Topic
Turning raw data or a messy set of facts into a clear conclusion is where most analysis work gets stuck. This page collects prompts built for that exact step: breaking down a dataset or report into key patterns, comparing options against a set of criteria, and structuring findings into a conclusion someone can actually act on. They're useful for analysts, product managers, and anyone who needs to make sense of numbers or unstructured information quickly. Every prompt is free and reusable — plug in your own data or context using the marked {{variable}} fields and get a structured, decision-ready answer instead of a generic summary.
62 prompts · page 3 of 7
Builds a SWOT analysis for a specific company, industry, context, and goal, pushing for 5-7 evidence-backed points in each quadrant instead of generic bullets that could describe any competitor. Adds impact assessment for weaknesses, prioritization for opportunities, and mitigation strategies for threats, then closes with strategic recommendations tied back to the stated goal.
Builds a fill-in-ready KPI report template for a business area, its KPI list, reporting frequency, and audience, meant to be generated once and reused every period. Includes a header section, a red/yellow/green scorecard, per-KPI detail with trend and variance from target, a commentary section, action items for underperforming metrics, and a data-definitions appendix explaining how each number is calculated.
Reviews a chart — its type, intended message, underlying data, and any suspected issues — before it goes into a deck or report. - Checks: whether the chart type fits the data relationship, honest visual encoding, data-to-ink ratio - Tests: whether the key insight lands within 5 seconds and holds up in black and white or for colorblind readers - Output: concrete before/after fixes, not just a list of complaints
Designs a deduplication pipeline for records — customers, transactions, or products — that carry small formatting or spelling variations instead of exact duplicates, using the dataset description, key identifying fields, and known variation types as inputs. Combines exact-match removal with fuzzy techniques like Levenshtein or phonetic matching, assigns a confidence score to each match, proposes a merge strategy, and generates a human-reviewable report before anything is deleted.
Plans a dashboard for a given audience and business area before it gets built in a BI tool, based on a metrics list, user goals, refresh frequency, and target tool. Specifies the layout, chart type per metric with reasoning, filter and drill-down controls, a color-coding scheme, alert thresholds, and mobile considerations, all built around whether a viewer can pass the 5-second glance test.
Turns a research question, study topic, and participant description into a ready-to-use interview guide before fieldwork starts. - Generates 8-12 open-ended questions ordered from general to specific - Builds in at least two probing follow-ups for topics that tend to get surface-level answers - Avoids yes/no phrasing and leading wording - Best piloted with one participant before the full study
Specifies an interactive exploration tool for a dataset's dimensions and metrics, covering layout, filter and drill-down behavior between named levels, comparison views, hover details, transitions, and the default view a user sees before touching anything. Adds a tool-specific implementation plan and performance notes for the expected row count, plus working Plotly Dash or Streamlit prototype code when the target tool is Python-based.
Builds a launch plan for a product, target market, competitive landscape, budget, and timeline — not just a list of channels to try. Covers target customer definition, value proposition, pricing and packaging, distribution channels, marketing and sales tactics, and success metrics, then closes with a concrete 90-day action plan meant to be revisited weekly.
Writes up a spike, drop, or unusual pattern the way an analyst should, starting from the anomaly description, time range, affected metrics, magnitude, and supporting data. States what happened in one sentence, quantifies the business impact beyond a percentage change, presents likely causes with evidence, rules out false positives like seasonality or pipeline bugs, and recommends both immediate action and prevention — tailored to a chosen audience and tone.