How Stripe Dunning Intelligence Automates Intent Scoring

Intelligent payment recovery with AI-personalized dunning. That single sentence captures a workflow gap that costs revops, customer success teams hours every week. The manual process behind what Stripe Dunning Intelligence automates is familiar to anyone who has worked in a revenue organization: someone pulls data from Stripe, Gmail, Slack, copies it into a spreadsheet or CRM, applies a mental checklist, writes a summary, and routes it to the next person in the chain. Repeat for every record. Every day.

Three problems make this unsustainable at scale. First, the process does not scale. As volume grows, the human bottleneck becomes the constraint. Whether it is inbound leads, deal updates, or meeting prep, a person can only process a finite number of records before quality degrades. Second, the process is inconsistent. Different team members apply different criteria, use different formats, and make different judgment calls. There is no single standard of quality, and the output varies from person to person and day to day. Third, the process is slow. By the time a manual review is complete, the window for action may have already closed. Deals move, contacts change roles, and buying signals decay.

These are not theoretical concerns. They are the operational reality for revops, customer success teams handling intent scoring and revenue operations workflows. Every hour spent on manual data processing is an hour not spent on the work that actually moves the needle: building relationships, closing deals, and driving strategy.

This is the gap Stripe Dunning Intelligence fills.

Four Agents. Five CRS Signals. AI-Personalized Dunning.

Stripe Dunning Intelligence is a multiple-node n8n workflow with 4 specialized agents. Each agent handles a distinct phase of the pipeline, and the handoff between agents is deterministic — no ambiguous routing, no dropped records. The blueprint is designed so that each agent does one thing well, and the overall pipeline produces a consistent, auditable output on every run.

Here is what each agent does:

• Fetcher (Webhook + Code): Stripe Webhook fires on invoice.payment_failed.
• Analyst (Tier 1 Reasoning): the primary reasoning model performs multi-signal churn risk scoring across 5 CRS categories: payment_failure_recurrence (failure frequency, consecutive failures, pattern analysis), plan_tier_value (MRR at risk, plan tier, ARR impact), usage_recency (recent activity, feature adoption, engagement level), tenure_depth (customer tenure, onboarding completion, expansion history), and support_history (open tickets, sentiment, escalation history).
• Writer (Tier 2 Creative): the analysis model composes a personalized dunning email matched to the selected recovery strategy: gentle_reminder (friendly nudge with payment link), urgency_nudge (deadline emphasis with consequences), value_reinforcement (highlight what they lose), payment_method_update (card expiry guidance), or downgrade_offer (retention with reduced tier).
• Deliverer (Code + 3-way Route): Routes based on CRS composite score.

When the pipeline completes, you get structured output that is ready to act on. The blueprint bundle includes everything needed to deploy, configure, and customize the workflow. Specifically, you receive:

• Production-ready 28-node n8n workflow — import and deploy
• Stripe Webhook integration for invoice.payment_failed events
• 5-signal CRS taxonomy: payment failure recurrence, plan tier value, usage recency, tenure depth, support history
• Per-signal scoring (1–10) with weighted composite and evidence-based churn risk assessment
• 5 recovery strategies: gentle reminder, urgency nudge, value reinforcement, payment method update, downgrade offer
• AI-personalized dunning emails matched to recovery strategy and churn risk level
• 3-way routing: urgent (email + Slack alert), standard (email), gentle (soft reminder)
• Slack alerts for high-risk accounts (CRS ≥ 7) with full account context
• Dual-model: the primary reasoning model (CRS analysis) + the analysis model (email composition) at $0.132/invoice
• ITP test results with 20 records, 14/14 milestones, 100% defensible

Every component is designed to be modified. The agent prompts are plain text files you can edit. The workflow nodes can be rearranged or extended. The scoring criteria, output formats, and routing logic are all exposed as configurable parameters — not buried in application code. This means Stripe Dunning Intelligence adapts to your specific process, terminology, and integration requirements without forking the entire workflow.

Understanding how the pipeline works helps you customize it for your environment and troubleshoot issues when they arise. Here is a step-by-step walkthrough of the Stripe Dunning Intelligence execution flow.

Step 1: Fetcher

Tier: Webhook + Code

Stripe Webhook fires on invoice.payment_failed. Fetcher pulls full customer context from Stripe API: subscription history, payment method metadata, invoice history, plan tier, recent charges, and customer lifetime value. Normalizes all signals into a unified risk assessment payload for downstream analysis.

