For CFOs and controllers whose close runs six or seven days: 11 prompts that match the bank feed, book the accruals with the working shown, chase every variance to the journal line, and trace every entry to its source, so the close drops to a day and the board can audit it line by line.
Never used Claude? It is free and takes 30 seconds to open. Copy the instruction below, paste it into Claude, and it reads this page and walks you through everything, one question at a time.
A short instruction plus a link to this page lands on your clipboard. First copy asks for your email once. That unlocks every button across the whole library.
Free account, no card, 30 seconds. This tab stays open so you can come back.
Open claude.ai ↗Claude reads this page, asks which computer you are on, then guides you step by step until it works. If anything errors, tell Claude what you see, and it fixes it with you.
If you can browse the web, open and read this page in full first — it has the complete guide and every prompt you will run (the vault is under the-vault anchor): https://consultance.ai/library/fast-close-desk#the-vault . If you cannot open links, tell me and I will paste the page in — do not guess the prompts. I want to set up the Fast Close Desk and run my month end close, six days of work in one, with every entry traced back to its source. Walk me through it step by step, one question at a time, and wait for my answer before moving on. I am a CFO or controller, not a developer. This is NOT a Terminal install, there is nothing to download or run in a command line. Define every term once. Keep me to one action per message. ## Honest ceiling, up front This vault is about 60% of the build: the prompts, the trace discipline, the reconciliation gate, the flux narrative. Consultance wires the last 40% into production, the part a prompt cannot do alone: live data wiring into your GL and bank feeds, role based access control, an audit trail your auditor will accept, and multi entity scale. That last 40% is implementation work. It is a call, not a prompt. When you hit that wall, reply "wire it" for a 30 minute slot. ## What this produces Your month end close run in your own Claude on your own numbers: the bank feed matched to the ledger, the accruals and prepaids built with the working shown, every entry traced back to a source document, the variance chased to the exact journal line, a reconciliation self check that must come back clean before anything is called closed, the flux narrative drafted, and a board package anyone can audit line by line. ## Step one, ask me this first, nothing else "Where does your data live for this close: will you upload your exports (trial balance, bank feed, sub-ledgers) into a Claude Project, paste the tables straight into the chat, or work in Excel with the Claude add-in? Any of the three works. I just need to know which, because every later prompt reads from that choice." Wait for my answer. Then continue, one step per message. ## The path you walk me down (UI-driven, no Terminal) - Tell me this is a point and click setup inside Claude, no code. Have me open Claude at claude.ai, click the Projects area in the left sidebar, and create a new private Project named "Month End Close." Explain that a Project is a private workspace whose files stay in my own account and are never seen by you or by consultance. - Have me pin the model. Point me to the model picker at the top of the chat and have me select Claude Fable 5. Explain in one line why: it holds the long context a full trial balance needs and it shows its working, which is the whole trust story. - Have me load my data the way I chose in step one: upload files into the Project knowledge, or keep them ready to paste, or connect the Excel add-in to my open workbook. Remind me my numbers stay in my tenant. - Walk me to the vault. Have me paste prompt 01, the onboarding router, first, and answer its four questions (close type, close stage, data source, tokens) before anything else runs. Do not let me skip it; every later prompt depends on it. - Then run 02 to 05 with me in order: match the bank feed, build the accruals, trace every entry, chase the variance. Read the first output together so I trust it before I run the rest. - Stop me at prompt 06, the reconciliation self check. Explain it is a hard gate: it re-derives the close a second way and must return RECONCILED. If it returns NOT RECONCILED, help me find the real gap; never plug it. Do not let me call the close done until it is clean and I have signed it. - Finish with prompts 07 and 08: the flux narrative and the board package. ## The first session drill By the end of this session I should have run one real close (last month's numbers are perfect for a dry run): bank feed matched, accruals booked with working shown, every entry traced, variance explained, a clean RECONCILED result I signed, and a board package I could hand over. Then show me the prompt order and my tokens so next month's close is a checklist, not a rebuild. Anti-pattern to avoid: do NOT tell me this is "not possible" in the Claude UI. Everything here runs in a normal Claude Project with no install. If I ask for live GL wiring, role based access, or multi entity scale, that is the last 40%, the implementation work, and the honest answer is "reply wire it for a call," not "Claude cannot do that." Before you tell me the close is done, confirm prompt 06 returned RECONCILED, that debits equal credits, that the cash reconciliation foots, and that every material variance has a named root cause. Do not say it is ready until that check is clean. I review every gate and sign the close myself. Repos, docs, and any calculators are a bonus path, never required. The whole close runs from the prompts on this page.
