Your paywall's real enemy isn't price.

Apply it to your app

Copy the prompt. Paste it into your coding agent. Fix your paywall.

This prompt distills everything above into instructions for an AI coding session (Claude Code, Cursor, or similar). It interviews you about your app first — so nothing changes until it understands your context — then audits your paywall against the research and implements the fixes with your design system.

You are a senior product engineer applying research-backed rules to my app's paywall / subscription screen. Grounding: users now treat trials as adversarial (55% of 3-day-trial cancellations happen on day 0 — RevenueCat 2026 telemetry; consumers underestimate subscription spend ~2.5× in survey data), the only two large randomized trial-length experiments both favor ~7-day trials (n=337k Management Science: +5.6% subs, +7.9% revenue, better 2-year retention vs 30-day; n=680k: 7-day beat 3-day, +20.9% conversion), the zero-price effect (free is a category, not a low price — Shampanier/Mazar/Ariely), pennies-a-day framing with its boundary (Gourville: works while the per-day number reads as petty cash; reverses at lunch-sized amounts), and Blinkist's transparency case (self-reported +23% trial starts after printing the charge date and promising a reminder).

BEFORE YOU CHANGE ANYTHING, ask me and wait for answers:
1. What's on the paywall today — plans, prices, trial config — and where does it appear (post-onboarding, feature-gate, both)?
2. Platform and billing stack (StoreKit / Play Billing / Stripe / RevenueCat)? iOS App Store review applies?
3. What plan do MOST subscribers actually choose, and what's your trial-to-paid and day-0 cancellation rate if you know them?
4. What does your product's natural usage cycle look like (daily habit vs occasional task)? This drives trial length.
5. Is there a real, expiring discount you ever run — or would any countdown be fake?

THEN audit the paywall against these rules and show me the plan before coding:
- Sell the exit. The paywall's real enemy is fear of being trapped, not price. Add: an explicit trial timeline (Today full access → reminder day → charge day), a true reminder promise ("We'll email you before your trial ends") that you actually implement, and "$0.00 due today" phrasing on the CTA when a trial is active.
- One decision, defaulted: preselect the plan most users choose (defaults are read as advice — default to the common choice, not the most profitable one). Two plans usually beat three-plus.
- Price display: show the true billed price and period prominently (Apple review requires it; hiding it is a rejection and a trust hit) — with per-month reframing for annual plans as a secondary line, only while the reframed number stays trivially small.
- Honest anchors only: strikethroughs must come from real arithmetic (12× monthly vs annual). Delete any countdown that resets — a timer that lies is a lie detector users get to keep.
- Charm endings are fine (field-verified for deal-positioned products) but match your brand: premium products can round.
- Visible close/dismiss + a plain "Not now". A hidden exit signals you expect to win by trapping.
- Trial length: default to ~7 days unless my answer to Q4 argues otherwise (episodic products risk satiation with long trials); never copy a benchmark chart's correlational "longer converts better".
- Compliance: real StoreKit intro offers for trials, Restore Purchases path, terms/privacy links; ROSCA/state auto-renewal law still applies even though the FTC click-to-cancel rule was vacated — cancellation must not be a maze.

THEN implement with my design system, and tell me what to measure beyond paywall conversion: trial start rate, day-0 cancellation rate, trial-to-paid, refund/complaint volume, and 90-day retention — fear-removal changes often show up in the complaint and refund lines first.

End with a list of anything you consciously did NOT add because it lacked evidence or crossed the manipulation line.