Tone Profiles and Experiments

Tone Profiles define how eligible payment communications should sound. Tone Experiments compare two profiles on real, eligible workflow traffic and summarize customer assignments and recorded payment conversions.

Neither feature sends a message by itself. A profile or experiment affects communication only when a tone-enabled workflow has a template, a customer, and the required delivery and AI configuration.

Before You Start

• Connect and test the communication channels used by the workflow.
• Create or identify a payment-reminder template used by a tone-enabled workflow.
• Confirm customer records and invoice context are available to that workflow.
• Configure the workspace's AI provider if you expect text transformation.
• Review required language and prohibited phrases with qualified legal or compliance owners.

Open Tone Profiles

1. Open Receivables.
2. Select Tone Profiles.
3. Review the performance summary at the top.
4. Manage profiles under Your Tone Profiles.

Tone Performance Analytics

The page shows:

• Communications — total tracked communications associated with an explicitly linked tone profile
• Sent — tracked communications currently recorded as sent
• Delivered — tracked communications with delivered status
• Delivery rate — delivered count divided by total tracked communications
• Deliveries by tone profile — delivered count grouped by linked profile
• Weekly send volume — sent count grouped by week

These are delivery counts, not payment-conversion or collection-speed metrics. The page currently uses all available performance data and a weekly timeline; it does not provide a visible date filter.

Analytics attribution follows the profile explicitly linked to a communication template. Communications that use a team default without a direct template link, or that receive an experiment override at send time, may not be attributed to the profile you expect in Deliveries by tone profile.

Create a Tone Profile

1. Select Create Profile.
2. Enter a name that describes the intended use.
3. Choose a quick-start template or Custom configuration.
4. Review Tone Settings.
5. Review Content Rules.
6. Select Save Profile.
7. Use Set Default after reviewing the profile if it should be the team's fallback.

New profiles are not made default automatically.

Quick-start choices

A quick start prefills the profile. You can continue editing it before saving.

Tone settings

Choose an Empathetic, Neutral, or Firm preset, then adjust:

• formality from casual to formal
• empathy from direct to compassionate
• urgency from gentle reminder to high priority
• reading level from grade 1 through grade 18
• brand voice description

Content rules

Configure:

• blocked phrases
• required disclaimers
• optional maximum character length

These rules validate transformed content. They are not a legal guarantee and are not a hard delivery gate for every path. If a transformed body violates the configured rules, the tone step can fall back to the original template content; the communication may still proceed. Review the original template as carefully as the generated version.

How a Profile Is Chosen

For an eligible tone-enabled communication:

1. A profile linked directly to the template is preferred.
2. If the template has no profile, the team default can be used.
3. An applicable customer-segment rule can adjust the profile or its settings.
4. A running experiment can replace that choice with the customer's assigned A or B profile.

If no profile is available, the original template is used. If the AI provider is unavailable or transformation fails, the original template content is also used rather than blocking the communication.

This precedence applies to tone-enabled workflow communication. Recovery steps created in Settings → Receivables Controls do not expose a template selector and should not be assumed to use tone profiles.

Manage Existing Profiles

• Select the edit icon to change the name, quick-start-derived configuration, tone settings, or content rules.
• Select Set Default to replace the current team default.
• Select the delete icon and confirm to permanently remove a profile.

Deleting a profile cannot be undone. Templates linked to it fall back to the team default. Experiments and segment rules linked to the deleted profile can also be removed. Choose a replacement, update active use, and preserve experiment results before deleting.

Open Tone Experiments

1. Open Receivables.
2. Select Tone Experiments.
3. Create a new experiment or select View details on an existing one.

Experiment Lifecycle

Draft

Creating an experiment stores:

• name
• optional description
• variant A profile
• variant B profile
• traffic percentage assigned to variant A, with the remainder assigned to B

The two profiles must be different. A new experiment starts as Draft and does not affect communication until you select Start experiment.

Running

Only one tone experiment can run for a team at a time. Starting another produces a conflict until the current experiment is paused or completed.

When an eligible communication is prepared with customer context:

1. The customer is assigned to A or B according to the traffic split.
2. The assignment remains fixed for that customer in that experiment.
3. The assigned profile becomes the tone choice for eligible messages during the running experiment.

Traffic split applies to customer assignment, not to a guaranteed message count. Small samples and repeat messages to the same customer can produce an uneven observed split.

Paused

Select Pause to stop the experiment from being selected for new eligible communication. Pausing also removes it from the automatic running-experiment lookup used by payment outcome recording. Payments that arrive while the experiment is paused may not be credited to its conversion summary.

Completed

Select Mark completed when the measurement window is finished. Then choose Variant A wins or Variant B wins.

Winner selection is manual. It records the chosen variant but does not make that profile the team default or update templates. Roll out the winner separately in Tone Profiles and any template configuration.

What Experiment Results Mean

The details view shows:

• assignment count
• conversion count
• overall conversion rate
• conversion rate for A and B
• customer IDs assigned to each variant
• created, started, and completed times

A conversion is an assignment with a recorded outcome containing a true converted or paid result. In the supported recovery completion path, a customer's payment can record that result while the experiment is still running.

The denominator is assigned customers, not delivered messages. The page does not show statistical significance, confidence intervals, time-to-payment, average recovered amount, or a guard against calling a winner on a very small sample.

Not every invoice status change records an experiment outcome. Manual paid-state corrections and alternative payment paths can leave an assigned customer without a recorded conversion. Verify the summary and source payment records before interpreting the rate.

Experiment Safety and Limits

• Create at least two profiles before beginning.
• Use profiles that differ in one intentional hypothesis when possible.
• Keep the experiment running through the payment-observation window if automatic conversion attribution matters.
• Do not edit or delete variant profiles during a running experiment.
• Do not treat delivery rate as collection conversion.
• Do not treat a higher raw conversion rate as conclusive without enough assignments and a suitable review period.
• Delete permanently removes the experiment and its assignments; the list does not present a separate confirmation dialog.
• A 0% or 100% traffic split is allowed, but it prevents a useful two-sided comparison.

Troubleshooting

A profile saved but messages did not change

Confirm that the message comes from a tone-enabled workflow with a template and that the template-specific or default profile is available. Then confirm the AI provider is configured. On failure, the original template is used.

Tone analytics show no profile data

The analytics only include communications associated with templates that explicitly reference a tone profile. A default-only or experiment-overridden use can be missing from the profile grouping.

An experiment has no assignments

Confirm that it is Running, that no other experiment is running, and that eligible template-based workflow communications are being prepared with customer context. Creating an experiment or an Auto-chase policy alone does not create assignments.

Assignments exist but conversions remain zero

Confirm that assigned customers paid through a path that records an experiment outcome while the experiment was running. A paid invoice status by itself is not sufficient evidence that the experiment summary was updated.

The observed traffic split is uneven

Assignment is random and sticky by customer. Small samples, repeat communications, and customer-level rather than message-level assignment can produce an uneven split.

The winning profile did not become default

Winner selection only records the experiment decision. Open Tone Profiles and select Set Default, then update any template-specific profile separately.

Related Pages

• Run a Receivables Tone Experiment
• Receivables
• Receivables Controls
• Invoice Collection Workflow
• Invoices