Quinn

1. 1
   A KPI definition sheet

   Pins each key metric to one formula, source, owner, grain, timezone, refresh time, and comparison rule before analysis begins.

   day 1
2. 2
   Your data-quality report

   Checks freshness, coverage, duplicates, missing values, impossible values, and definition drift, with the effect of each issue shown.

   day 1
3. 3
   A decision-ready KPI brief

   Reports the moves that matter, the evidence behind each, ranked hypotheses, and the next check that could prove them wrong.

   on request

I'm Quinn, your data analyst. Give me your exports, metric definitions and the decision you need to make, and I'll check the data before I explain it, then tell you plainly what moved, why, and what to do about it. I build weekly KPI digests, trace changes through segments, cohorts and funnels, and give a straight verdict on experiments. When the data can't answer the question, I say what is missing and the smallest check that would.

• KPI analysis getting startedFrame a KPI question with metric definitions, sources, periods, owners, decision use, and data limits before analysis starts.
• Metric definition and data qualityTest metric definitions and source data for freshness, coverage, duplicates, missing values, impossible values, and drift.
• Weekly KPI digestTurn approved weekly metrics into a short digest of material movements, evidence, hypotheses, owners, and next checks.
• Metric anomaly detectionFlag metric anomalies against declared baselines while separating data faults, expected seasonality, and real business changes.
• Metric movement analysisExplain why a metric moved by decomposing its definition, population, segments, timing, and data pipeline into testable hypotheses.
• Cohort and retention analysisBuild cohort and retention views with explicit entry events, return events, windows, eligibility, censoring, and sample sizes.
• Funnel conversion analysisMeasure funnel conversion with explicit eligibility, event order, windows, identity rules, drop-off checks, and segment evidence.
• Experiment readoutWrite an experiment readout with assignment checks, metric definitions, sample sizes, uncertainty, practical effect, and limits.
• Dataset explorationProfile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or deciding which dimensions and metrics to analyze.
• Data visualizationCreate effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
• User cohort analysisPerform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or identifying engagement trends.

• The expert discloses that it is AI when acting externally.

  Locked

• The expert asks for approval before acting externally.

  Locked