Recipes
Try prompts for experiment analysis, campaign review, implementation checks, recurring reports, and next-test planning.
Recipes are prompts you can use as a starting point. Copy one into Superwall Agents, then swap in your app, campaign, placement, date range, or segment. Good prompts name the business question and the decision you want to make. Ask for the analysis, the evidence, and the next step.
Experiment analysis
Use these when you want to understand what changed and what to test next.
Analyze the latest experiment results for our onboarding paywall. Tell me what changed, which variant is winning, which segments look different, and what experiment we should run next.Analyze the latest paywall experiment. Which variant is winning, what segment differences matter, and what should we test next?Compare paywall conversion, trial conversion, and ARPU over the last 30 days by country and demand score bucket. Show charts and call out the biggest opportunities.Campaign and placement review
Use these when you want to find weak spots in campaign performance.
Find campaigns with strong traffic but weak paywall conversion. Group by placement and suggest the highest-leverage changes.Compare trial conversion and ARPU by country over the last 30 days. Show charts and recommend where we should run localized paywall tests.Look at users who saw paywalls multiple times but did not convert. What patterns do they share, and what experiment could address them?Implementation checks
Use these when your app repo is available and you want the agent to compare implementation details against your Superwall setup.
Inspect the iOS repo connected through GitHub and verify that our Superwall SDK integration correctly identifies users, resets on logout, registers placements, and handles subscription status.Inspect the connected iOS repo and verify that the Superwall SDK integration matches our selected application. Check configuration, identify/reset behavior, placement registration, and subscription status handling.Find every placement registered in that repo and compare it to our campaign setup. Call out missing, unused, or inconsistently named placements.Recurring reports
Use these when the same analysis should happen on a schedule.
Every Monday at 9 AM America/Chicago, review the previous week's experiment results and suggest three next tests with expected impact and risks.Analyze the previous 7 days of onboarding campaign performance. Compare paywall conversion, trial conversion, paid conversion, and ARPU to the prior 7 days. Create charts, summarize notable changes, and recommend three experiments for the next week.Multi-app or multi-project work
If you work across multiple apps or organizations, name the target directly in the prompt.
For the Acme Fitness iOS project, analyze onboarding campaign performance for the last 14 days and suggest the next experiment.How is this guide?