Open finance skill
Duplicate supplier invoice check
Which supplier invoices may have been entered twice?
Flag repeated supplier invoice numbers and similar supplier, date and amount combinations. Review the original documents before deciding whether either entry is wrong.
Records you need
- ✓Supplier invoices
- ✓Supplier names
- ✓Dates and amounts
What you get
- ✓Exact duplicate candidates
- ✓Possible duplicates
- ✓Reasons to review
Checks performed
- ✓Repeated invoice number
- ✓Same supplier, date and amount
- ✓Similar invoices entered near the same date
From finding to decision
Repeated amounts are a question, not a deletion instruction.
Distinguish a duplicate import from a legitimate repeated purchase or split invoice. The same amount can relate to different dates, suppliers or work.
- Compare supplier, original invoice number, issue date and the goods or services purchased.
- Inspect the original files and accounting-entry IDs, including credits or reversals.
- Keep exact duplicate candidates, legitimate repeats and uncertain similarities in separate groups.
Evidence ready for review
The original and suspected duplicate have distinct retained identities and supporting documents.
Who makes the next decision?
The person responsible for supplier bills decides which entry needs correction after confirming what is owed.
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
Two invoices from the same vendor carry the same invoice number and amount.
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
| Record | Vendor | Invoice | Entered | Amount |
|---|---|---|---|---|
| AP-881 | Example Supply | EX-4402 | Jul 10 | $8,250 |
| AP-914 | Example Supply | EX-4402 | Jul 13 | $8,250 |
Apply the documented check
Flag an exact invoice-number match, then compare vendor, amount, and nearby dates.
Surface the flagged result
Needs review
Probable duplicate: same vendor, invoice number, and amount, entered three days apart.
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
One record may be a duplicate, but it could also be a correction or legitimate split posting.
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
Open both source documents and confirm which record, if either, should be voided.
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":"duplicate-billing"}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