Variance Analysis Narrative Engine
Turn monthly variance tables into driver-attributed, board-ready commentary — price/volume/mix decomposition, evidence-tested one-time vs structural labels, and a forecast-linked review section, every close.
A 4-step agentic workflow pack for finance built to run with ChatGPT, Claude, and Gemini. Open the Markdown files, fill the variables, and paste into your model. Most buyers get a reviewable result in about 15 minutes.
- Decompose every material variance into volume, price, mix, FX, and timing effects with stated assumptions — never a fabricated split
- Stop 'one-time' abuse with hard evidence standards: bounded event + no recurrence in 4 periods, or it gets reclassified structural
- Write driver-led commentary that explains causes and actions instead of restating the numbers the reader can already see
- Annualize structural drivers into an honest full-year run-rate impact with a mechanical raise/hold/lower forecast call
- Assemble the complete monthly review section — headline bridge, top drivers, watch items with triggers, appendix discipline
- Reuse the same four-step flow every close so commentary quality stops depending on who wrote it that month
Prompt Customization Service — optional help adapting variables and output to your brand voice. Choose your tier at checkout (not tied to this prompt's price).
This pack is $9 on its own. Buying every pack separately costs $935. The Lifetime Bundle is $149 one-time — you save $786 (84% off) and unlock every future pack free.
Get the Lifetime Bundle — $149Paste the license key from your receipt. It must match this prompt pack.
What ships with your purchase
Prompt files
Plain Markdown files with `{{variables}}` you fill in, ready to paste into ChatGPT, Claude, or Gemini. No setup, no tooling required.
Usage guide
Variable reference, model compatibility, examples, and customization tips so you can adapt the pack to your brand voice.
Lifetime updates
When we improve the pack, you get the new version automatically. Email support included with every purchase.
Models tested: ChatGPT, Claude, Gemini.
The workflow inside this pack
4 composable prompts you run in order — each one picks up where the last left off.
- Step 1
Variance Decomposer
Paste your variance table plus period context and get every material line decomposed into volume, price, mix, FX, and timing effects — each with a stated assumption.
- Step 2 · optional
One-Time vs Structural Classifier
Feed in the decomposed drivers with your evidence notes and each one gets a label held to a hard standard — a named bounded event for one-time, two prior years for seasonal, a persistence mechanism for structural.
- Step 3 · optional
Narrative Composer
Paste the classified drivers and your audience, and get a headline paragraph plus per-driver commentary in the X-drove-$Y-because-Z shape — no number walls, no 'due to timing' without a reversal period.
- Step 4 · optional
Review Pack Assembler
Combine the narrative and classification outputs into one disciplined section: plan-to-actual bridge, six-row driver table, and watch items that each carry a trigger threshold and check date.
Perpetual (lifetime) use license
Your one-time purchase includes an ongoing right to use this prompt pack with the AI tools and models you control for your own and your clients' work — not for resale or public redistribution of the files as a product.
We keep the copyright
The prompt files, guides, examples, and bundled assets stay our copyrighted works (or our licensors'). Payment grants the limited license in our Terms only — it does not transfer ownership.
Need help adapting this prompt to your team? Add Prompt Customization Service at checkout.