Hire an AI sale discount and price change review
Check a sale or price change against real costs. Get margin checks, offer wording and a price list to approve.
What you give
- Your plan, with the products, the change, how long it runs and why
- Selling price, unit cost, freight, shipping out, fees and your 90-day refund rate, the first time
- Your margin floor for sale prices
What you get
- Margin and break-even ROAS for each product, at the current and planned price
- The deepest discount that keeps your floor, or a plain "no discount fits"
- Stock to have ready, or clearance stages with dates
- Sale wording, and a previewed price list to approve
An example
You plan a sale, a discount code or a clearance and want to know it still pays.
You ask: “Check a sale or price change against real costs. Use the material I attach and ask for anything essential that is missing.”
You get back:
- Job and verdict. Says if this is a sale, clearance, price rise or clean-up, and whether to go, fix or stop.
- Margin. Gross margin and break-even ROAS for each product at the current price and the planned price, against your floor.
- Depth that holds. The first tested discount that keeps your floor and how many rounds it took, or a plain no.
An example, not your task.
Words used here
- ROAS: sales earned for each unit of money spent on ads
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
Details
Everything it can hand back
Your task sets the actual outputs. The specialist picks the methods that cover them.
- Margin and break-even ROAS for each product, at the current and planned price
- The deepest discount that keeps your floor, or a plain "no discount fits"
- Stock to have ready, or clearance stages with dates
- Sale wording, and a previewed price list to approve
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
- Picking a discount depth from what looks big, then checking the margin.
- Stacking a code on top of a sale without testing the combined depth.
- A strikethrough price that was never charged.
- Rolling out a price rise to everything at once.
- 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 plan a sale, a discount code or a clearance and want to know it still pays.
- Job and verdict. Says if this is a sale, clearance, price rise or clean-up, and whether to go, fix or stop.
- Margin. Gross margin and break-even ROAS for each product at the current price and the planned price, against your floor.
- Depth that holds. The first tested discount that keeps your floor and how many rounds it took, or a plain no.
- Stock and timing. Extra stock to have ready, or clearance stages, with start and end dates.
- Wording. The offer form, the sale price display and the banner text.
- Price list to approve. Each product with its old price and new price, shown as a preview.
How the work is checked
- Every product's margin is checked at the planned price, not only at the current one.
- The proposed depth was tested at the stated costs and floor, or is explicitly untested or failing. No capped search is described as a global optimum.
- A price rise comes with an undoable test.
- The strikethrough list is a preview. Nothing live changed without a clear yes.
- 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
- Name the job. Decides if this is a sale, a clearance, a price rise or the monthly clean-up of old strikethrough prices.
- Test the margin. Checks gross margin and break-even ROAS at the current price and at the planned price, against your floor.
- Loop on depth. If the margin fails, it cuts the discount by five points and checks again, up to three rounds. It stops at the first depth that holds.
- Choose by job. A sale gets a stock check. A clearance gets staged cuts. A price rise gets a lowest viable price and an undoable test.
- Word it. Sets the percent or amount form, the sale price display and the banner text, without promising a deeper cut than the plan allows.
- Hand back a preview. Gives you the plan and a previewed price list. It changes live prices only after 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 discount-and-price-change-checker 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/discount-and-price-change-checker/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
- Your plan, with the products, the change, how long it runs and why
- Selling price, unit cost, freight, shipping out, fees and your 90-day refund rate, the first time
- Your margin floor for sale prices
- Stock levels and past promotion results (optional)
Helpful context (optional)
- Shipping and warehouse quotes per order
- The results of your last two or three sales
Tools and access
- Claude Code: It can keep the pricing folder, read your log and run the monthly clean-up on a schedule.
- Your store platform: Export product prices, compare-at prices and stock levels. Connect it only if you want the agent to make a change you approve.
- 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 only needs to solve one equation and compare the answer with the market.
- Google Sheets: Put the waterfall in a sheet so you can change CAC and see the price move.
- ChatGPT with data analysis, or Claude with code execution: They can fit the lift model to your sales table and show the result.
- Any good chat AI: Fine for the calendar and stock plan once you give it lift figures.
Functions and deliverables
- Sale discount and price change review: Check a sale or price change against real costs. Get margin checks, offer wording and a price list to approve.
- Margin and break-even ROAS for each product, at the current and planned price
- The deepest discount that keeps your floor, or a plain "no discount fits"
- Stock to have ready, or clearance stages with dates
- Sale wording, and a previewed price list to approve
- 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
- Minimum viable price calculator: Share costs, sales targets and acquisition spend. Calculate the lowest viable price or identify a product that cannot pay.
- The lowest viable price
- A bottom-to-top price table at low, mid and high CAC
- A keep, reprice, reposition or cut call, with the reason
- A list of checks it could not finish
- Price test planner: Share costs, sales history and price options. Compare contribution, test demand cases and plan a reversible price test.
- Recommended price to test
- Base, low and high cases
- Test design with guardrails
- Rollback plan
- Promotion and stock planner: Share past promotions, baseline sales, stock, and costs. Get estimated promo lift and stock needs.
- A promotion calendar
- Expected lift for each deal type
- Return after trade spend for each deal
- Extra stock needed by week and location
- A clear go, change or stop for each deal
- Clearance discount planner: Share stock, past prices, sales, and deadlines for a discount plan with sales and revenue estimates.
- A markdown schedule by item, with the week and depth of each cut
- A recommended price for each item
- Expected revenue and how many units should clear
- A week-by-week plan, with store-level changes
- A before and after estimate of markdown cost
- Discount wording and price display planner: Turn a real price cut into sale badges, price displays and coupon wording. Get the sums, suggested wording and checks on the reference price.
- The best discount format, percent or amount
- Sale price display and badge wording
- Banner and email subject lines
- A warning if the discount is too deep
- A check that the reference price is genuine
- Fake sale price cleaner: Share store and age limit. Get stale compare-at prices in dry-run; live updates clear those without a real discount.
- A dry-run list of affected variants
- A CSV backup of old values
- Cleared compare-at prices on a live run
- A count of what changed
- Bulk price changer: Change prices for a whole Shopify collection or tag at once, with a floor and ceiling. Preview every old and new price before it goes live.
- A preview of old and new prices
- Updated prices on every variant
- Price limits applied
- A summary of what changed
- 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 plan a sale, a discount code or a clearance and want to know it still pays.
- You want to raise prices and need a test you can undo.
- You think old strikethrough prices are sitting on your product pages.
Limits to check before starting
- You sell one product on a one-off whim: work out the margin by hand in a spreadsheet instead.
- Your prices are fixed by a supplier or a retailer: there is no price for this agent to test, so skip it.
- You need tax or legal advice on sale claims: ask an accountant or a lawyer who knows your country's rules.
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 (a paid tool, needed only to save the pricing folder and run the monthly clean-up on a schedule), add it as a skill or save it in .claude/agents, then give it your plan. A plain chat works without it.
- The first time, give it your product costs and your margin floor. It saves them.
- Read the margin table and the depth that holds. Change the plan if you want a deeper cut and accept the lower margin yourself.
- Approve the price list in clear words if you want it to make the change. This needs a store connection with write access, which your store admin sets up and your plan or the connector may limit or charge for. Otherwise, change prices yourself from the preview.
- After the sale, tell it the result so the log can use it next time.
Read it as data
Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/discount-and-price-change-checker 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.