Failed-payment recovery

Every week a recovery agent pulls failed charges and expiring cards from your billing provider, segments customers by failure cause, and drafts matched recovery emails — you approve every send before it goes out.

Saves you ~2.5 h / week

Start with this playbook

How it works

Trigger
On the “Weekly recovery run” schedule.
Job
Pull failures and expiring cards, segment by cause, draft matched outreach.
Outcome
Cause-matched recovery emails and a tracked recovery queue ready for approval.

What it installs

Agents 2

  • Payment Recovery Agent

    Owns the weekly failed-payment run: pulls failures and expiring cards, drafts cause-matched outreach for approval, and logs outcomes.

  • Failed-payment recovery Quality Reviewer

    Checks primary evidence, domain controls, deliverable completeness, and communication quality, stopping the run when the work is wrong, unsupported, incomplete, or uncertain.

Teams 1

  • Failed-payment recovery quality team

    The delivery agents produce the work while an independent quality reviewer checks each workflow handoff against explicit evidence, domain, and communication requirements before the run can continue.

Workflows 1

  • Failed-payment recovery

    Pull failures and expiring cards, segment by cause, draft matched outreach, approve the batch, and log outcomes.

Documents 1

  • Recovery tracker

    The living record of every failed payment: recovered MRR, outstanding balances, and write-offs.

Goals 1

  • Failed payments recovered before they become churn

    Keep involuntary churn low by catching every failed charge and expiring card within a week. Success looks like: Every failed charge enters a cause-matched, human-approved outreach sequence within one weekly run, and the recovery tracker shows current recovered, outstanding, and unrecoverable MRR with no customer in more than one sequence.

Skills 2

  • failed-payment-segmentation

    Segment failed charges by decline type and run the dunning stack — pre-dunning expiry alerts, decline-aware retries, a timed four-email sequence, grace period, hard cancel — against recovery benchmarks. Adapted from coreyhaines31/marketingskills/churn-prevention.

  • recovery-outreach-writing

    Write the four-email dunning sequence — day 0 friendly alert, day 3 reminder, day 7 urgency, day 10 final warning — with a no-login payment link, concrete loss framing, and blameless plain-text copy. Adapted from coreyhaines31/marketingskills/churn-prevention.

Schedules 1

  • Weekly recovery run

    Runs the failed-payment recovery cycle weekly: pull failures, segment, draft, approve, log. ## Professional quality control Objective: complete the recurring Failed-payment recovery operating cycle and deliver a review-ready, evidence-backed result rather than merely report that the schedule ran. Start by fixing the review period, reading the current source records and prior run, confirming required access, and listing missing or contradictory inputs. Execute the bundle's full authored method in order, retaining source, calculation, command, or before/after evidence for load-bearing findings. Separate facts from interpretation, apply supplied policy without inventing thresholds, and stop any branch that requires missing authority or an unconfirmed human rule. Produce the complete named deliverable plus an evidence record, assumptions, exceptions, unresolved questions, and concrete next actions with owners where the method calls for them. Run the workflow's independent verifier checks and fix failures before requesting approval. The task is done only when every requested section and quality criterion passes or a blocker is explicit; silence, inaccessible data, or polished prose is not proof of completion. Recompute material figures independently from raw records; verify period, currency, sign, formula, rounding, tie-outs, and roll-forwards. Distinguish accounting policy from assumptions and route judgment to the human. Financial narrative must explain drivers plainly without generic AI phrasing, invented precision, or certainty unsupported by the books. The human retains authority over publication, sending, spend, signing, merging, deployment, and other consequential external actions.

Connectors pick at least 1 of 4

  • Stripe

    Stripe

    Connects to Stripe so the recovery agent can read failed charges, card expiry dates, and subscription status for the customers it drafts outreach to.

    Open the Stripe connector
  • Paddle

    Paddle

    Connects to Paddle so the recovery agent can read failed transactions, card expiry dates, and subscription status for the customers it drafts outreach to.

  • Polar

    Polar

    Connects to Polar so the recovery agent can read failed orders, payment-method state, and subscription status for the customers it drafts outreach to.

  • PayPal

    PayPal

    Connects to PayPal so the recovery agent can read failed transactions, billing-agreement state, and subscription status for the customers it drafts outreach to.

Folders 1

  • Payment recovery

Requirements

  • Billing data in your payment provider — The agent reads failed charges, card expiry dates, subscription status, and customer records from the billing provider you pick during setup (Stripe, Paddle, Polar, or PayPal). Until that access is authorized, it works from failure exports you attach to the run.

Setup guide

How to Automate Failed Payment Recovery

A practical guide to recovering failed subscription payments with an agent: segmentation, retry logic, drafted emails, and approvals.

Read the setup guide

Don't see your workflow? Describe it.

A sentence or two about a recurring job is enough. We design the playbook that runs it and show you exactly what it saves.

* What keeps taking time you don't have? *

Takes a minute · no account needed