Open finance skill
Spend concentration review
Which vendors or categories create concentration risk?
Rank synthetic spend by vendor and category, then calculate concentration shares for an operator to interpret.
Inputs
- ✓Transaction list
- ✓Vendor mapping
- ✓Category mapping
Outputs
- ✓Top vendors
- ✓Top categories
- ✓Concentration shares
Checks performed
- ✓Vendor aggregation
- ✓Category aggregation
- ✓Top-five concentration
Guided synthetic example
See the check from input to decision
A growing contractor relies heavily on one fleet and equipment vendor.
This is the operating model we use at Level. The percentages are estimated shares of the work in a typical review. Actual effort varies with data quality, complexity, and the issue found.
Start with the source records
About 15% of work| Vendor | Category | Trailing 90-day spend | Share |
|---|---|---|---|
| Example Fleet | Vehicles | $72,000 | 60% |
| Example Supply | Materials | $31,200 | 26% |
| Other vendors | Mixed | $16,800 | 14% |
Run the deterministic check
About 20% of workAggregate spend by normalized vendor and category, then calculate each share of total spend.
Surface the flagged result
About 10% of workNeeds review
Example Fleet represents 60% of trailing 90-day spend.
Use recorded finance judgment to analyze possible reasons
About 25% of workAt 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
Concentration is not automatically bad. A vehicle purchase cycle may be temporary, while recurring dependence could create pricing or continuity risk.
Make the final human judgment
About 20% of workA Level finance professional validates the source evidence, challenges the AI-assisted analysis, and decides which explanation is supported.
Make the operating decision
About 10% of workSeparate recurring from one-time spend and decide whether alternative vendors or negotiated terms are needed.
Use this system
Start with the example, then inspect the structure
- 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.
MCP preview
run_synthetic_example {"slug":"spend-concentration-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.