Recipes
Stop staring at dashboards. Just ask.
64 paste-ready prompts that turn your agent into a debugger, a product analyst, an oncall, a growth marketer. Each one solves a real problem teams have — and ships with the setup code you need to try it.
Featured
Build a composite account-health dashboard
Score every B2B account on usage, revenue, and support load. Publish one URL your CS team checks instead of wrangling data each QBR.
Find your magic activation moment
Discover which first-24h action correlates highest with day-30 retention. Most teams can't answer this. You'll answer it in 90 seconds.
Nightly Routine: draft PRs for low-risk silent bugs
Routine runs at 2am, picks the top silent bug, investigates it, opens a draft PR if the fix is small and contained. Lights-out triage for the next morning's review.
Where exactly do shoppers drop off in checkout?
Build the product-view to purchase funnel with drop-off and time-on-step. The 1-prompt ecommerce funnel that Shopify analytics doesn't ship.
Predict churn 30 days before it happens
Build a behavioral early-warning system that flags at-risk users while there's still time to save them. No ML team required.
Track crash-free user rate per app version
Distinct users who hit a crash divided by DAU, per app version. The industry-standard mobile health metric — surface version-by-version drops fast.
Diagnose a customer complaint in 30 seconds
Paste a customer message. The agent pulls their session, finds the error they hit, walks their funnel, and tells you what to reply.
Find what broke after your last deploy
Diff error fingerprints before and after the latest deploy SHA. Surface regressions in 30 seconds, including a candidate fix.
Rank errors by revenue impact, not raw count
Multiply users-affected by their plan ARR to surface the bugs costing real money. Stop triaging by event volume.
Push notification: sent → opened → action conversion
Joined funnel from push provider's send webhook through open through in-app action. Per-campaign breakdown — what marketing platforms refuse to show you.
Build a signup funnel and find where users drop off
One prompt builds the full funnel from landing → activation, publishes it as a public dashboard, and ranks drop-off steps by severity.
Track trial-to-paid conversion by acquisition source
Build the trial-to-paid funnel split by acquisition source. Surface the channel that converts 8x better than the rest.
Get a weekly digest of what your agent did
Routine that reads the audit log every Friday and Slacks a category breakdown: cases resolved, flags toggled, surveys created. Don't trust — verify in 60s.
debug Stop fires. Find regressions. Catch silent bugs.
-
Track crash-free user rate per app version
2 minutesDistinct users who hit a crash divided by DAU, per app version. The industry-standard mobile health metric — surface version-by-version drops fast.
-
Diagnose a customer complaint in 30 seconds
30 secondsPaste a customer message. The agent pulls their session, finds the error they hit, walks their funnel, and tells you what to reply.
-
Find what broke after your last deploy
30 secondsDiff error fingerprints before and after the latest deploy SHA. Surface regressions in 30 seconds, including a candidate fix.
-
Rank errors by revenue impact, not raw count
2 minutesMultiply users-affected by their plan ARR to surface the bugs costing real money. Stop triaging by event volume.
-
Mobile background-sync failure monitoring
2 minutesBackground sync, refresh, prefetch jobs fail silently and degrade UX. Group failures by task_name and network_type to find the patterns.
-
Find IE/Safari/old-Chrome-only crashes
2 minutesSplit client-side errors by browser and version. Surface fingerprints concentrated in one engine — usually older Safari or a stale Chromium.
-
Track static-asset 404s per release
2 minutesGroup asset 404s by URL and deploy SHA. Catch stale CDN caches and missing hashed bundles before users see a blank page.
-
Diagnose CORS errors after a deploy
1 minuteFind CORS-blocked requests grouped by origin and endpoint. Surface the misconfigured Access-Control-Allow-Origin from a recent service move.
-
Find connection-pool / timeout patterns in errors
2 minutesSurface DB connection exhaustion, statement timeouts, and deadlock retries. Find the original slow query starving everything else.
