Hire an AI monthly store profit reviewer
Build a consistent monthly profit view. Compare costs and margins, investigate large changes and rank proposed fixes.
What you give
- The month's costs and invoices, or a ledger export
- Orders, discounts, refunds, shipping collected and ad spend for the month
- Last month's P&L, from the second month on (it saves it for you after the first run)
What you get
- A P&L in dollars, percent of revenue and per order, in the same layout as last month
- The lines that moved past the limit, each with its reason, and whether it is a one-off
- A fix-first list with the money each fix is worth
An example
You want to know your real profit each month, not only your sales.
You ask: “Build a consistent monthly profit view. Use the material I attach and ask for anything essential that is missing.”
You get back:
- The month. Net revenue, gross margin and net profit, each against last month, with the sums.
- What moved, and why. The lines that moved past the limit, each with a reason and a note on whether it is a one-off or a trend.
- Path taken. Which checks ran, such as a sales drop split or a margin re-check, and why.
An example, not your task.
Hire this specialist
It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.
Related specialists
- Store profit and margin analyst
- Cash pool interest and fee checker
- Production yield and capacity reviewer
- Project cash and debt coverage reviewer
Skills and workflows for this job: Plan budgets, costs and cash flow
Details
Everything it can hand back
Your task sets the actual outputs. The specialist picks the methods that cover them.
- A P&L in dollars, percent of revenue and per order, in the same layout as last month
- The lines that moved past the limit, each with its reason, and whether it is a one-off
- A fix-first list with the money each fix is worth
- A new versus returning customer split, and a cash lever ranking if profit is under target
How it does the job well
- Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
- Show the calculation, inputs and period for every figure.
- Label actuals, estimates and forecasts clearly.
- Send tax, legal and regulatory questions to a qualified professional.
Mistakes it avoids
- Changing the layout or the COGS rule mid-year without saying so.
- Calling a month good or bad from revenue alone.
- Blaming a drop on ads when the cost line that moved is shipping or stock.
- Giving tax or filing advice.
- Mixing cash and accrual figures, or different periods, in one comparison.
- Rounding or formula errors that do not tie back to totals.
What a good result looks like
An example, not your task: You want to know your real profit each month, not only your sales.
- The month. Net revenue, gross margin and net profit, each against last month, with the sums.
- What moved, and why. The lines that moved past the limit, each with a reason and a note on whether it is a one-off or a trend.
- Path taken. Which checks ran, such as a sales drop split or a margin re-check, and why.
- Fix first. Up to 7 changes to approve, each with its money size, the step behind it and the reason.
- Watch next month. One to three numbers that decide what the next close looks into.
- Files and missing. The P&L file, each step's file, and every item that was missing.
How the work is checked
- The P&L uses the same layout and COGS rule as last month, or it says it is the first month.
- Every change is shown in dollars and points, with the sums.
- A margin drop is traced to a named cost line, or the answer says it could not be.
- No fix is proposed for a one-off as if it were a trend.
- States which checks passed, failed or could not run, and names missing inputs.
These checks have not been run against a model yet. Your AI uses them to check its own work.
Capabilities
- Set the rules once. In the first month it works out true unit costs, picks the cost of goods rule and saves the P&L layout.
- Refresh only what changed. It updates unit costs only when new supplier, freight or duty invoices came in, and sorts only the cost lines the rule doesn't cover.
- Build and compare. It builds the P&L in the saved layout, sets it against last month and writes the reason for each line that moved.
- Choose what to look into. If net revenue fell by over a tenth, it splits the drop into traffic, conversion and order value. If margin fell two points or more, it re-checks your main products.
- Check who pays for growth. It splits the P&L into new and returning customers when there are enough orders, and ranks cash levers if profit is under target.
- Hand back one list. It saves the month's line in its history, ranks the fixes by money and stops for your yes.
How the role works
- Checks your task, context and available tools.
- Picks the methods needed and prepares a work plan.
- Carries out supported tasks, with each method's limits and review gates.
- Checks the real deliverables and corrects supported faults.
- Hands back files, evidence and unresolved gaps.
Your specialist's working setup
Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.
Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.
Use this specialist through MCP or the API
Call prepare_specialist with role_id monthly-profit-close only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.
For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.
Complete ZIP: Download base specialist. API: GET /api/v1/specialists/monthly-profit-close/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.
Inputs and helpful context
The specialist starts from the task brief. Only active methods require their inputs.
For the primary method, when used
- The month's costs and invoices, or a ledger export
- Orders, discounts, refunds, shipping collected and ad spend for the month
- Last month's P&L, from the second month on (it saves it for you after the first run)
- Your profit target and what changed this month (optional)
Helpful context (optional)
- Supplier, freight and duty invoices for the month
- A note of every price change and sale you ran
Tools and access
- Claude Code: It can keep the close folder, read last month's files and run on a schedule.
- Your store platform and ad accounts: Export orders, refunds, discounts and ad spend for the same dates as your costs.
- A spreadsheet tool: Holds the order lines and invoices and lets you check the allocation sums.
- Shopify: The landed cost per unit goes in as cost per item so profit reports use it.
- Your accounting tool: Source of the cost lines. Xero, QuickBooks and similar tools export a profit and loss to paste.
- Any good chat AI: Any current chat AI can sort pasted lines and ask the setup questions.
- Your accounting tool: Source of the P&L export. Ask your bookkeeper to tag costs by bucket.
- Shopify: Gives gross sales, discounts, refunds and shipping charged.
