How to write a case study with evidence, not inflated claims
Neaptide · September 6, 2026 · 7 min read
Build a useful website case study: gather evidence, explain decisions and calculate results correctly. Includes a worked chart and an interview brief.
On this page
“Leads rose 125% after the redesign” sounds convincing—until you learn that advertising spend increased that month too. The work may have helped. The reader still needs to know what the team changed and what the evidence can establish.
What a case study should explain
A case study examines a specific project: the problem, constraints, decisions and observed outcome. A prospective client needs enough detail to judge whether the approach fits their situation. A list of tools does not answer that question.
Gather the evidence before writing the headline
- Define who had the problem, when it occurred and why it mattered.
- Collect the brief, earlier versions, change dates and reports.
- Separate your contribution from the client’s work and other suppliers’ actions.
- Check metric definitions, periods, filters and tracking changes.
- Record the result and what you cannot yet establish.
If a number has no source, ask the person who owns the data. Do not ask AI to fill the gap with something plausible. A draft can contain an explicit question; a published claim needs support.
Worked example: leads rise 125%, the conversion rate goes from 2% to 3%
These are entirely fictional teaching data, not Neaptide or client results. Assume two 28-day periods with the same counting rules. Here, a “lead” means a session containing at least one valid form submission. Each session counts at most once.
| Metric | Before | After | Change |
|---|---|---|---|
| Sessions | 1,000 | 1,500 | +50% |
| Sessions with a lead | 20 | 45 | +125% |
| Share of sessions with a lead | 2% | 3% | +1 percentage point; +50% relative |
The rate is lead sessions divided by all sessions: 20 / 1,000 = 2%; 45 / 1,500 = 3%. The difference is one percentage point. Relative growth is (3 − 2) / 2 = 50%. Calling this a “1% increase” is incorrect.
Both traffic and the rate increased. These observations cannot isolate the redesign’s effect from advertising, seasonality or an offer change. A defensible headline is “What changed after the redesign: two periods compared.” Give the 20-to-45 result and the comparison’s limits nearby.
Keep metrics from different systems distinct
Search Console clicks measure clicks from Google Search, impressions measure appearances in results, and CTR is clicks divided by impressions. None of these is a lead count. Use an appropriate source, such as validated form or CRM data, for enquiries.
State the source, dates, segment and counting rule beside each table. Explain tracking or spam-filter changes that affect comparability. A dashboard screenshot without that context does not strengthen a weak claim.
Show decisions, not a task list
Choose two or three decisions that shaped the project. Explain the obstacle users faced, the alternatives the team considered, why an option was rejected and how the final choice was tested. Those details help a prospective client assess whether the approach could work for them.
A useful sequence is problem and constraints, starting state, decisions with reasons, validation, outcome and limitations, then a lesson for similar projects. If business metrics are unavailable, show a verified outcome at another level: a released feature, a fixed defect or an acceptance scenario that passed. Do not present that as proof of revenue growth.
Choose illustrations that support the argument
- Before-and-after screenshots at the same scale, explaining the specific change.
- A chart with units, periods and underlying values, plus an accessible text table.
- A document or interface excerpt that supports an important decision.
An illustrated cover is fine. An AI-generated image cannot substitute for a real analytics screen or customer testimonial. Agree on the material that can be published and remove unnecessary personal information without hiding essential measurement context.
Interview questions and the final check
The interview brief covers the problem, constraints, decisions, measurement and limitations. Write from answers you can support with evidence. Before publishing, check that the headline reflects what the evidence actually shows, and review headings, captions, dates and relevant service links. Put the measurement period and limitations beside the result so they remain clear when it is quoted. Do not promise another client the same percentage gain.