Closing the Books Without the Spreadsheet Shuffle: My Fall Internship at Ramp

Summary

During a fall internship at Ramp, the author worked on reducing repetitive accounting work around month-end close, focusing on amortization and ERP mapping workflows. One project uses receipt data, merchant category codes, customer history, and embedding similarity to detect likely prepaid expenses and suggest service periods and accounts or templates, with recommendations reviewable before application. A second built Ramp-Native Amortization to create schedules, generate periodic debit and credit journal entries, handle catch-ups and reclassifications, and sync entries to ERPs through a dashboard; transaction and reimbursement support was nearing alpha production release, while bill pay was next. The third generates high-confidence mapping-rule suggestions from customer coding patterns on a nightly schedule. Across the work, backtesting, accuracy metrics, and human workflow research support automation intended to earn trust rather than remove accountant judgment.

Context

Accounting teams encounter repetitive manual work during month-end close, including identifying prepaid expenses, rebuilding amortization logic in spreadsheets, creating recurring journal entries, switching between Ramp and ERPs, and manually configuring mapping rules. These steps consume time and create opportunities for errors, while accounting workflows require high confidence.

Approach / What changed

The work covered three initiatives: an AI-powered system that detects likely prepaid expenses and suggests service periods and accounts or templates; Ramp-Native Amortization, which creates schedules, generates journal entries, handles catch-ups and reclassifications, and syncs with ERPs; and nightly generation of high-confidence mapping-rule suggestions from customer coding patterns. Backtesting, metrics, and accountant workflow research were used to guide safe automation.

Takeaways

• Receipt-based amortization detection combines merchant category code pre-filtering, customer history, model analysis, and embedding similarity to focus AI calls and suggest prepaid accounts or templates.
• Ramp-Native Amortization initially records an expense as a prepaid asset, then generates periodic entries that debit the expense account and credit the prepaid account, with catch-up and reclassification flows for changes.
• Suggested mapping rules are generated nightly from customer coding patterns, with high-confidence automation intended to produce codings that do not require manual overrides.

Related reading