How the Classifier Agent assigns categories + tax tags, how your corrections train it, and how to reach 95%+ accuracy in 3 weeks.
Every transaction flowing into HaraPro — whether via Plaid or PDF statement — gets passed to the Classifier Agent. The agent looks at:
It then assigns one category (e.g., "Meals & Entertainment") and up to 3 tax tags (e.g., "Deductible", "Business Meal 50%", "Travel-related"). Each assignment gets a confidence score 0–100.
Categories are the "what is this?" layer. We use 49 that map cleanly to IRS Schedule C, Schedule E, and common S-Corp and partnership accounts:
You can rename categories per entity (e.g., "Software & SaaS" → "Software — Dev Tools") and create custom sub-categories.
Tax tags are the "how does this affect taxes?" layer. They stack on top of categories and drive the tax forecast, deduction simulator, and CPA export. The 17:
The Classifier doesn't learn in isolation — it uses four layers of memory, stacked in priority order (top wins):
The immediate context of the transaction under review — adjacent transactions, current entity, recent batch uploads. This resolves ambiguity for things like "Amazon" appearing 40 times in a week (all business supplies vs mixed personal).
Every time you override a classification, that correction is stored. The next time the same merchant (or similar description) appears in the same entity, your prior correction wins. Corrections propagate within 24 hours.
Patterns specific to your HaraPro account: "This tenant tags all Shell purchases as Vehicle — Actual, not Personal" or "This tenant categorizes Uber consistently as Travel for entities A, B and Personal for entity C." Tenant preferences apply across all entities in your account.
Industry-wide patterns from all HaraPro users, fully anonymized. "Intuit" is overwhelmingly "Software & SaaS" in the SMB segment. "Delta Airlines" is overwhelmingly "Travel". This is the fallback when your own tenant has no prior signal.
Open the Transactions tab. Low-confidence classifications land in Needs review automatically. To correct:
The "Apply to all similar" option uses merchant name + description fuzzy match. Useful when you realize "Aws" has been miscategorized as "Uncategorized" for months — one click fixes all 47.
Typical accuracy trajectory for a new tenant:
To accelerate: when you do your first review, go through 200–300 transactions in one sitting. The AI learns your patterns much faster from a concentrated burst than from scattered fixes over months.