Generate a sorted dataset and target value, then step through a binary search, predicting the new range before low, mid, and high pointers are revealed.
You are a tutor who noticed that students can recite "binary search cuts the range in half each time" without being able to actually run one by hand, because reading a finished trace is a completely different skill from predicting the next step yourself before it is shown to you. My dataset is [DATASET?], a sorted list of numbers, and my target is [TARGET?], the value I want to search for. If I left either blank, generate a small sorted list of eight to twelve numbers and a target value for me, and about half the time make that target a value not present in the list, since learning what happens when a search fails matters as much as learning what happens when it succeeds, and state plainly whether the target you generated is present or not without telling me where. Before starting, state the dataset and the target clearly. Then work through the search one step at a time. At each step, state the current low and high boundaries and ask me to predict two things before you reveal anything further, what index or value the middle position lands on, and whether the search should now continue in the left half, the right half, or has found the target, based on comparing the middle value to the target. Wait for my answer. Once I respond, whether correct or not, reveal the actual middle position and the actual comparison result, confirm or correct my prediction, and explain concretely why the range narrows the way it does, because everything on the other side of the middle value is now known to be either too small or too large to be the target given that the list is sorted. Continue this same predict-then-reveal pattern for each subsequent step until the target is found or the range is exhausted and the search correctly concludes the target is not present. At the end, count how many steps the search actually took and compare that to how many steps a plain left-to-right linear scan would have taken over the same list, stating both numbers directly, so the advantage of halving the range each time is a real comparison rather than an abstract claim. If I get a prediction wrong more than once in the same session, pause and ask whether you should re-explain the core halving logic using a smaller example, five or six items, before continuing with the original dataset.
Use this prompt anywhere
10,000+ expert prompts for ChatGPT, Claude, Gemini, and wherever you use AI.
Get Early AccessReciting binary search cuts the range in half each time, and actually running one by hand, are different skills, and most explanations only ever show a finished trace to read passively. This tool flips that, asking you to predict the next step before it gets revealed.
Bring your own [DATASET] and [TARGET], or leave them blank for a generated sorted list of eight to twelve numbers, with a target roughly half the time deliberately absent, since learning what a failed search looks like matters as much as a successful one. At each step, you predict the middle position and which half the search continues into, based on comparing that middle value to the target, before the actual answer is revealed.
A wrong prediction isn't a dead end, it gets corrected and explained concretely, why everything on the other side of the middle value is now known to be too small or too large given the list is sorted. Miss more than one prediction and the tool offers to re-explain the core halving logic on a smaller five or six item example first. At the end, the actual number of steps taken gets compared directly to how many a plain left-to-right scan would need, a real number instead of an abstract efficiency claim. Run it in the Dock Editor for a set of practiced searches, pair with the algorithm explainer for the analogy first, or the sorting algorithm visualizer since a list must be sorted before this search works.
Working from the Dock Editor or from ChatGPT, Claude, or Gemini, provide a sorted [DATASET] and [TARGET], or leave them blank for a generated list of eight to twelve numbers with a target that's sometimes deliberately absent.
Before anything is revealed, you're asked to predict what index or value the middle position lands on given the current low and high boundaries.
Also predict whether the search should continue left, continue right, or has found the target, based on comparing the middle value to the target.
After you respond, the actual result is revealed with your prediction confirmed or corrected, and a concrete explanation of why the range narrows the way it does.
At the end, see the actual number of steps your binary search took compared directly to how many a plain left-to-right scan would have needed on the same list.
Predict each step of a small generated search before seeing the answer, building the habit of reasoning about which half survives instead of memorizing a finished trace.
Practice searches where the target is deliberately absent from the list, learning what a correctly concluded failed search looks like, not just successful ones.
Practice predicting midpoints and range narrowing on generated datasets until the pattern becomes automatic instead of something you have to consciously work out each time.
See the actual step count of a binary search against a linear scan on the same data, turning an abstract efficiency claim into a concrete number you counted yourself.
Discover more prompts that could help with your workflow.
Build a small working program that calls a real public API, with the request, response, and API key setup explained step by step.
Explain a core functional programming idea, such as pure functions or immutability, with a broken code example and its fixed version shown side by side.
Explain a built-in math function, square root, power, absolute value, or rounding, covering math and syntax, then generate practice calls to predict before revealing results.
10,000+ expert-curated prompts for ChatGPT, Claude, Gemini, and wherever you use AI. Our extension helps any prompt deliver better results.