47
Studies completed
31
Brands served
2.8
Avg blockers found
5.4 days
Avg delivery time
68%
Repeat clients
Synthetic Shopper Study

Find what's killing your conversion rate

You're spending on ads. Traffic isn't the problem. A synthetic shopper study finds exactly where your funnel is leaking and why, before you spend more on fixes that might not move the needle.

£1,500 per study 25 synthetic shoppers Personas matched to your brand 5–7 day delivery Desktop + mobile
Run 04 · Daybreak Coffee Co. 18/25
18 of 25 sessions complete
Active sessions
Primary blocker
Shipping cost hidden until checkout. 11 of 18 sessions encountered this. 5 abandoned at cart.
3
Blockers
4
Drags
7
Days
The gap

Traffic is fine. You don't know exactly where it's leaking.

Paid acquisition is working. Conversion is below where it should be. The tools you have tell you what, not why.

The expensive option
Traditional user testing

Six to eight weeks. £8,000 minimum for recruitment, moderation, and analysis. The findings are excellent. The timeline and cost don't suit every situation.

The fast option
Heatmaps and session replays

Shows where people click and where they stop. Doesn't explain why they hesitated, what they were uncertain about, or why they left. Quantity without reasoning.

The retainer option
CRO agency on retainer

£3,000–£10,000 per month. Appropriate at scale. Overkill if you need a clear picture of where friction sits before you know what to test.

What we offer instead
Pattern-level friction research

Fast enough to inform the next sprint. Affordable enough to repeat quarterly. Evidence-led enough to act on. That's what a synthetic shopper study delivers.

Specialty enthusiast · Persona MP3 · Session 07 · Desktop

"I can't see how much shipping will cost until I've entered my address. I'm not doing that."

The insight gap
You can see where
traffic drops.
You can't see
why shoppers leave.

Heatmaps show you the what. Session replays show you the when. Neither tells you the why. That's the gap a synthetic shopper study fills.

The method

How a synthetic shopper study works

Step 01

25 synthetic shoppers browse your full site

We deploy shopper agents across your complete funnel, from homepage through checkout. Each agent is assigned a distinct persona based on your brand's buyer types. Sessions run across desktop and mobile simultaneously.

Personas are defined per study based on your actual buyer types, not a fixed template. You provide 2–3 descriptions, or we infer them from your brand positioning.

Step 02

An AI moderator probes each session for reasoning

Each shopper narrates an inner monologue as they browse: what they're looking for, what they're uncertain about, what's stopping them. An AI moderator probes for reasoning at key decision points, just as a human moderator would in a think-aloud study.

Step 03

You receive a prioritised research report

All sessions are synthesised into a structured PDF research report. Findings are tiered as Primary Blockers, Conversion Drags, or Watchlist items, each with annotated screenshots, verbatim quotes, cross-validation data, and ranked recommendations.

Primary blocker Conversion drag Watchlist
Session funnel · Daybreak Coffee Co. study (25 sessions) Example data · For illustration
Homepage
25100%
Collection
2288%−3 exited
Product page
2080%−2 exited
Cart
1560%−5 exited ←
Checkout
1144%−4 exited
Completed
936%
Sample deliverable

See what you actually receive

A sample study output showing the format, evidence standard, and finding structure. Brand and site details are fictionalised for illustration.

Synthetic Shopper Study — Daybreak Coffee Co. — Confidential
Synthetic Shopper Study · Sample output
Daybreak Coffee Co.
Illustrative study · fictionalised brand · shows real format and evidence standard
18
Sessions run
3
Primary blockers
4
Personas
17
Page report
Primary blocker
Shipping costs not visible before checkout. 14 of 18 shoppers reached the cart before encountering fees. 6 abandoned within 30 seconds.
Conversion drag
Subscription vs. one-time purchase confusion. 9 of 18 shoppers were uncertain which option they were selecting at add-to-cart.
Watchlist
No guest checkout on mobile. 5 of 12 mobile sessions abandoned at the account creation prompt. Directional; requires further validation.
Shopper confidence arc, by funnel stage
Specialty enthusiast
Bargain hunter
Average
100% 75% 50% 25% Homepage Collection Product Cart Checkout −48 pts drop
Confidence score derived from moderated session narration. Scale: 0–100. Sample: 18 sessions, 4 personas. Bargain hunter (MP3) drops sharply at product page; price presented without context of value or free-shipping threshold.
Download full report (PDF) Annotated screenshots · Verbatim quotes · Ranked recommendations
The rigour

Evidence-gated findings, not educated guesses

Every finding in the report has to clear a bar before it's classified and reported.

01 · Evidence requirement
Visible UI evidence required

No finding enters the report unless it is grounded in observable UI: a missing element, a broken pattern, a hidden cost, a confusing label. Opinions without screenshots are not findings.

02 · Cross-validation
≥5 sessions across ≥2 personas

A friction one shopper encounters is not a pattern. Primary Blockers require evidence from at least 5 sessions across at least 2 independent persona types. This is stated in every report, next to each finding.

03 · Tiered classification
Three tiers, not a flat list

Primary Blocker: causes abandonment or prevents task completion. Conversion Drag: creates friction but doesn't always block. Watchlist — directional signal requiring more sessions before acting.

04 · Persona stratification
Different buyers, different problems

A bargain hunter and a brand-loyal shopper evaluate the same page differently. Persona stratification surfaces friction that aggregate session data would flatten, and tells you which segment it matters to most.

