When does an AI agent use this pattern?

When the trigger described above matches the situation the agent is handling. The agent queries FusedFrames at runtime, this pattern is returned and the agent follows the recorded reasoning and steps to reach the recorded outcome.

How were the steps captured?

By the desktop app on the machine of someone who actually does this work. It records clicks, keystrokes, copy and paste, drag and drop, selected text and screen regions across Stripe and NetSuite, then groups them into the meaningful steps shown above.

Where does the reasoning come from?

From the operator. When the desktop app sees a decision the action alone cannot explain, it asks why in the moment. The operator's answer is recorded and becomes the reasoning attached to the pattern, so the AI agent gets the thinking and not just the steps.

What if my team handles this differently?

Capture how your team actually does it. The desktop app records what your operator does on your tools and the web app distills that into a pattern shaped by your team. Each team's library reflects their own approach rather than the example shown here.

What if a case looks like this pattern but does not quite fit?

The pattern is linked to 1 alternative. The agent can follow the connections shown on this page to a related pattern that matches the case more closely.

How does my AI agent actually call this pattern?

Through the read-only REST API or the npm CLI. Create an API key in the dashboard, choose whether it accesses all libraries or specific ones and have your agent query at runtime. The response is structured JSON ready for tool use.

Is the data shown on this page from a live customer?

No. Example libraries on this site are illustrative. Patterns in your own account are built from your team's captured actions and stay private to your workspace.

How do I build a pattern like this for my team?

Install the desktop app on the machine of the person who already does this work, ask them to handle a real case end to end, then distill the captured action into a pattern in the web app. The pattern you end up with mirrors how your team actually operates.

Sending a personalised dunning email to a high-value customer in arrears

For customers above $5,000 MRR whose manual retry has not recovered the charge, the senior RevOps manager suppresses Stripe's automated dunning and sends a personal email instead. The email reaches the named accounts payable contact with the invoice details, a plain-language failure reason and a single payment-update link.

Tags

dunninghigh-value-customerpersonalisationstripearrelationship

Lets your agent filter to the right pattern

Categories and tags scope the retrieval set, so your agent receives only the patterns relevant to the task instead of scanning the full library.

What and why

The observed behaviour and the reasoning behind it.

Behaviour

When a customer with monthly recurring revenue above $5,000 has had a charge fail and the manual retry has not recovered it, the senior RevOps manager suppresses Stripe's automated dunning email and sends a personalised email from her own address to the named accounts payable contact at the customer with the invoice number, the amount, the failure reason in plain language and a single link to update payment method. Automated dunning is left enabled for accounts below the threshold.

Reasoning

Automated dunning emails work for low-value subscriptions where the cost of writing a personal note is higher than the value at risk. Above a $5,000 monthly recurring revenue threshold the relationship cost of an automated email outweighs the operational saving: the named contact reads the email as a brusque collections notice and the account moves to the front of the customer's churn evaluation queue. A personalised email from a known sender with the failure reason explained in plain language recovers the charge in roughly four out of five cases without damaging the relationship.

Gives your agent an operator's reasoning

Behaviour records the action; reasoning records the rationale. Your agent applies both to handle cases that diverge from the captured examples.

Cause and effect

What initiates this pattern and what it produces.

Trigger

A customer with monthly recurring revenue above $5,000 has had at least one Stripe charge fail and the first manual retry has not recovered the payment.

Outcome

The named accounts payable contact receives a personalised email from the senior RevOps manager with the invoice details and a payment-update link, Stripe automated dunning stays suppressed for the duration and the customer either updates the card so the next retry succeeds or escalates the conversation to the relationship owner before recognition is paused.

Tells your agent when to act and what to verify

Your agent stays within the scope set by the trigger and outcome, so it doesn't extend beyond the work or finish before the outcome is met.

Standard operating procedure

Step-by-step instructions to reproduce this pattern.

NetSuite

Pull the customer's named accounts payable contact, the open invoice number and the monthly recurring revenue figure.

The named contact is on the customer record under Contacts, not on the invoice. Confirm monthly recurring revenue is above $5,000 because below that threshold the automated dunning is the right path. The MRR figure is the trailing-three-month rolling average, not the current month.

Expected: The named contact, invoice number and MRR figure are captured.

Stripe

Confirm Smart Retries and automated dunning are suppressed for the customer.

