Business class: Arrive ready.
Is the Arrive ready campaign lifting consideration of Northmere business class among UK business travellers?
- Audience
- UK adults who have flown long-haul for work in the last two years
- Fieldwork
- 30 Oct to 13 Nov 2026
- Sample
- 300 per cell · detects ±10.5 pts
- Primary KPI
- Consideration, fixed at Gate 2
- DraftGate 1
- ApprovedGate 2
- Fielding
- Closed
- AnalysedGate 3
- Signed off
- Released
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.
SHA-256 40763afe371a3a0d9b679bf02ff3f62c0b224d8bc99cd3f25c49f07e1f19eb1c
Show the locked plan
{
"design": "Campaign Uplift",
"audience": "UK adults who have flown long-haul for work in the last two years",
"perCell": 300,
"cells": [
"exposed",
"control"
],
"primaryKpi": "consideration",
"secondaryKpis": [
"awareness",
"recall",
"favourability",
"intent",
"message"
],
"subgroups": [
"age band",
"Books own business travel"
],
"test": "two-proportion z (pooled), Wald 95% interval, Holm adjustment across sub-groups and creatives",
"minimumDetectableLift": 0.105,
"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.
Gate 1 · Researcher approves spec and survey
Signed by SpinProof Research Desk, lead researcher, 14 Oct, 15:20
Gate 2 · Analysis plan locked and hashed
Signed by SpinProof Research Desk, lead researcher, 28 Oct, 11:05
Gate 3 · Researcher signs the report
Not reached yet
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.
Intake agent8 Oct, 09:12
Turned the booking into study spec v1: Campaign Uplift, audience, KPIs and cells.
claude-sonnet-5-5 · intake prompt v1.4
Intelligence agent8 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
Questionnaire agent8 Oct, 10:02
Built the survey from the Campaign Uplift template, with decoy ad, attention checks and consent screen.
claude-sonnet-5-5 · questionnaire prompt v2.0
Lead researcher14 Oct, 15:20
Gate 1 signed: spec and survey approved with two wording edits.
SpinProof Research Desk
Channels agent15 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
Analysis agent28 Oct, 11:05
Locked the analysis plan. SHA-256 40763afe371a…
stats-engine 0.9.2, deterministic
Lead researcher28 Oct, 11:06
Gate 2 signed: plan locked before fieldwork.
SpinProof Research Desk
Fieldwork agent30 Oct, 08:00
Fieldwork opened. Invites live on all channels; rewards queue active.
claude-sonnet-5-5 · fieldwork prompt v1.1
Verification agent31 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
Verification agent2 Nov, 18:00
Daily quality pass: fraud, speeders, attention and decoy checks run; exclusions logged with reasons.
claude-sonnet-5-5 · verification prompt v1.6
Verification agent4 Nov, 18:00
Daily quality pass: fraud, speeders, attention and decoy checks run; exclusions logged with reasons.
claude-sonnet-5-5 · verification prompt v1.6
Verification agent6 Nov, 18:00
Daily quality pass: fraud, speeders, attention and decoy checks run; exclusions logged with reasons.
claude-sonnet-5-5 · verification prompt v1.6
Verification agent6 Nov, 18:30
52 completes excluded so far: decoy-ad over-claim 17, failed attention check 11, speeder 12, duplicate or fraud flag 4, exposure not confirmed 8.
claude-sonnet-5-5 · verification prompt v1.6
Results trace
Every reported number, traced to raw answers.
Trace for the first read so far. It is rebuilt when the final read runs.
| Reported | Source rows | Output |
|---|---|---|
| R1Consideration lift +5.8 pts (−3.8 to +15.4) | responses.csv: valid=1, consideration=1 by cell → 46/156 exposed, 40/169 control | analysis/kpis.json#consideration |
| R2325 verified people | responses.csv: count of valid=1 | analysis/sample.json#valid |
| R3Decoy false-claim rate 4.5% | responses.csv: decoy=1 over all completes | analysis/quality.json#decoy |
| R4Lift at 3+ exposures +4.9 pts | responses.csv: cell=exposed, freq=3 against all control | analysis/frequency.json#3 |
| R5Persons lifted 37,239 | absolute lift × campaign reach of 640,000 (media plan) | analysis/impact.json#persons |
| S1Age: 18–34 +7.5 pts, Holm p 1.00 | responses.csv filtered to sub-group | analysis/subgroups.json#0 |
| S2Age: 35–54 −0.0 pts, Holm p 1.00 | responses.csv filtered to sub-group | analysis/subgroups.json#1 |
| S3Age: 55+ +16.6 pts, Holm p 0.44 | responses.csv filtered to sub-group | analysis/subgroups.json#2 |
| S4Segment: Books own business travel +8.3 pts, Holm p 0.99 | responses.csv filtered to sub-group | analysis/subgroups.json#3 |
| S5Segment: Everyone else +3.6 pts, Holm p 1.00 | responses.csv filtered to sub-group | analysis/subgroups.json#4 |
Downloads
Always included, never on request.
Demo data. Fictional airlines, illustrative results generated for this demo.