Demo: fictional airlines, illustrative data.Back to the site
Creative TestAnalysed· Awaiting Gate 3 sign-off

Winter city breaks: two ads.

Which winter city-break ad should run from December, and does either move consideration?

Audience
UK adults 18 to 54 who took a European city break in the last two years
Fieldwork
27 Oct to 31 Oct 2026
Sample
200 per cell · detects ±12.8 pts
Primary KPI
Consideration, fixed at Gate 2
Step 5 of 7 · Analysed2 of 3 gates signed

Method lock

Locked before fieldwork.

The spec, survey version, primary KPI, sub-groups and analysis plan are hashed at Gate 2. If any of it changed afterwards, the hash would not match.

Locked 26 Oct, 11:05kj-winter-cities-survey-v1.1

SHA-256 d50de074310ca27333046051afa0f6343d44568f812487fdf8ec260ef60311d4

Show the locked plan
{
  "design": "Creative Test",
  "audience": "UK adults 18 to 54 who took a European city break in the last two years",
  "perCell": 200,
  "cells": [
    "control",
    "A",
    "B"
  ],
  "primaryKpi": "consideration",
  "secondaryKpis": [
    "favourability",
    "message",
    "intent"
  ],
  "subgroups": [],
  "test": "two-proportion z (pooled), Wald 95% interval, Holm adjustment across sub-groups and creatives",
  "minimumDetectableLift": 0.128,
  "exclusions": [
    "decoy-ad over-claim",
    "attention check",
    "speeder (< one third of median time)",
    "duplicate or fraud flag",
    "exposure not confirmed by media data"
  ]
}

Human gates

Who signed what, and when.

  1. Gate 1 · Researcher approves spec and survey

    Signed by SpinProof Research Desk, lead researcher, 21 Oct, 15:20

  2. Gate 2 · Analysis plan locked and hashed

    Signed by SpinProof Research Desk, lead researcher, 26 Oct, 11:05

  3. Gate 3 · Researcher signs the report

    Waiting for SpinProof Research Desk, second reviewer

Agent run log

Every action, with the model or code version used.

Agents draft, recruit, check and write. Deterministic code does the statistics. Real people give every answer.

  1. Intake agent19 Oct, 09:12

    Turned the booking into study spec v1: Creative Test, audience, KPIs and cells.

    claude-sonnet-5-5 · intake prompt v1.4

  2. Intelligence agent19 Oct, 09:31

    Built the context brief: competitor ads from Meta Ad Library, share of search baseline, AI answer visibility baseline, news and social scan.

    claude-sonnet-5-5 · intel prompt v1.2

  3. Questionnaire agent19 Oct, 10:02

    Built the survey from the Creative Test template, with decoy ad, attention checks and consent screen.

    claude-sonnet-5-5 · questionnaire prompt v2.0

  4. Lead researcher21 Oct, 15:20

    Gate 1 signed: spec and survey approved with two wording edits.

    SpinProof Research Desk

  5. Channels agent22 Oct, 10:15

    Set up recruitment: Meta ad sets with screener, QR codes for placements, panel quotas, SpinProof panel invites.

    claude-sonnet-5-5 · channels prompt v1.3

  6. Analysis agent26 Oct, 11:05

    Locked the analysis plan. SHA-256 d50de074310c…

    stats-engine 0.9.2, deterministic

  7. Lead researcher26 Oct, 11:06

    Gate 2 signed: plan locked before fieldwork.

    SpinProof Research Desk

  8. Fieldwork agent27 Oct, 08:00

    Fieldwork opened. Invites live on all channels; rewards queue active.

    claude-sonnet-5-5 · fieldwork prompt v1.1

  9. Verification agent28 Oct, 18:00

    Daily quality pass: fraud, speeders, attention and decoy checks run; exclusions logged with reasons.

    claude-sonnet-5-5 · verification prompt v1.6

  10. Verification agent29 Oct, 18:00

    Daily quality pass: fraud, speeders, attention and decoy checks run; exclusions logged with reasons.

    claude-sonnet-5-5 · verification prompt v1.6

  11. Verification agent30 Oct, 18:00

    Daily quality pass: fraud, speeders, attention and decoy checks run; exclusions logged with reasons.

    claude-sonnet-5-5 · verification prompt v1.6

  12. Verification agent31 Oct, 18:30

    61 completes excluded in total: decoy-ad over-claim 20, failed attention check 19, speeder 14, duplicate or fraud flag 8.

    claude-sonnet-5-5 · verification prompt v1.6

  13. Fieldwork agent31 Oct, 20:00

    Quotas met in every cell. Fieldwork closed; rewards paid.

    claude-sonnet-5-5 · fieldwork prompt v1.1

  14. Analysis agent4 Nov, 09:00

    Ran the locked plan: every KPI, pre-registered sub-groups, Holm adjustment. No deviations from plan.

    stats-engine 0.9.2, deterministic

  15. Reporting agent4 Nov, 11:30

    Drafted the report from computed tables only. Every number linked to an analysis output.

    claude-sonnet-5-5 · reporting prompt v1.8

  16. Evidence agent4 Nov, 11:45

    Assembled the Evidence File. 0 untraced numbers. Charts re-checked against tested values.

    claude-sonnet-5-5 · evidence prompt v1.0

Downloads

Released with the report.

Raw data, crosstabs and the full Evidence File are released together once Gate 3 is signed.

Demo data. Fictional airlines, illustrative results generated for this demo.