If Stripe automation is still active the customer will receive both the personal email and the automated email and the personal email loses its weight. The suppression should already be in place from the failed-charge retry pattern but always confirm before sending.

Expected: Stripe Smart Retries and dunning automation are suppressed for the customer.

Stripe

Generate a payment-update link from the customer's billing portal and copy the secure URL.

Use the customer billing portal link, not the raw Stripe Checkout link. The portal link lets the customer update the card on file rather than process a one-off payment, which fixes the underlying problem. Copy the URL but do not click it; clicking creates a session that can fail validation later.

Expected: A secure payment-update URL is on the clipboard.

NetSuite

Open the customer record and click Email Customer, picking the High-Value Dunning template, with the senior RevOps manager set as the From user and the relationship owner copied.

Send from the senior RevOps manager's NetSuite user, never the `billing@` shared mailbox. Copying the relationship owner means they see the message before the customer does and can flag if the timing is wrong. The High-Value Dunning template seeds subject and body with the customer entity and invoice number; no urgency words appear in the template by design.

Expected: The Email Customer pane is open with the High-Value Dunning template loaded, the right From user, the named recipient and the relationship owner copied.

NetSuite

Edit the template body in place to cover the invoice number, the amount, the failure reason in plain language and paste the payment-update link from the clipboard.

Plain language matters: 'the card on file was declined' lands better than 'card_declined error'. Avoid words like overdue, urgent or final notice. Use the named contact's first name, mention you noticed the failure and offer to jump on a quick call if anything has changed at their end. Paste the Stripe portal link verbatim, never re-type it.

Expected: A short, polite, plain-language email body is composed in NetSuite with the payment-update link inline.

NetSuite

Send the email from NetSuite and confirm the timeline entry on the customer record records the send time, recipient and From user.

The send time matters because the next manual retry is scheduled three working days after this email. NetSuite's customer timeline logs it automatically against the customer record, which the billing analyst running the retry reads to pick up the timeline. If no reply has come back at the next retry slot, retry; if a reply comes back asking for time, pause until the agreed date.

Expected: The email is sent from NetSuite and the customer record timeline carries the send entry with timing, recipient and sender.

Stripe

Schedule the next manual retry three working days from the email send.

Three working days lets accounts payable cycle the request through their own approvals. Going faster lands on the same person who has not yet had time to act; going slower risks recognition having to pause anyway. If the customer has replied agreeing to a date, schedule the retry for the morning after that date.

Expected: The next manual retry is on the calendar three working days from the email send.

Hands your agent your team's exact steps

Your agent executes the documented procedure in order, against the applications named at each step, producing consistent output across human and agent runs.

Book a demo

Related patterns

How this pattern connects to other patterns in the library.

Often previous

Retrying a failed Stripe subscription charge on a three-day cadence

Often next

Pausing NetSuite revenue recognition after a customer enters dunning

Alternative to

Retrying a failed Stripe subscription charge on a three-day cadence

Lets your agent confirm the match and its scope

Alternative patterns let your agent compare candidates and select the closest match. Previous and next patterns define position in the workflow, so the agent operates within the scope of this one.

Supporting actions

Actions that provide evidence for this pattern.

Sent personalised dunning email to Aurelius Partners ($14,200 invoice INV-2026-04-1198)

Generated Stripe billing portal link for cus_RvUprq for payment update

Copied relationship owner Felix Nordstrom on Northgate Capital dunning email

Logged 28 April send time on Halberd Cybersecurity dunning notes

Shows your agent the evidence behind the pattern

Each pattern is derived from captured action sequences. Your agent can reference the source actions to verify any field, so nothing it acts on is authored by hand or hallucinated.

Metadata

Timestamps and identifiers.

Evidence	Observed 19 times across 2 connections
Applications	Stripe, NetSuite
First seen	12 Feb 2026, 11:18
Last seen	4 May 2026, 14:32

Helps your agent rank patterns by confidence

Action count and last-seen timestamp weight each pattern by frequency and recency, so your agent selects the highest-scoring match rather than the first returned.

Questions

Frequently asked questions

Book a demo View all examples

Speak to the founder

Get a demo. Watch a live capture, then an AI agent query the result.

Ask anything. Pricing, security or integrating with your stack.

No purchase obligation

Book a call

Start capturing

Record in minutes. Install once and work as normal.

Plug AI agents in. One API call from any AI agent stack.

Refund on unused credits if you cancel