Open finance skill
Monthly CFO review
What changed this month, and which questions should an operator ask?
Turn invented monthly summaries into a review of changed numbers, unanswered questions and next actions for a finance professional and owner.
Records you need
- ✓Current month summary
- ✓Earlier period summary
- ✓Size of change to review
What you get
- ✓Key changes
- ✓Items needing review
- ✓Discussion questions
Checks performed
- ✓Comparable periods
- ✓Important changes
- ✓Missing-data warning
From finding to decision
Which movement requires someone to do something?
A monthly summary is useful when it connects a changed number to its cause, responsible person and next decision. Percentage changes alone do not explain what to do.
- Compare equivalent periods and keep actual results separate from forecasts.
- Trace each important change to the operating records behind it.
- Write one action, responsible owner and review date for each supported finding.
Evidence ready for review
The owner can distinguish established facts, hypotheses and decisions on the same page.
Who makes the next decision?
Agree the few actions that matter before the next review instead of expanding the dashboard.
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 owner sees higher revenue and assumes the month improved, while cash and margin moved the other way.
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
| Metric | June | July | Movement |
|---|---|---|---|
| Revenue | $100,000 | $110,000 | +$10,000 |
| Gross margin | 45% | 40% | -5 pts |
| Cash | $80,000 | $70,000 | -$10,000 |
| AR over 60 days | $18,000 | $29,000 | +$11,000 |
Apply the documented check
Compare current, prior, and threshold values, then organize material changes into a discussion sequence.
Surface the flagged result
Needs review
Revenue increased, but margin, cash, and aging all deteriorated.
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 pattern suggests growth may be consuming cash, but only job, billing, collection, and cost context can explain why.
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
Assign owners to the margin and collections investigations, then track the actions at the next monthly review.
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":"monthly-value-summary"}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