For equity analysts and PMs who lose three nights a print week to the copy paste between the filing and the model: 12 Claude prompts that roll the quarter, reset the run rate, reconcile guidance against your estimates, and redraft the note before the open, on your own model in your own Claude.
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/earnings-update-kit#the-vault . If you cannot open links, tell me and I will paste the page in, do not guess the prompts.
I want to INSTALL the real setup so Claude runs a post-earnings model update on my actual model and the actual print, not just a chat demo. Walk me through it step by step, do not skip the install. Treat me like a covering analyst, a PM, or a finance lead who has never built a Claude Project or installed an Office add-in, and define every term once.
One honest thing up front: this Kit is about 60% of the build. It reads the print and the transcript you load, rolls your model, and cites every number. The last 40%, wiring live data into the model, enforcing who on the desk sees what, keeping an audit trail your compliance team accepts, and running it across a full multi-name coverage list at production scale, is the proper integration, and that is the part consultance wires into production. You can run the whole update by hand tonight with what is below; the wiring is a call, not a prompt.
This is NOT a Terminal or coding install. There is nothing to compile. It is two paths: a private Claude Project for the print and the model (recommended) and an optional Excel add-in so the roll happens in your real workbook.
## Path 1 (RECOMMENDED) — a private Claude Project for the earnings update
This is where the press release, the 8-K or 10-Q, the earnings deck, the transcript, and your model 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. Pin **Claude Fable 5**. Nothing to install for this path. (Fable 5 is the model name, the current frontier for this work; pin it in the model picker.)
2. **Create the update workspace.** In Claude, create a new **Project** named for the name and the quarter (for example "ACME Q3"). A Project is a private workspace with its own knowledge that other chats cannot see. Your model, your estimates, and your notes stay in your own tenant.
3. **Load the print.** The night the print lands, drop the press release, the 8-K or 10-Q, the earnings deck, and the call transcript into the Project knowledge, along with your prior model if you have it. Public prints, releases, and transcripts only, nothing you are not allowed to hold.
4. **Run the vault.** Run prompt 01, pick the kind of print, the name and quarter, your prior estimates, and your data source (A) upload (or (D) connector if you pull from FactSet, Capital IQ, or Bloomberg under your own access). Then run 02 to 12 in order: read the print, roll the quarter, reset the run rate, reconcile guidance, flag the movers, the reconciliation gate, the CFO call read, the note, the estimate log, the scenarios, and the review-meeting hardening.
5. **Gate it.** Run prompt 07 before the note ships. A reconciliation MISMATCH (a segment table that does not sum, a headline that does not tie, a guidance number quoted wrong) is a number to fix, not a footnote.
6. A named human analyst signs the note. This is a working tool, not investment advice.
## Path 2 (OPTIONAL) — Claude for Excel add-in so the roll happens in your workbook
If I want the quarter to roll into my real model and the full-year to re-tie in live formulas:
1. In Excel (Microsoft 365 desktop or web): **Home** or **Insert** tab, **Add-ins** or **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 03 (roll the quarter) and prompt 04 (reset the run rate) say "do this in my workbook as real formulas," so the full-year re-ties live and the prompt 07 tie-out runs on live cells.
4. Pin **Claude Fable 5** for the read, the reconciliation, the call, and the note.
## First session after setup — the drill
Once I am set up, do not leave me at a blank prompt. Walk me through the highest-value run:
- **The input:** the press release and the transcript for the name I just got the print on, loaded into the Project, plus my prior estimates for the quarter.
- **First prompt to run:** prompt 01 (the router), then prompt 02 (read the print), then prompt 03 (roll the quarter).
- **What good output looks like:** a print table where every reported figure cites its source and sits next to my prior estimate, a run-rate walk that shows reported to clean to forward, and guidance quoted verbatim next to my own numbers.
- **The check before I trust it:** run prompt 07 (reconciliation self-check). If the headline figures do not tie to the raw release, or a segment table does not sum, or a guidance number is quoted wrong, fix it before the note ships. Status must read RECONCILED.
