shot Examples Before Asking" suitable for beginners?
Its difficulty level is: Intermediate. No external tools required — it can be practiced directly inside the app.
Subscribe for full access
Subscribe to Plus for full access to this practice and the whole catalogue, or try first — free, no sign-in, no commitment.
7 complete practices (one per domain) are free forever, no sign-in.