- Shopify Analytics: Gives net sales, shipping, sessions, conversion rate and AOV for both periods.
- Google Analytics 4: Confirms sessions with bot traffic filtered out.
- Meta Ads Manager and Google Ads: Give spend, CPM, CPC, change history and campaign detail.
- Any good chat AI: Any current chat AI can do the sums if it shows its working. Check one product by hand first.
- Shopify admin: The Cost per item field on each product feeds live margin reports, so your numbers stay current.
- Any good chat AI: It can filter lines and add them up if you attach the tagged order list and show its sums.
- Google Sheets: Pivot tables split a P&L by order tag well, and you can keep a month-by-month history.
- Any good chat AI: Any chat AI can run the small model. Check the day 180 cash for the top lever by hand.
- Shopify: Its cohort and product reports give your repeat share and sell-through.
- Excel or Google Sheets: Holds the base model so you can change one lever and see the result.
Functions and deliverables
- Monthly store profit reviewer: Build a consistent monthly profit view. Compare costs and margins, investigate large changes and rank proposed fixes.
- A P&L in dollars, percent of revenue and per order, in the same layout as last month
- The lines that moved past the limit, each with its reason, and whether it is a one-off
- A fix-first list with the money each fix is worth
- A new versus returning customer split, and a cash lever ranking if profit is under target
- Store profit and margin analyst: Build unit costs and a monthly profit report from invoices and sales. Split new and returning buyers, then track daily margins.
- Landed cost per unit with every layer shown, margin per unit and a late-cost checklist
- Every cost line sorted into cost of goods or expense, with gross margin before and after and a score out of 100 (lines already in the right place)
- A monthly P&L in dollars, percent of sales and per order, with the line to fix first
- A first-time and a returning P&L, who pays for whom, and an acquisition health score out of 100
- A daily margin sheet with returns set aside each day and checked against the month
- Landed cost allocator: Work out landed cost per unit for each product in a shipment. Paste your order lines and freight and duty invoices to see true margin.
- Landed cost per unit for each product, with each layer shown
- The basis used for each lump cost, and why
- Margin per unit, and products below your floor
- A checklist of costs that often arrive late
- Product cost sorter: Sort your store's cost lines into COGS or expense, see which rule decided each, and get gross margin before and after, scored out of 100.
- A table of each line, its bucket, the rule used and a confidence mark
- The lines in the wrong place and what to do about each
- Gross margin before and after the fixes
- Questions where the rule depends on your setup, and a score out of 100
- Store profit and loss builder: Share your sales and costs. Get a four-bucket P&L with targets and the line to fix first.
- A P&L in dollars, percent of revenue and per order
- A gross-to-net revenue bridge
- The contribution margin you need for your profit target
- Which lines moved and by how many points, and the bucket to fix first
- Month-end variance commentary writer: Write month-end variance commentary for every line that moved past your limit. Give it this period, last period and budget. You get a reason for each.
- A commentary table for flagged lines
- Changes against prior and budget
- A one sentence driver for each line
- A short summary of the biggest movers
- Store sales decline investigator: Share two periods of store and ad numbers. Get the sales drop split into traffic, conversion and order value, with next checks.
- The percent change in each of the three levers
- Which lever drove the drop and by how much
- A cause chain and the next check for that lever
- A noise call, an act or wait decision, and a score out of 100 with its sum
- Product margin checker: Check your product margin before you set ad targets. Give it a price and every cost. Get gross margin, break-even ROAS and CAC, and a score.
- Product margin against true gross margin, with the gap in dollars and points
- Break-even ROAS and break-even CAC
- The three margins, labelled product, gross (CM2) and contribution (CM3)
- A go or no-go flag and a score out of 100, with the sum shown
- New and returning customer profit analyst: Share monthly profit and loss lines, tagged orders and a shared-cost rule. Compare new and returning customer profit with a planning score.
- A first-time customer P&L with its profit contribution
- A returning customer P&L with its profit contribution
- Who is subsidising whom, and the monthly trend
- A score out of 100 for acquisition health
- Cash flow improvement planner: Share stock, sales, costs and cash. Compare six changes by cash freed at 180 days and profit impact.
- Cash at day 0, 30, 60 and 180 for each of six levers
- The levers ranked by cash freed, with net income change shown apart
- The best two or three to combine, and what to track for 90 days
- A score out of 100 and how it was worked out
- me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
- One me.md file with up to ten dated sections
- A list of facts taken from memory, for you to check
- A short note of what it removed for privacy
- The two next steps, to save it and set it up
Tasks you can use it for
- You want to know your real profit each month, not only your sales.
- Margin or profit slipped and you don't know which cost line did it.
- You want to see whether new customers pay for themselves, month after month.
Limits to check before starting
- You only need a one-off P&L: build it with a single skill like the Store profit and loss builder instead of running the whole close.
- Your store has no full month of real sales and costs yet: wait a month, or ask your accountant for a simple profit check.
- You need tax or filing advice: ask your accountant, because this agent does not do tax.
Best way to use this role
Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.
- Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to close the month.
- In the first month, give it your invoices and sales. It sets the unit costs, the cost of goods rule and the layout, and saves them.
- From the second month, put the new exports in the same folder. It compares against last month's files.
- Read the list. Make the changes you agree with yourself, and have your accountant check the cost lines it flagged.
- Run it again on the 5th of next month.
Read it as data
Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-profit-close for its role instructions and pinned sources.
This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.