Rowshni
Loading...
?
A

Anonymous mode

Use all reconciliation features without signing in. Data persists in this browser.

Workflow Progress

Follow the sequence below to move from raw files to final reconciliation output.

1

Upload Files

Upload GL, subledger, and transaction data

In Progress
2

Map Columns

Map your CSV columns to canonical fields

Pending
3

Preview Data

Review transformed data before running

Pending
4

Illuminate

AI agents validate, analyse, and generate your reconciliation report

Pending

Next Action

Upload required files

Start with GL and subledger balances so mapping can begin.

Go to Upload

1. Upload

Pending

2. Map

Pending

3. Preview

Pending

4. Reconcile

Pending

Step 1

Upload Files

Upload your GL balance, subledger balance, and transaction files. Supports CSV, TSV, TXT, and Excel (.xlsx) from any accounting system.

GL Trial Balance*

CSV/TSV/TXT - Period auto-detected from filename

Subledger Balance (AP/AR Aging)*

CSV/TSV/TXT - Period auto-detected from filename

Transaction Detail

Optional: Transaction-level detail for variance investigation (CSV/TSV/TXT)

Supporting Files

Optional: Upload supporting CSV/TSV/TXT files (multiple files allowed).

Step 2

Map Columns

Map source columns to canonical fields. You can auto-suggest and then adjust only the mismatches.

No file uploaded for gl balance

Upload a file in the Upload Workspace above

Complete required mappings to continue

Mappings are saved locally in your browser

Data Preview

Upload and map your files to see a preview

Step 4

Illuminate

AI agents validate, analyse variances, investigate, and generate your reconciliation report.

4 agents

How threshold works

Variances above this amount are flagged as material and need follow-up. Lower values increase sensitivity.

Nothing to reconcile yet

Complete steps 1–3 first: upload GL and subledger files, map the columns, and apply the mappings.

Sample data

Download test scenario files

Realistic reconciliation scenarios for balanced cases, variances, cutoff timing differences, and multi-period analysis.

About Rowshni

Rowshni means "light". It streamlines GL-to-subledger reconciliation with guided steps and AI assistance.

Platform Snapshot

  • 4-stage Illuminate pipeline: Validation, Analysis, Investigation, and Report
  • Frontend: Next.js web app | Backend: Fastify orchestrator
  • Gemini, OpenAI, and Claude supported
Technical Reference
AI Agents: 4Version: 0.1.0Fields: 11
  • Next.js 16 web application
  • Fastify orchestrator service (OpenAI, Claude, Gemini modes)
  • Spec-Kit contracts for data validation
  • Gemini 2.0 Flash (default free-tier Illuminate pipeline)
  • Optional Claude skills for mapping and investigation

For full technical details, turn off Simple mode or open the User Guide.