Open finance skill
Recurring subscription review
Which software and service charges are recurring, overlapping, or quietly increasing?
Detect recurring charges, renewal patterns, price increases, duplicate tools, and subscriptions whose owner or usage is unclear.
Records you need
- ✓Transaction history
- ✓Consistent supplier names
- ✓Review period
What you get
- ✓Recurring-charge list
- ✓Yearly cost if charges continue
- ✓Subscriptions to review before cancellation
Checks performed
- ✓Similar billing frequency
- ✓Price changes
- ✓Possible tool overlap
From finding to decision
A cancellation candidate may run an important integration.
Charges show what was paid, not who uses a service, which work relies on it or when the contract can end. Check those before treating a yearly spending estimate as available savings.
- Match repeated charges to the contract and actual billing frequency.
- Ask the named owner to identify users, connected workflows and renewal terms.
- Compare keeping the service, combining tools and renegotiating terms before cancellation.
Evidence ready for review
The list separates observed charges, assumptions about yearly cost and approved decisions.
Who makes the next decision?
The service owner accepts the effect on connected work before an authorized cancellation.
Collect the supporting records from your software
Level diagnostic method reviewed . Apply it to the selected records and accounting policy; the teaching example does not resolve a live account.
Guided synthetic example
See the check from input to decision
The synthetic scenario assumes these charges recur monthly. Example CRM and Sample Outreach are candidates for a possible overlapping sales workflow, subject to usage and dependency review.
How review effort might be shared
An illustrative allocation is 15% collecting records, 20% applying checks, 10% flagging results, 25% investigating reasons, 20% finance review and 10% choosing an action. These percentages were not measured across engagements. Actual effort varies with data quality, complexity and the issue found.
Start with the source records
| Vendor | Monthly charge | First seen | Owner |
|---|---|---|---|
| Example CRM | $1,250 | Jan | Sales |
| Sample Outreach | $790 | Mar | Unknown |
| Demo Scheduler | $240 | Feb | Sales |
Apply the documented check
Cluster normalized payees by cadence and similar amount, then annualize only charges supported by a recurring pattern.
Surface the flagged result
Needs review
$2,280 of monthly software spend annualizes to $27,360, with $9,480 tied to a tool whose owner is unknown.
Use recorded finance judgment to analyze possible reasons
At Level, we record the review logic, known explanations, and questions our finance professionals use in this situation. AI applies that documented human judgment to organize the most plausible reasons, without pretending it knows which reason is true.
Possible reasons to investigate
An unknown owner can indicate waste, but the tool may support a critical integration or contracted workflow that transaction data cannot reveal.
Make the final human judgment
In a Level engagement, a Level finance professional validates the source evidence, challenges the AI-assisted analysis, and decides which explanation is supported.
Make the operating decision
Confirm ownership, usage, renewal date, and dependency before deciding to keep, consolidate, renegotiate, or cancel.
Each skill uses an independent synthetic scenario. Shared month labels do not mean the examples describe one company or a single financial period.
Use this system
Start with the example, then inspect the structure
The JSON download is a sample record file to inspect with an AI assistant or developer. It is not a file to upload into your accounting software.
- Download the invented input and expected output.
- Replace one field at a time with a safe test value.
- Compare the result with the expected structure.
- Have a finance professional review every exception before acting.
Website example JSON and registry: CC BY 4.0 (attribution required). Downloadable toolkit ZIP: MIT. Each version identifies its own frozen examples.
Developer preview: AI-assistant helper (MCP)
This tool call returns fixed, invented sample records only. It does not connect to your books. Read the setup instructions.
run_synthetic_example {"slug":"recurring-subscription-review"}Human review is part of the system
This check organizes evidence and surfaces exceptions. A person with finance domain expertise still needs to interpret the result, validate the source records, and discuss the operating decision.
Open source does not mean open client data. We publish reusable finance tools, checks, templates, and playbooks. Client records, workpapers, credentials, communications, and private configurations remain confidential.
Use it yourself, or bring us the messy part
Get a one-page plan for checking your records
Tell us where the records stop making sense. We will reply with the first check to run, the records it needs, and the decision that still needs human finance judgment.
Install the free skills yourself