Diagnose Stripe `card_declined` patterns

Why this matters

Payment failures cluster by reason — and each reason needs a different response:

• insufficient_funds → customer issue, retry in 3 days
• do_not_honor → bank issue, retry in 1 day, try different processor
• card_velocity_exceeded → your retry logic is too aggressive, slow down
• incorrect_cvc → UX issue, surface a clearer error in your form
• card_declined (generic) → ambiguous, possibly fraud — different ladder entirely

Most teams treat all payment failures as a single “Stripe error” line in their error tracker. They retry the same way regardless. The result: aggressive retries on real bank declines (annoys customer), gentle retries on velocity-exceeded (just stalls), and no UX fix for CVC errors (which are 100% addressable).

Agentry groups by decline_code in one query and tells you which patterns to fix in code vs which to handle in CS workflow.

What you get

• Top decline codes from the last 30 days with count and ARR exposure
• For each: a recommended response strategy (retry timing, UX fix, CS outreach)
• The specific customers in the top bucket so support can reach out before they churn

Walk through it

agentry_analytics_query {
  project_id: "default",
  hogql: "SELECT properties.decline_code AS code, count() AS cnt, uniq(distinct_id) AS users, sum(toFloat(properties.amount_cents) / 100) AS dollars_failed FROM events WHERE event = 'payment_failed' AND timestamp >= now() - INTERVAL 30 DAY GROUP BY code ORDER BY cnt DESC"
}

{
  "rows": [
    { "code": "insufficient_funds",       "cnt": 412, "users": 388, "dollars_failed": 28840 },
    { "code": "do_not_honor",             "cnt": 188, "users": 142, "dollars_failed": 14200 },
    { "code": "card_velocity_exceeded",   "cnt":  96, "users":  18, "dollars_failed":  4800 },
    { "code": "incorrect_cvc",            "cnt":  78, "users":  64, "dollars_failed":  4100 },
    { "code": "expired_card",             "cnt":  44, "users":  44, "dollars_failed":  2200 },
    { "code": "card_declined",            "cnt":  31, "users":  28, "dollars_failed":  1860 }
  ]
}

agentry_analytics_query {
  project_id: "default",
  hogql: "SELECT distinct_id, count() AS retry_attempts FROM events WHERE event = 'payment_failed' AND properties.decline_code = 'card_velocity_exceeded' AND timestamp >= now() - INTERVAL 30 DAY GROUP BY distinct_id ORDER BY retry_attempts DESC LIMIT 5"
}

{
  "rows": [
    { "distinct_id": "[email protected]", "retry_attempts": 12 },
    { "distinct_id": "[email protected]", "retry_attempts": 9 },
    { "distinct_id": "[email protected]", "retry_attempts": 8 }
  ]
}

The output

Stripe Payment Failures (30d), grouped by decline_code

CODE                         COUNT  USERS  $ EXPOSED   FIX TYPE
insufficient_funds            412    388    $28,840   CS workflow
do_not_honor                  188    142    $14,200   CS workflow
card_velocity_exceeded         96     18     $4,800   ★ YOUR BUG
incorrect_cvc                  78     64     $4,100   ★ UX FIX
expired_card                   44     44     $2,200   email reminder
card_declined (generic)        31     28     $1,860   ambiguous

★ ACTION ITEMS:

  card_velocity_exceeded (your retry logic is too aggressive)
    Affected customers (top 3):
       [email protected]         12 failed retries
       [email protected]             9 failed retries
       [email protected]      8 failed retries
    Fix: bump retry interval to >=24h between attempts.
    Comm: CS apology email to each affected user today.

  incorrect_cvc (UX is hiding the error)
    78 customers re-entered wrong CVC; many gave up.
    Fix: inline real-time validation + clearer error message.

  All others: Stripe Smart Retries + dunning workflow handles these.

Setting it up

You need a webhook handler for Stripe’s payment_intent.payment_failed or charge.failed event that re-emits to Agentry with decline_code:

// /api/webhooks/stripe
app.post("/webhooks/stripe", express.raw({ type: "application/json" }), async (req, res) => {
  const event = stripe.webhooks.constructEvent(
    req.body, req.headers["stripe-signature"]!, STRIPE_WEBHOOK_SECRET
  );

  if (event.type === "payment_intent.payment_failed") {
    const pi = event.data.object;
    const lastError = pi.last_payment_error;

    await fetch(`https://api.agentry.sh/v1/analytics/${process.env.AGENTRY_PROJECT_ID}/`, {
      method: "POST",
      headers: {
        "Authorization": `Bearer ${process.env.AGENTRY_DSN}`,
        "Content-Type": "application/json",
        "User-Agent": "myapp-stripe/1.0",  // REQUIRED — Cloudflare 403s default UAs
      },
      body: JSON.stringify({
        event: "payment_failed",
        distinct_id: pi.receipt_email ?? pi.customer,  // user identifier
        properties: {
          decline_code: lastError?.decline_code ?? "unknown",
          error_code:   lastError?.code,
          amount_cents: pi.amount,
          currency:     pi.currency,
          payment_intent_id: pi.id,
        },
      }),
    });
  }

  res.json({ received: true });
});

For richer grouping, also capture card_country, card_brand, and processor_response_code — useful for diagnosing fraud-vs-real declines down the line.

Variations

• “Same decline-code breakdown but split by checkout type (one-time vs subscription renewal). Different patterns dominate each.”
• “Show me the % of insufficient_funds decisions that EVENTUALLY succeed (next retry). My Smart Retries config feels too aggressive.”
• “For each customer with 3+ card_velocity_exceeded failures, draft a CS apology email offering account credit.”
• “Daily cron at 8am: post yesterday’s top decline_code and trend vs prior 7d average to #payments-oncall.” (uses a Routine)