Revenue anomaly watch

A daily agent compares charges, refunds, and subscription movement against trailing baselines and explains anything that moves beyond normal bounds — you approve the drafted next step from your inbox.

Saves you ~13.5 h / week

Start with this playbook

How it works

Trigger
On the “Daily revenue pulse” schedule.
Job
Pull yesterday's billing movement, compare to baselines, write the briefing or all-clear.
Outcome
A verified revenue briefing with the next action.

What it installs

Agents 2

  • Revenue Watch Agent

    Owns the daily revenue pulse: baseline comparison, anomaly explanation with a drafted next step, and the anomaly log.

  • Revenue anomaly watch 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

  • Revenue anomaly watch 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

  • Revenue anomaly watch

    Pull yesterday's billing movement, compare to baselines, write the briefing or all-clear, and sign off the next step.

Documents 1

  • Anomaly log

    The dated record of every daily pulse: baselines, flagged movements, explanations, and how each resolved.

Goals 1

  • Revenue surprises surfaced within a day

    Catch unusual movement in charges, refunds, and subscriptions within one daily cycle, with a usable explanation. Success looks like: Every out-of-bounds movement appears in the inbox within one day carrying a decomposed explanation and one approved-or-declined next step, quiet days cost the reader one line, and the anomaly log holds an unbroken dated history.

Skills 2

  • revenue-baselines

    Track daily billing movement against trailing same-weekday baselines, split MRR into new, expansion, contraction, and churn instead of blended averages, and judge the split against SaaS health thresholds. Adapted from deanpeters/Product-Manager-Skills/saas-revenue-growth-metrics.

  • anomaly-explanation

    Explain a flagged revenue movement with materiality thresholds that gate the investigation, driver decomposition into volume, price, and mix effects with a narrative per driver, and one reversible drafted next step. Adapted from anthropics/knowledge-work-plugins/variance-analysis.

Schedules 1

  • Daily revenue pulse

    Runs the revenue anomaly watch every morning: pull, compare, brief, sign off. ## Professional quality control Objective: complete the recurring Revenue anomaly watch 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 watch agent can read daily charges, refunds, and subscription creations and cancellations for the baseline comparison.

    Open the Stripe connector
  • Paddle

    Paddle

    Connects to Paddle so the watch agent can read daily transactions, refunds, and subscription creations and cancellations for the baseline comparison.

  • Polar

    Polar

    Connects to Polar so the watch agent can read daily orders, refunds, and subscription creations and cancellations for the baseline comparison.

  • PayPal

    PayPal

    Connects to PayPal so the watch agent can read daily transactions, refunds, and subscription creations and cancellations for the baseline comparison.

Folders 1

  • Revenue watch

Requirements

  • Billing data in your payment provider — The agent reads daily charges, refunds, and new and churned subscriptions from the billing provider you pick during setup (Stripe, Paddle, Polar, or PayPal). Until that access is authorized, it works from the daily exports you attach to the run.

Setup guide

How to Monitor Revenue Anomalies

Run a daily revenue pulse that compares billing movement to baselines, explains anomalies, and routes next steps for approval.

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