## Rules for walking me through this
- One step at a time. Define every term once: Project, knowledge, 8-K, 10-Q, run rate, add-back, adjusted vs GAAP, guidance reconciliation, `<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.
- Public prints only. Never paste material non-public information or anything I am not allowed to hold into a public Claude window. Use a Project with your tenant controls.
- A named human analyst signs the note. Claude reads the print and ties the numbers; a person owns the call. Not investment advice.
- The official FactSet, Capital IQ, and Bloomberg docs are a bonus path if I want to wire a live data pull later, never required to run the vault by hand.
First message: ask me "Path 1 (Claude Project for the print and the model, recommended) and do you also want Path 2 (Excel add-in so the roll happens in your workbook)? And which name and quarter are you updating, and is it a clean beat or miss, a messy print, guidance-only, or a name you do not model yet?" 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.
For equity analysts and PMs who lose three nights a print week to the copy paste between the filing and the model: 12 Claude prompts that roll the quarter, reset the run rate, reconcile guidance against your estimates, and redraft the note before the open, on your own model in your own Claude.
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 Kit is about 60% of the build, a reconciled, sourced, defensible first draft you can run by hand tonight. We wire the last 40% into production: a live data feed that pulls the release, the filing, and the transcript the second they hit the wire and drops the numbers into the model, role based access so only the right analyst sees the right name, an audit trail your compliance team accepts under FINRA 2241 and SEC 17a-4, and the queue to run it across a full multi name coverage list at earnings season scale. Done with you, then handed over so you own it.
Book a build call →Prompt set and build authored by consultance.ai. FactSet, Capital IQ, and Bloomberg are referenced as the incumbent tooling this runs alongside, no affiliation implied. The Kit reads public prints, releases, and transcripts only; your model, estimates, and notes stay in your own Claude tenant and we never see them. This is not investment advice; a named human analyst signs every note before it reaches a PM, an IC, or a client.
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.
The person drowning in this every week is the one who'll actually want it.
Post Earnings Model Update Kit is a finance and data build in the consultance.ai AI Build Library. For equity analysts and PMs who lose three nights a print week to the copy paste between the filing and the model: 12 Claude prompts that roll the quarter, reset the run rate, reconcile guidance against your estimates, and redraft the note before the open, on your own model in your own Claude. It fits Equity research analysts, buy side PMs and associates, family office and PE public markets teams, and finance leaders who cover names through earnings season and want the post print model update done in one morning instead of three all nighters, without the work ever leaving their tenant. Setup difficulty is Medium, with 4 plain-English steps.
For equity analysts and PMs who lose three nights a print week to the copy paste between the filing and the model: 12 Claude prompts that roll the quarter, reset the run rate, reconcile guidance against your estimates, and redraft the note before the open, on your own model in your own Claude.
It fits Equity research analysts, buy side PMs and associates, family office and PE public markets teams, and finance leaders who cover names through earnings season and want the post print model update done in one morning instead of three all nighters, without the work ever leaving their tenant.
Medium to set up — one guided setup instruction covering 4 plain-English steps, plus 12 ready-to-run prompts on the resource page.
The Kit is about 60% of the build, a reconciled, sourced, defensible first draft you can run by hand tonight. We wire the last 40% into production: a live data feed that pulls the release, the filing, and the transcript the second they hit the wire and drops the numbers into the model, role based access so only the right analyst sees the right name, an audit trail your compliance team accepts under FINRA 2241 and SEC 17a-4, and the queue to run it across a full multi name coverage list at earnings season scale. Done with you, then handed over so you own it.
Prompt set and build authored by consultance.ai. FactSet, Capital IQ, and Bloomberg are referenced as the incumbent tooling this runs alongside, no affiliation implied. The Kit reads public prints, releases, and transcripts only; your model, estimates, and notes stay in your own Claude tenant and we never see them. This is not investment advice; a named human analyst signs every note before it reaches a PM, an IC, or a client.
Post Earnings Model Update Kit 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.