For commercial P&C underwriters: 16 prompts that read a submission, pull the loss runs, build the technical price, and draft the quote, moving a risk to a quote in days instead of weeks.
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.
I want to INSTALL the real setup so Claude runs first-pass underwriting on my actual submissions, not just a chat demo. Walk me through it step by step, do not skip the install. Treat me like an underwriter or MGA program manager who has never built a Claude Project or installed an Office add-in, and define every term once.
This is NOT a Terminal or coding install. There is nothing to compile. It is two paths: a private Claude Project for the submission files (recommended) and an optional Excel add-in for the SOV analysis and the pricing math.
## Path 1 (RECOMMENDED) — a private Claude Project for the underwriting file
This is where the submission, ACORD applications, SOV, loss runs, and broker narrative live so every prompt reads from one governed place.
Walk me through ONE step at a time, waiting for me to confirm each:
1. **What I need.** A Claude account on a Team or Enterprise plan so the data stays in my tenant. Pin **Opus 4.8**. Nothing to install for this path.
2. **Create the underwriting workspace.** In Claude, create a new **Project** named for the submission or the program. A Project is a private workspace with its own knowledge that other chats cannot see. Your submissions, loss runs, and SOVs stay in your own tenant.
3. **Load the submission.** Drop the ACORD application, the SOV, the 5 year loss runs, the financials, the supplementals, and the broker narrative into the Project knowledge. For a program, load the binding authority and the rate guide too.
4. **Run the vault.** Run prompt 01, pick your line of business (property, casualty, professional, marine, treaty, MGA program) and data source (A) upload (or (D) connector if you pull from your policy admin system, Verisk / ISO, or a cat model under governed access). Run 02 to 12 in order: intake, loss runs, exposure, cat screen, pricing, terms, referral check, the pricing self-check, the quote and binder, the file memo, and the renewal view.
5. **Gate it.** Treat prompt 08 (the referral and authority check) and prompt 09 (the pricing self-check) as hard gates. A referred risk does not bind on your authority alone, and a price that fails the self-check does not go into a quote. A licensed underwriter signs every bind, and your actuary owns the rate. A prompt cannot do either.
6. **Shadow-run first.** Run the workflow on already-bound or declined submissions and compare its calls to the desk before you put it near live business. See the 90 day rollout in the bundle.
## Path 2 (OPTIONAL) — Claude for Excel add-in for the SOV and the pricing
If I want the SOV analysis and the technical price to live in real formulas:
1. In Excel (Microsoft 365 desktop or web): **Home** or **Insert** tab, **Add-ins** / **Get Add-ins**, search **"Claude"**, **Add**. Tell me where the button is in my version.
2. Sign in to the docked Claude side panel.
3. In vault prompt 01 choose data source (C) Excel add-in. For prompt 04 (SOV) and prompt 06 (pricing) say "build this into my workbook as real formulas," so the SOV totals and the price build-up recompute and the prompt 09 self-check runs on live cells.
4. Pin **Opus 4.8** for the pricing, the cat screen, and the self-check.
## Rules for walking me through this
- One step at a time. Define every term once: Project, knowledge, submission, ACORD, SOV, COPE, loss run, burning cost, attritional vs large loss, technical price, rate adequacy, PML, AAL, referral, binding authority, treaty, `<review_gate>`, `{{TOKEN}}`.
- Do NOT tell me a step is "not possible." If the Excel add-in is missing, check Excel for Microsoft 365, try Excel on the web, or AppSource. For the Project path there is nothing to install.
- Never paste live insured PII or a broker's confidential submission into a public Claude window outside a Project. Use a Project with your tenant controls; respect your data providers' terms.
- Never use a protected class or an obvious proxy for one as a rating or acceptance factor. The NAIC AI bulletin and state law require discrimination testing and human oversight.
- This does the first pass. It does not replace the licensed underwriter who signs the bind, the credentialed actuary who certifies the rate, or your filed rates. Read the audit and compliance overlay before any output touches a live risk. Not legal, actuarial, or underwriting advice.
First message: ask me "Path 1 (Claude Project for the submission, recommended) and do you also want Path 2 (Excel add-in for the SOV and pricing)? And what line of business is this: property, casualty, professional, marine, treaty, or an MGA program?" Then start step 1.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.
Browser-based. No signup. Drop in your numbers and see the trade in real time. Opens in a new tab so the prompts stay where you left them.
For commercial P&C underwriters: 16 prompts that read a submission, pull the loss runs, build the technical price, and draft the quote, moving a risk to a quote in days instead of weeks.
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 ↑We would deliver a deployed underwriting workspace: the prompts loaded into your Claude tenant, governed connectors to your policy admin system, Verisk, and your cat model, the pricing wired to your loss-cost methodology and filed rates, an underwriting authority and referral gate, NAIC AI governance and discrimination-testing documentation, and an audit-ready file binder. Done with you, then handed over so you own it.
Book a build call →Prompt set authored by consultance.ai. Lloyd's, Munich Re, Swiss Re, Chubb, and AIG are referenced as the underwriting standard the pack matches, no affiliation implied. Your submission and insured data stays in your own Claude tenant; we never see it. This does the first pass, it does not replace the licensed underwriter who signs the bind, the credentialed actuary who certifies the rate, or your filed rates; the NAIC AI bulletin discrimination testing and human oversight apply. Not legal, actuarial, underwriting, or investment 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.
Submission to Quote Underwriting Pack is a finance and data build in the consultance.ai AI Build Library. For commercial P&C underwriters: 16 prompts that read a submission, pull the loss runs, build the technical price, and draft the quote, moving a risk to a quote in days instead of weeks. It fits commercial P&C underwriters, carriers, MGAs and program managers, and reinsurance desks running submissions through a desk of underwriters and pricing actuaries over 6 to 10 weeks. Setup difficulty is Medium, with 4 plain-English steps.
For commercial P&C underwriters: 16 prompts that read a submission, pull the loss runs, build the technical price, and draft the quote, moving a risk to a quote in days instead of weeks.
It fits commercial P&C underwriters, carriers, MGAs and program managers, and reinsurance desks running submissions through a desk of underwriters and pricing actuaries over 6 to 10 weeks.
Medium to set up — one guided setup instruction covering 4 plain-English steps, plus 12 ready-to-run prompts on the resource page.
We would deliver a deployed underwriting workspace: the prompts loaded into your Claude tenant, governed connectors to your policy admin system, Verisk, and your cat model, the pricing wired to your loss-cost methodology and filed rates, an underwriting authority and referral gate, NAIC AI governance and discrimination-testing documentation, and an audit-ready file binder. Done with you, then handed over so you own it.
Prompt set authored by consultance.ai. Lloyd's, Munich Re, Swiss Re, Chubb, and AIG are referenced as the underwriting standard the pack matches, no affiliation implied. Your submission and insured data stays in your own Claude tenant; we never see it. This does the first pass, it does not replace the licensed underwriter who signs the bind, the credentialed actuary who certifies the rate, or your filed rates; the NAIC AI bulletin discrimination testing and human oversight apply. Not legal, actuarial, underwriting, or investment advice.
Submission to Quote Underwriting Pack 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.