For PE ops, portfolio CFOs, and portco operators watching a book on different ERPs: 10 prompts that inventory exports, score each function against the plan you underwrote, flag breaks weekly, and refuse any figure that cannot trace to one entity and one source file, replacing the seven figure Palantir Foundry rollout.
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/ops-intel-screen#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 Ops Intel Screen and run it on one portfolio company first, pulling exports into one operating picture and scoring against the plan we underwrote. Walk me through it step by step, one question at a time, and wait for my answer before moving on. I am PE ops, a portfolio CFO, or a portco operator, not a developer. This is NOT a Palantir install. There is nothing to download except Claude. Define every term once. Keep me to one action per message. ## Honest ceiling, up front This vault is about 60% of the build: export inventory, normalization, plan scoring, entity trace, weekly break detection. Consultance wires the last 40%: live ERP pulls, role based access, LP grade audit trail, multi portco roll up at scale. Reply "wire it" for a 30 minute slot when you hit that wall. ## What this produces One live operating picture from raw exports: every function scored against the underwritten plan (not last quarter), breaks flagged in the week they happen, weekly ops review rebuilt from exports not slides, and every figure tied to one named entity and one source file before anything reaches a sponsor or board. ## Step one, ask me this first, nothing else "Where do your portfolio exports live for this run: will you upload ERP, CRM, HRIS, and warehouse exports into a Claude Project, paste tables into the chat, or work in Excel with the Claude add in? Any of the three works. I 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) - Have me open Claude at claude.ai, create a private Project named "Ops Intel Screen," and pin Claude Opus 5. - Have me load exports for ONE portfolio company first (not the whole book on day one). - Walk me to prompt 01, the onboarding router. I must answer scope, stage, data source, and tokens before anything else runs. - Run prompts 02 to 06 in order: inventory, normalize, build the picture, score vs underwritten plan, flag weekly breaks. - Stop me at prompt 07, the entity trace hard gate. Nothing prints until every figure ties to one entity and one source file. If it returns CONTAMINATED, we fix the folder structure before continuing. - Finish with 08 to 10: weekly ops review, board pack from exports, refresh cadence. ## The first session drill By the end I should have one portco on the screen with a clean entity trace gate, at least one break flagged against plan, and a weekly review I would actually send a sponsor. Then show me the prompt order for next week's refresh. Anti-pattern: do NOT tell me I need Palantir Foundry or a forward deployed team. This runs on exports I already have. Before you call the screen ready, confirm prompt 07 returned CLEAN, every tile cites a source file, and scores use the underwritten plan not last quarter. I sign every external output myself. Related: [[pe-portfolio-monitoring-pack]] · [[enterprise-automation-pack]]
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 PE ops, portfolio CFOs, and portco operators watching a book on different ERPs: 10 prompts that inventory exports, score each function against the plan you underwrote, flag breaks weekly, and refuse any figure that cannot trace to one entity and one source file, replacing the seven figure Palantir Foundry rollout.
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 Ops Intel Screen: the prompts loaded into your Claude tenant, live export pulls or ERP connectors so the screen refreshes on schedule, role based access so the right sponsor sees the right portco, an audit trail your LP will accept, and multi portco roll up with automated entity contamination checks. 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 Palantir Technologies, SAP, or Anthropic implied; they are referenced only as the incumbent stack and model provider. Your portfolio company exports stay in your own Claude tenant; we never see them. This moves the labor of the operating review, it does not replace independent audit, LP reporting from the fund administrator, or the human sign off; a named human signs every output before it reaches a sponsor or board. Not investment or accounting 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 founders, CFOs, and deal teams: 9 Claude prompts that rebuild the cap table from the signed documents instead of the spreadsheet, run the waterfall clause by clause against the actual LPA or charter, and recompute fee and carry independently, so a stale sheet gets caught before a round closes on it.
For CFOs and finance leaders: the map of seven finance desks, deal, diligence, close, tax, underwriting, family office, and market, each one a free prompt vault that runs inside your own Claude, plus the order to install them in so a team actually adopts them.
For CFOs and controllers: 11 Claude prompts that run the month end close reconciliation itself, match bank and subledgers both directions, catch the account that will not foot, and draft the flux memo, so a 6 day close lands in 2.
The person drowning in this every week is the one who'll actually want it.
PE Ops Intel Screen From Exports is a finance and data build in the consultance.ai AI Build Library. For PE ops, portfolio CFOs, and portco operators watching a book on different ERPs: 10 prompts that inventory exports, score each function against the plan you underwrote, flag breaks weekly, and refuse any figure that cannot trace to one entity and one source file, replacing the seven figure Palantir Foundry rollout. It fits PE operating partners, portfolio CFOs, and portco operators at private equity backed companies who need a live operating picture across exports on different ERPs without a seven figure Palantir Foundry rollout. Setup difficulty is Medium, with 5 plain-English steps.
For PE ops, portfolio CFOs, and portco operators watching a book on different ERPs: 10 prompts that inventory exports, score each function against the plan you underwrote, flag breaks weekly, and refuse any figure that cannot trace to one entity and one source file, replacing the seven figure Palantir Foundry rollout.
It fits PE operating partners, portfolio CFOs, and portco operators at private equity backed companies who need a live operating picture across exports on different ERPs without a seven figure Palantir Foundry rollout.
Medium to set up — one guided setup instruction covering 5 plain-English steps, plus 10 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 Ops Intel Screen: the prompts loaded into your Claude tenant, live export pulls or ERP connectors so the screen refreshes on schedule, role based access so the right sponsor sees the right portco, an audit trail your LP will accept, and multi portco roll up with automated entity contamination checks. 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 Palantir Technologies, SAP, or Anthropic implied; they are referenced only as the incumbent stack and model provider. Your portfolio company exports stay in your own Claude tenant; we never see them. This moves the labor of the operating review, it does not replace independent audit, LP reporting from the fund administrator, or the human sign off; a named human signs every output before it reaches a sponsor or board. Not investment or accounting advice.
PE Ops Intel Screen From Exports 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.