Skip to main content
2,200+ service businesses benchmarked. Do you know your gross profit per labor hour? See where you stand →
Level
← All finance systems

Open finance skill

Categorization history health

Is transaction history consistent enough to support reliable automation?

Measure vendor-level categorization consistency, overrides, ambiguity, and time drift before proposing automation rules.

Inputs

  • Categorized transactions
  • Vendor normalization
  • Override history

Outputs

  • Stable candidates
  • Conflicting history
  • Manual-policy queue

Checks performed

  • History coverage
  • Category consistency
  • Time drift

Guided synthetic example

See the check from input to decision

A vendor appears frequently, but its historical categories are inconsistent.

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.

1

Start with the source records

About 15% of work
VendorTransactionsMost common categoryConsistency
Example Hardware62Materials61%
Sample Telecom38Telephone97%
2

Run the deterministic check

About 20% of work

Measure normalized-vendor history, category concentration, overrides, and time drift before proposing automation.

3

Surface the flagged result

About 10% of work

Needs review

Example Hardware is only 61% consistent and should not receive a broad automatic category rule.

4

Use recorded finance judgment to analyze possible reasons

About 25% of work

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 may legitimately span materials, tools, repairs, and office purchases, or the historical books may contain miscoding.

5

Make the final human judgment

About 20% of work

A Level finance professional validates the source evidence, challenges the AI-assisted analysis, and decides which explanation is supported.

Which categories are legitimate?
Did behavior change over time?
What secondary field reliably separates purchases?
6

Make the operating decision

About 10% of work

Keep the vendor manual or add a narrow secondary condition after finance policy review.

Use this system

Start with the example, then inspect the structure

  1. Download the invented input and expected output.
  2. Replace one field at a time with a safe test value.
  3. Compare the result with the expected structure.
  4. Have a finance professional review every exception before acting.

MCP preview

run_synthetic_example {"slug":"categorization-history-health"}

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.