This stage is critical because it ensures that downstream agents receive structured, validated input. Each agent in the pipeline trusts the output contract of the previous agent. If Fetcher identifies an issue — a missing field, a low-confidence score, or an unexpected input format — the pipeline handles it explicitly rather than passing garbage downstream. This is the difference between a prototype and a production-grade workflow: every handoff is defined, every edge case is documented.

Step 2: Analyst

Tier: Tier 1 Reasoning

the primary reasoning model performs multi-signal churn risk scoring across 5 CRS categories: payment_failure_recurrence (failure frequency, consecutive failures, pattern analysis), plan_tier_value (MRR at risk, plan tier, ARR impact), usage_recency (recent activity, feature adoption, engagement level), tenure_depth (customer tenure, onboarding completion, expansion history), and support_history (open tickets, sentiment, escalation history). Each signal scored 1–10 with weighted composite and evidence-based assessment. Selects one of 5 recovery strategies matched to risk profile.

This stage is critical because it ensures that downstream agents receive structured, validated input. Each agent in the pipeline trusts the output contract of the previous agent. If Analyst identifies an issue — a missing field, a low-confidence score, or an unexpected input format — the pipeline handles it explicitly rather than passing garbage downstream. This is the difference between a prototype and a production-grade workflow: every handoff is defined, every edge case is documented.

Step 3: Writer

Tier: Tier 2 Creative

the analysis model composes a personalized dunning email matched to the selected recovery strategy: gentle_reminder (friendly nudge with payment link), urgency_nudge (deadline emphasis with consequences), value_reinforcement (highlight what they lose), payment_method_update (card expiry guidance), or downgrade_offer (retention with reduced tier). Tone, urgency, and messaging calibrated to CRS level.

This stage is critical because it ensures that downstream agents receive structured, validated input. Each agent in the pipeline trusts the output contract of the previous agent. If Writer identifies an issue — a missing field, a low-confidence score, or an unexpected input format — the pipeline handles it explicitly rather than passing garbage downstream. This is the difference between a prototype and a production-grade workflow: every handoff is defined, every edge case is documented.

Step 4: Deliverer

Tier: Code + 3-way Route

Routes based on CRS composite score. Urgent (CRS ≥ 7): sends dunning email via Gmail AND posts Slack alert with account context for immediate human follow-up. Standard (CRS 4–6): sends dunning email via Gmail. Gentle (CRS < 4): sends soft reminder email via Gmail. All paths log delivery status and CRS metadata.

This stage is critical because it ensures that downstream agents receive structured, validated input. Each agent in the pipeline trusts the output contract of the previous agent. If Deliverer identifies an issue — a missing field, a low-confidence score, or an unexpected input format — the pipeline handles it explicitly rather than passing garbage downstream. This is the difference between a prototype and a production-grade workflow: every handoff is defined, every edge case is documented.

The entire pipeline executes without manual intervention. From trigger to output, every decision point is deterministic: if a condition is met, the next agent fires; if not, the record is handled according to a documented fallback path. There are no silent failures. Every execution produces a traceable audit trail that you can review, export, or feed into your own reporting tools.

This architecture follows the ForgeWorkflows principle of tested, measured, documented automation. Every node in the pipeline has been validated during ITP (Inspection and Test Plan) testing, and the error handling matrix in the bundle documents the recovery path for each failure mode.

Every metric is ITP-measured. The Stripe Dunning Intelligence agent monitors failed Stripe invoices, scores churn risk across 5 signals with evidence-based assessment, selects from 5 recovery strategies, composes personalized dunning emails, and routes delivery based on risk severity at $0.132/invoice.

The primary operating cost for Stripe Dunning Intelligence is the per-execution LLM inference cost. Based on ITP testing, the measured cost is: Cost per Invoice: $0.132/invoice (ITP-measured average). This figure includes all API calls across all agents in the pipeline — not just the primary reasoning step, but every classification, scoring, and output generation call.

To put this in context, consider the manual alternative. A skilled team member performing the same work manually costs $50–75/hour at a fully loaded rate (salary, benefits, tools, overhead). If the manual version of this workflow takes 20–40 minutes per cycle, that is $17–50 per execution in human labor. The blueprint executes the same pipeline for a fraction of that cost, with consistent quality and zero fatigue degradation.

Infrastructure costs are separate from per-execution LLM costs. You will need an n8n instance (self-hosted or cloud) and active accounts for the integrated services. The estimated monthly infrastructure cost is $13–20/month (100 failed invoices/month), depending on your usage volume and plan tiers.

Quality assurance: BQS audit result is 12/12 PASS. ITP result is 20 records, 14/14 milestones PASS, 74% exact strategy, 100% defensible. These are not marketing claims — they are test results from structured inspection protocols that you can review in the product documentation.