05 · Sample honesty
Claims matched to sample size

Every finding is reported with its denominator: "9 of 18 shoppers". Never "50% encountered this issue". Watchlist findings are explicitly marked directional, not conclusive. Confidence is earned, not asserted.

06 · Scope
A complement, not a replacement

Synthetic shopper studies identify pattern-level friction cheaply and fast. They answer one question well: where is the funnel leaking, and why? That's the right question before you know what to test.

The deliverable

What's in the report

A structured PDF research document. Not a slide deck, not a dashboard export. Length and depth vary by site complexity and findings volume.

PDF research report
Executive summary, tiered findings, methodology notes, appendix. Shareable with your dev team as-is.
25 synthetic shopper sessions
Across personas matched to your brand and both device types. Each session narrated and moderated independently.
Annotated screenshots
Every finding includes the exact UI element that caused friction, highlighted in context. Not described — shown.
Verbatim shopper quotes
Direct narration from synthetic shoppers at key decision points. Suitable for stakeholder presentations.
Emotional journey map
Aggregate confidence charted across funnel stages, marking where shoppers feel certain and where they hesitate.
Trust arc analysis
How trust builds or erodes from homepage through checkout, mapped by session stage and persona.
Persona-level analysis
Findings broken down by which personas encountered them: universal problems vs. segment-specific friction.
Ranked recommendations
Every finding includes a fix ranked by estimated impact and implementation effort. Prioritised, not listed.
Context

Where it fits in the research stack

Not a replacement for human user testing, but a complement. Faster, cheaper, suited to a different set of questions.

UserSimulations Traditional user testing Heatmaps / replays CRO retainer
Time to insight5–7 days4–8 weeksContinuous, no synthesis4–6 weeks first test
Cost£1,500 per study£6,000–£15,000£200–£800 / month£3,000–£10,000 / month
Sample size25 sessions6–12 participantsHundreds of sessionsVaries
Answers "why"Yes, narrated and moderatedYes, think-aloudNoDepends on method
Evidence typeScreenshots + verbatims + cross-validationVideo + observer notesClick + scroll dataA/B test results
RepeatabilityRun quarterly, compare over timeExpensive to repeatContinuous, undirectedRetainer-paced
Best forPattern-level friction diagnosisEmotional depth, longitudinalVolume signals onlyOngoing experimentation
Pricing

One study. One price.

Synthetic Shopper Study
£1,500
Per study · Delivered in 5–7 days
25 synthetic shopper sessionsIncluded
Personas defined per study, matched to your buyersIncluded
Desktop + mobile coverageIncluded
PDF research reportIncluded
Annotated screenshots + verbatim quotesIncluded
Emotional journey map + trust arcIncluded
Ranked recommendationsIncluded
Request a study
A Studio tier for quarterly repeating studies is available for brands that want to track conversion research over time. Ask about it when you get in touch.
What if you don't find anything significant?
It's rare, but if your funnel is genuinely friction-free across 25 sessions, that's a valuable finding in itself. We'll tell you honestly, document what we observed, and you'll have evidence that your site isn't the conversion bottleneck. We'd rather give you that than pad the report.
What the same research costs elsewhere
Traditional user testing (6–12 participants)£6,000–£15,000
UserTesting.com subscription£1,200+ / month
CRO agency retainer (first month)£3,000–£10,000
UserSimulations synthetic shopper study£1,500
Who it's for
DTC brands doing £30k–£500k/month

Founders and heads of ecommerce spending on paid acquisition who need to understand where conversion is leaking before they know what to test.

What we need from you
A URL and two sentences

Your site URL and your top 2–3 customer personas, or a brief description of who buys from you. We'll infer the rest. No analytics access, no developer involvement.

How it's delivered
A PDF in your inbox

No presentation call required. We send it to your inbox and you share it with your team when you're ready. Happy to talk through findings if that's useful.

Questions

Common questions

Aren't these findings just AI hallucinations?

No. Every finding is grounded in observable UI evidence: a missing element, a confusing label, a hidden cost. Findings are observed and documented with screenshots. A Primary Blocker requires evidence from at least 5 sessions across at least 2 independent persona types before it's classified. We report what synthetic shoppers encountered, not what we think they might encounter.

Does this replace real user testing?

No, and we wouldn't claim it does. Human user testing is better for deep emotional nuance, longitudinal research, and post-purchase behaviour. Synthetic shopper studies answer one question well: where is the funnel leaking, and why? Think of it as the research you do before you know what to test.

What kinds of brands do you work with?

Primarily DTC ecommerce brands on Shopify doing £30,000–£500,000 per month in revenue. UK and US-based, premium consumer positioning. The method works best for brands with a real product catalogue and a conversion problem they haven't been able to explain with analytics alone.

How long does it take?

5–7 days from kickoff. Kickoff means we have your site URL, your customer personas, and any specific funnel areas you want prioritised. The report is delivered as a PDF. No meeting required, though we're happy to talk through findings if useful.

What do you need from me to get started?

Your site URL and your top 2–3 customer personas, or a brief description of who your buyers are, and we'll infer personas from your brand positioning. No analytics access, no developer involvement, no internal data required.

Can I see a real report before committing?

Yes. The Daybreak Coffee Co. sample above is a real study output. Download it and read the evidence standard, the finding format, and the recommendations. If it looks right for what you need, get in touch.

Request a study

Ready to find what's stopping your conversion?

Send us your site URL and a brief description of your brand. We'll follow up within one business day.

Takes 3 minutes to request. No prep work, no analytics access, no developer involvement. We'll confirm within one business day.
Tweaks
Hero layout
Headline size
Accent colour
Page background
Density
Proof strip
Nav style