Open finance skill
Does the supporting cost detail add up to the reported total?
Add invented cost-detail rows and compare their sum with the reported total. This arithmetic check is called footing. Show the difference without changing either source.
From finding to decision
Footing means adding the detail and checking it against the reported total. It checks arithmetic, not whether the right accounts, dates, units and transactions were included.
The sum can be reproduced, the selected records match those behind the reported total, and each unexplained item has a retained ID.
Finance decides whether remaining differences come from timing, expense categories or missing records.
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
The cost-detail schedule does not equal the total reported in the monthly package.
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.
| Cost line | Detail amount |
|---|---|
| Direct labor | $3,000 |
| Materials | $2,000 |
| Detail total | $5,000 |
| Reported control total | $5,100 |
Sum the Direct labor and Materials detail rows, excluding the Detail total and Reported control total rows. Compare that detail sum with the control total using a $1 screening tolerance. A difference within $1 passes only when it is explained by documented presentation rounding; every other difference needs review.
Needs review
The supporting detail is $100 below the reported control total.
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 variance could be a missing row, a stale report, a classification difference, or a formula-range error.
In a Level engagement, a Level finance professional validates the source evidence, challenges the AI-assisted analysis, and decides which explanation is supported.
Trace the $100 variance before relying on the schedule for reporting or analysis.
Each skill uses an independent synthetic scenario. Shared month labels do not mean the examples describe one company or a single financial period.
Accounting review examples
These are additional review scenarios to discuss with your accountant or automation team. They describe what to check and when a person needs to investigate. They are illustrative, not software tests you can run here or proof of how a particular vendor works.
Test: Compare the individual records for the same date, as well as the total.
Expected: A matching total is not enough if records are missing or different.
Pause and investigate when: The comparison date or record IDs are missing.
Test: Save the source system, report date, filters, row count, total, column names and a file checksum (a digital check for file changes).
Expected: The team can tell whether the file changed or was incomplete before using it.
Pause and investigate when: The source, report settings or file checksum cannot be verified.
Test: Confirm the right report, expected columns, completed download and included records before processing the file.
Expected: A changed screen or export format needs review before automation continues.
Pause and investigate when: A required column is missing or a status value is unexpected.
Use this system
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.
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":"cost-detail-footing"}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
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