The prompt
Help me match statement rows to ledger rows and leave one clean exception list for one manual batch.
Use only the approved inputs I paste below. Return a review table with these columns:
Date | Description | Amount | Reference | Match ID | Match reason | Confidence | Status
Rules:
- Link each judgment to the exact supplied source or write unknown.
- Remove obvious duplicates inside this batch and preserve any human edits I include.
- Use the wording template or criteria I provide; do not invent claims, people, amounts, dates, evidence or decisions.
- Show blockers separately instead of guessing.
- Prepare the work only. Do not send, publish, schedule, book, spend, approve, reject, delete or change a live record.
Approved inputs, rules and sources:
[paste here]What this free prompt does
It handles one manual batch from the context you paste and returns review-ready work. It does not save a workspace, remember prior runs, watch a clock or manage follow-ups.
When the job repeats
The paid Reconciliation Agent adds the full recurring system: one-choice setup, exact Google Sheet structure, the pack's fixed run clock, history-aware dedupe, new-or-due-only processing, replay protection, approval queues and verified writeback. It is $19 one-time.
What to bring
Reconciliation is a row-by-row match between the statement and the ledger, and the exceptions are always found at 6pm on close day.
What a good run returns
A sheet with statement row, ledger row, match status, difference and next action, in a Bookkeepers Reconciliation Workspace folder.
Where the free version ends
This free prompt handles one manual batch from pasted context. The Reconciliation Agent ($19 one-time) installs this as a standing workflow: fixed evidence rules, a saved output in your own Drive every run, fictional-data testing before real work, and hard stops before anything sends, spends or publishes. More detail on the AI bank reconciliation guide.
Questions people ask
Is this prompt really free?
Yes. Copy it, paste it into any capable assistant, bring the inputs listed. No signup, no email gate.
Which assistants does the prompt work in?
Any capable chat assistant: Instinct, ChatGPT, Claude, Gemini, Grok, DeepSeek, Perplexity, Microsoft Copilot, Hermes, OpenClaw, Town, Muse and others.
What is the difference between the free prompt and the $19 agent?
The prompt is a one-off: you re-paste the rules every run. The $19 agent is the same job productized - tested setup, saved files, consistent output, standing cycle.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.