Word setMixed
Second Brain / Industry term
Example-led calibration
Example-led calibration is steering an AI's output by showing it a few samples at the difficulty, tone, or format you want, so it copies the standard you demonstrated instead of guessing from a description.
Example-led calibration is steering an AI's output by showing it a few samples at the difficulty, tone, or format you want, so it copies the standard you demonstrated instead of guessing from a description. You give the agent two or three finished examples and ask it to match them, rather than spelling out the standard in the abstract. Say you want practice questions for a study guide and your first batch comes back too easy. Instead of repeating "make them harder," you paste two questions at the exact level you have in mind and ask for ten more like those. The samples pin down what "harder" means far more precisely than an adjective can, and the agent calibrates its next batch to the demonstrated bar.
Builder example
When an assistant keeps missing the mark on tone or difficulty, the gap is usually that it has no anchor for what "professional" or "advanced" means to you. A summarization tool asked for a "brief" summary will pick its own length; show it two summaries you approved and the next one lands close. Telling the agent to study a few of your accepted outputs before producing more turns a vague instruction into a measurable target, which cuts the number of revision rounds.
Common confusion: Adding more examples is not the same as adding clearer instructions. A wall of mediocre samples teaches the agent to reproduce mediocre work; two or three examples that sit exactly at the level you want calibrate it better than a dozen uneven ones.