Open finance skill
Check automatic expense categories
Do the rules that assign purchases to accounts still fit the records?
Compare automatic expense-category rules with historical purchases. Find rules that are outdated, conflict with evidence or cover purchases that need different treatment.
Records you need
- ✓Expense-category rules
- ✓Past categorized purchases
- ✓Manual changes to suggested categories
What you get
- ✓Supported rules
- ✓Conflicts to review
- ✓Proposed narrower rules
Checks performed
- ✓Consistency with past purchases
- ✓How often categories are changed
- ✓Which purchases each rule covers
From finding to decision
Consistent classification can consistently be wrong.
A broad supplier rule can hide purchases that belong in different expense categories. Review the original documents and past exceptions before narrowing the rule. Preserve useful automation.
- Compare the rule with original purchase records and past manual changes.
- Find a reliable extra condition, such as a supported transaction memo or cardholder detail.
- Test the proposed condition against past exceptions. Inspect both purchases it accepts and purchases it leaves for review.
Evidence ready for review
The proposal states which purchases it covers and leaves ambiguous purchases for review.
Who makes the next decision?
An authorized accounting owner approves a specific rule change after reviewing its consequences.
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
One broad vendor rule categorized transactions consistently last year but conflicts with recent purchases.
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 | Rule account | Transactions | Overrides |
|---|---|---|---|
| Example Marketplace | Office supplies | 84 | 19 |
| Sample Fuel | Vehicle fuel | 46 | 1 |
Apply the documented check
Measure rule coverage and override frequency, then inspect whether conflicts reflect vendor ambiguity or a stale rule.
Surface the flagged result
Needs review
Example Marketplace has a 23% override rate, too high for an unconditional office-supplies rule.
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
The vendor sells multiple categories, so a narrower memo, amount, cardholder, or class condition may work better than deleting automation.
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
Stage a narrower rule proposal and have a finance professional test it against historical exceptions before approval.
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":"vendor-rule-audit"}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