Prompts
Showing 133 to 144 of 578 results
Design a Dashboard People Will Actually Use
Builds a dashboard around one audience and one decision cycle, with each number earning its place, thresholds that say what good looks like, and an...
Design an Event Tracking Plan Before You Build the Feature
Specifies the events and properties a feature needs so the questions you'll be asked in three months are answerable, with naming conventions and a ...
Write a Data Dictionary for a Table or Dataset
Documents what each field actually means, including the edge cases and known quirks that cause silent misuse, and pins each metric to one authorita...
Segment Customers From Behavior, Not Intuition
Builds segments from what customers actually do rather than who they look like, tests whether the segments are real and stable, and insists each on...
Run a Cohort and Retention Analysis
Builds a cohort retention analysis with the definitions pinned down first — what counts as active, when the clock starts, how to read the curve — a...
Check Whether a Difference Is Real or Just Noise
Applies significance reasoning to observational data — segment comparisons, period-over-period changes, group differences — where no experiment was...
Reconcile Two Data Sources That Disagree
Finds the real reason two systems report different numbers for the same thing — definition, timing, filtering, or genuine loss — and settles which ...
Work Out Why a Number Moved
Decomposes a metric change into where it actually came from — segment, mix, volume, or definition — before anyone starts guessing at causes, and ch...
Clean and Validate a Messy Dataset
Works through a dataset's structural problems in the order that matters — duplicates, missing values, types, outliers, categories — and forces a do...
Write an Analysis Plan Before You Pull the Data
Turns a vague business question into a specific answerable one, commits to the method and the decision rule before any data is touched, and names w...
Write a Project Instruction File for a Coding Agent
Turns the tacit conventions of a codebase into a project instruction file (CLAUDE.md, AGENTS.md, or similar) that is short, verifiable, and actuall...
Cut the Cost and Latency of an AI Feature
Finds where an AI feature's tokens, dollars, and seconds actually go, then ranks the reductions by saving against quality risk — caching, model tie...