-
Find what broke after the last npm update
30 secondsTie new error fingerprints to the deploy that bumped dependencies. Spot the silent regression nobody intended to ship.
grow Funnels. Activation. Churn. Content.
-
Find your magic activation moment
2 minutesDiscover which first-24h action correlates highest with day-30 retention. Most teams can't answer this. You'll answer it in 90 seconds.
-
Where exactly do shoppers drop off in checkout?
2 minutesBuild the product-view to purchase funnel with drop-off and time-on-step. The 1-prompt ecommerce funnel that Shopify analytics doesn't ship.
-
Predict churn 30 days before it happens
10 minutesBuild a behavioral early-warning system that flags at-risk users while there's still time to save them. No ML team required.
-
Push notification: sent → opened → action conversion
5 minutesJoined funnel from push provider's send webhook through open through in-app action. Per-campaign breakdown — what marketing platforms refuse to show you.
-
Build a signup funnel and find where users drop off
2 minutesOne prompt builds the full funnel from landing → activation, publishes it as a public dashboard, and ranks drop-off steps by severity.
-
Track trial-to-paid conversion by acquisition source
3 minutesBuild the trial-to-paid funnel split by acquisition source. Surface the channel that converts 8x better than the rest.
-
Find which products silently kill conversion
5 minutesPer-SKU funnel from product view to purchase. Surface products that convert below their category average — fix the laggards instead of generic PDP tweaks.
-
API quota usage as engagement and upsell timing
3 minutesFor each customer on a usage-based plan, show daily call volume as % of cap. Flag accounts approaching 80% — the perfect upgrade moment.
-
Is checkout too slow?
2 minutesCompute p50/p90/p99 of checkout duration split by mobile and desktop. Mobile p99 is usually 4-8x worse than desktop p50.
-
Auto-survey churned users and read the answers in chat
5 minutesStop guessing why customers leave. Trigger a 3-question survey on cancellation, then ask the agent to summarize the responses weekly.
ops Routines. Webhooks. Alerts. Dashboards.
-
Build a composite account-health dashboard
10 minutesScore every B2B account on usage, revenue, and support load. Publish one URL your CS team checks instead of wrangling data each QBR.
-
Nightly Routine: draft PRs for low-risk silent bugs
1 hour to set upRoutine runs at 2am, picks the top silent bug, investigates it, opens a draft PR if the fix is small and contained. Lights-out triage for the next morning's review.
-
Get a weekly digest of what your agent did
10 minutesRoutine that reads the audit log every Friday and Slacks a category breakdown: cases resolved, flags toggled, surveys created. Don't trust — verify in 60s.
-
Alert on unexpected agent mutations
30 minutesRoutine that watches the audit log for high-impact actions (flag deletes, suppression adds, cohort deletes). Pages #security if anything happens outside business hours.
-
Who's still on the old client?
1 minuteDistinct users per app_version over 7 days. See the long tail of old clients — informs the force-update decision and deprecation timing.
-
Per-customer API call analytics
3 minutesGroup api_request events by customer_id over 30 days with daily breakdown. The view usage-based pricing needs but most teams cobble together from logs.
-
Auto-document your captured event taxonomy
1 minuteEvery event captured in the last 30 days with count, first-seen, last-seen, sample property keys. Markdown table for Notion — your event taxonomy doc that never goes stale.
-
Match supply to demand per region or category
10 minutesPer-region ratio of buyer-side events to seller-side events. Spot starved regions before they churn. Liquidity is the metric that decides supply vs demand growth investment.
-
Model Black Friday from last year's data
5 minutesPull peak ingest rates and page-view rates from last year's holiday window. Real numbers for the infra capacity conversation — no more back-of-envelope guesses.
-
Build a public live-stats widget for your marketing site
2 minutesPublish real product metrics to your homepage in 30 seconds. Social proof that updates itself, no backend, no auth, embed-friendly.
Try any of these in your own agent.
Send this to Claude Code, Cursor, Codex, or any coding agent. It reads the canonical reference, picks MCP or plain HTTP, and sets you up.