9 files — workflow JSON, system prompts, configuration guides, and complete documentation.

When you purchase Stripe Dunning Intelligence, you receive a complete deployment bundle. This is not a SaaS subscription or a hosted service — it is a set of files that you own and run on your own infrastructure. Here is what is included:

• stripe_dunning_intelligence_v1_0_0.json — The 28-node n8n workflow
• README.md — 10-minute setup guide with Stripe webhook, Gmail, Slack, and Anthropic configuration
• system_prompt_analyst.txt — Analyst system prompt (CRS 5-signal taxonomy, weighted scoring, strategy selection)
• system_prompt_writer.txt — Writer system prompt (5 recovery strategies, tone calibration, personalization rules)
• crs_scoring_guide.md — CRS signal definitions, scoring calibration, and strategy mapping examples
• stripe_webhook_setup.md — Stripe webhook endpoint configuration for invoice.payment_failed events
• email_templates_reference.md — Recovery strategy email examples and customization guidance
• itp_results.md — ITP test results — 20 records, 14/14 milestones, 74% exact strategy, 100% defensible
• CHANGELOG.md — Version history

Start with the README.md. It walks through the deployment process step by step, from importing the workflow JSON into n8n to configuring credentials and running your first test execution. The dependency matrix lists every required service, API key, and estimated cost so you know exactly what you need before you start.

Every file in the bundle is designed to be read, understood, and modified. There is no obfuscated code, no compiled binaries, and no phone-home telemetry. You get the source, you own the source, and you control the execution environment.

Stripe Dunning Intelligence is built for Revops, Customer Success teams that need to automate a specific workflow without building from scratch. If your team matches the following profile, this blueprint is designed for you:

• You operate in a revops or customer success function and handle the workflow this blueprint automates on a recurring basis
• You have (or are willing to set up) an n8n instance — self-hosted or cloud
• You have active accounts for the required integrations: Stripe account (with webhook endpoint configured), Gmail (Google Workspace or personal), Slack workspace
• You have API credentials available: Anthropic API, Stripe (webhook endpoint), Gmail OAuth2, Slack Bot Token
• You are comfortable importing a workflow JSON and configuring API keys (the README guides you, but basic technical comfort is expected)

This is NOT for you if:

• Does not retry failed payments — Stripe handles payment retries natively
• Does not modify Stripe subscriptions or cancel accounts — sends outreach only
• Does not monitor successful payments — that is what Expansion Revenue Detector does
• Does not scrape external websites — all data from Stripe API
• Does not monitor account health over time — that is what Account Health Intelligence Agent does
• Does not re-engage dormant contacts — that is what Contact Re-Engagement Scorer does

Review the dependency matrix and prerequisites before purchasing. If you are unsure whether your environment meets the requirements, contact support@forgeworkflows.com before buying.

Deployment follows a structured sequence. The Stripe Dunning Intelligence bundle is designed for the following tools: n8n, Anthropic API, Stripe, Gmail, Slack. Here is the recommended deployment path:

1. Step 1: Import workflow and configure credentials. Import stripe_dunning_intelligence_v1_0_0.json into n8n. Configure Stripe webhook for invoice.payment_failed events, Anthropic API key, Gmail OAuth2 credentials, and Slack Bot Token following the setup guides.
2. Step 2: Configure webhook endpoint and Slack channel. Set up the Stripe webhook endpoint pointing to your n8n webhook URL. Configure the target Slack channel for urgent alerts. Review the CRS scoring guide for signal definitions and strategy mapping.
3. Step 3: Activate and verify. Enable the workflow in n8n. Trigger a test invoice.payment_failed event from Stripe (use test mode or CLI). Verify the dunning email is composed with the correct recovery strategy and delivered via Gmail. Check Slack alert fires for CRS >= 7.

Before running the pipeline on live data, execute a manual test run with sample input. This validates that all credentials are configured correctly, all API endpoints are reachable, and the output format matches your expectations. The README includes test data examples for this purpose.

Once the test run passes, you can configure the trigger for production use (scheduled, webhook, or event-driven — depending on the blueprint design). Monitor the first few production runs to confirm the pipeline handles real-world data as expected, then let it run.

For technical background on how ForgeWorkflows blueprints are built and tested, see the Blueprint Quality Standard (BQS) methodology and the Inspection and Test Plan (ITP) framework. These documents describe the quality gates every blueprint passes before listing.

Ready to deploy? View the Stripe Dunning Intelligence product page for full specifications, pricing, and purchase.