Grab the whole pack as one file, or tap any prompt below to copy it on its own. Placeholders that look like {{THIS}} get swapped for your own numbers — and if you ran Step 1, Claude fills them in for you.
For CFOs and controllers whose close runs six or seven days: 11 prompts that match the bank feed, book the accruals with the working shown, chase every variance to the journal line, and trace every entry to its source, so the close drops to a day and the board can audit it line by line.
The setup rail and every prompt above are free and stay free. The cost is your time, and the risk of wiring it wrong on live data.
Back to the prompts ↑The vault is about 60% of the build; we wire the last 40% into production. We would deliver a deployed close desk: the prompts loaded into your Claude tenant, live data wiring into your GL and bank feeds so the close pulls itself, role based access control so the right people see the right entities and numbers, an audit trail your auditor will accept, and multi entity and intercompany logic mapped to your real hierarchy. Done with you, then handed over so you own it and the data never leaves your tenant.
Book a build call →Prompt set authored by consultance.ai. No affiliation with BlackLine, Trintech, Oracle Hyperion, or OneStream implied; they are referenced only as the incumbent being replaced. Your trial balance and workpapers stay in your own Claude tenant; we never see them. This moves the labor of the close, it does not replace independent audit or the human sign-off; a named human signs every close before it reaches the board or the auditor. Not accounting or audit advice.
Want this wired into your stack instead of running it yourself? That is our AI deal desk and finance automation service.
The AI tools, launches, and shifts that actually matter, in plain English. New library drops the moment they land.
More like this
For CFOs and PE deal teams: run six Big 4 grade deliverables yourself with 12 prompts, including the quality of earnings pass and the LP reporting pack, plus the partner questions the model skips.
For PE deal teams, CFOs, and IC members: 11 Claude prompts that run a second read on a seller's quality of earnings, test every add-back against the source, catch the recurring cost dressed up as one time, and rebuild EBITDA the way the buyer should see it before it clears into the price.
For deal teams and corp dev building the buy-side merger model: 12 prompts that run accretion or dilution, the funding mix, goodwill, synergies, and the breakeven price where the deal stops adding to EPS, in an afternoon instead of a two-week associate build.
manual now, installed when you're ready
The free version above. It runs this read on a file you paste in, in your own Claude. Yours to keep.
The same read, wired into your cfo and back office stack, running the second a report lands. Nothing to upload, no new login.
See the installed versionThe person drowning in this every week is the one who'll actually want it.
Cut Your Month End Close to One Day is a finance and data build in the consultance.ai AI Build Library. For CFOs and controllers whose close runs six or seven days: 11 prompts that match the bank feed, book the accruals with the working shown, chase every variance to the journal line, and trace every entry to its source, so the close drops to a day and the board can audit it line by line. It fits CFOs, controllers, and finance leaders at companies and PE portfolio businesses whose month end close eats six or seven days of reconciling, accruals, variance chasing, and board narrative every single period. Setup difficulty is Medium, with 5 plain-English steps.
For CFOs and controllers whose close runs six or seven days: 11 prompts that match the bank feed, book the accruals with the working shown, chase every variance to the journal line, and trace every entry to its source, so the close drops to a day and the board can audit it line by line.
It fits CFOs, controllers, and finance leaders at companies and PE portfolio businesses whose month end close eats six or seven days of reconciling, accruals, variance chasing, and board narrative every single period.
Medium to set up — one guided setup instruction covering 5 plain-English steps, plus 11 ready-to-run prompts on the resource page.
The vault is about 60% of the build; we wire the last 40% into production. We would deliver a deployed close desk: the prompts loaded into your Claude tenant, live data wiring into your GL and bank feeds so the close pulls itself, role based access control so the right people see the right entities and numbers, an audit trail your auditor will accept, and multi entity and intercompany logic mapped to your real hierarchy. Done with you, then handed over so you own it and the data never leaves your tenant.
Prompt set authored by consultance.ai. No affiliation with BlackLine, Trintech, Oracle Hyperion, or OneStream implied; they are referenced only as the incumbent being replaced. Your trial balance and workpapers stay in your own Claude tenant; we never see them. This moves the labor of the close, it does not replace independent audit or the human sign-off; a named human signs every close before it reaches the board or the auditor. Not accounting or audit advice.
Cut Your Month End Close to One Day is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.
This build comes from our AI consulting and AI implementation practice — see the full AI in finance guide and how we work with CFO teams.