When to use Price Optimization
Reach for Price Optimization when:- You have at least a few weeks of transaction history per SKU - the model needs signal.
- You want a goal-based recommendation rather than a deterministic rule output.
- You want to try “what if we re-priced this category to maximize margin?” without committing to specific guardrails.
Open Price Optimization
In any grid:- Click Agents in the top toolbar (or the pinned Price Optimization button if you have one).
- Select Price Optimization from the All Agents modal.
- The configuration dialog opens as two columns: the configuration tabs - General, Parameters, Rules, and Automation - on the left, and the Config by AI panel on the right.

Configure by AI - describe what you want in plain language
The Config by AI panel sits beside the configuration tabs as a chat-style assistant, usable at any point. Use it when you know the outcome you want but not which knobs to turn.- Prompt - describe your goal in 1-3 sentences. Example: “Maximize profit across the KVI products without dropping margin too far or moving prices more than 10%.”
- Run AI - generates values into the configuration tabs.
Configure across the tabs
Fill the tabs in any order. Config by AI lives beside the tabs and can be used at any point; it switches between the optimization and rules assistants to match the tab you’re on.General - the optimization goal
- Optimization Goal - Maximize Profit (prioritize margin and bottom-line return), Maximize Revenue (drive top-line growth and sales volume), or GMROI (balance margin against how fast inventory turns). Choosing GMROI unlocks a Days of Supply min/max (default 7 and 30 days) and an optional end-of-life date per SKU; the optimizer uses these to raise prices near a stockout and mark down overstock, and falls back to profit-only where they aren’t set. See Inventory-aware pricing with GMROI.
Parameters - scope, inputs, and guardrails
- Manual price overrides - Preserve manually updated prices controls how prices you edited by hand are treated in the run. With it on, those prices stay as they are and the optimizer skips them instead of proposing a new price. Turn it on when you have hand-set prices you don’t want overwritten.
- Expected Impact Timeframe - how far ahead the optimizer projects the impact of the new prices when scoring them (e.g. Next 30 days).
- Confidence tiers - choose which elasticity-confidence tiers the run may act on, so you can hold back low-evidence SKUs.
- Scope - run against the Full grid or a Sample of rows to validate the setup before a full run.
- Inputs - map the grid columns the model reads: Price (current selling price) and Cost (cost per unit). Historical sales/transactions provide the demand signal the model fits, and competitor prices (if present) let the model account for competitive position.
Looking for the account-level model parameters? Clustering, recommendation corridors, seasonality, confidence thresholds, and model freshness are account-level demand-model settings, not per-run ones. They live in Settings → Modelling. See Modelling. That tab is Admin only, because a change there affects every future run and recalculation on the account.
Rules - guardrails on the recommendation
The Rules tab is a permanent tab, with the same rule list, Add rule control, and rule-count badge as Dynamic Pricing. The rules you add here run as the Apply Pricing Rules step after the model proposes prices, acting as guardrails on the recommendation (for example a margin floor or a rounding pattern). The 8 rule types are explained for business users in the Pricing rules guide and in full technical detail in the Dynamic Pricing reference. Rule validation must pass before a run can start.Read the result
After a run, each recommendation lands in its own cell in the output grid - one value per cell, so recommendations are easy to scan and act on row by row. Per recommendation you can:- Set the price type the recommended price should apply as (e.g. regular or promotional).
- Set the effective date the price should take effect.
- Proposed Price - the recommended price per SKU.
- Price Change and Price Change % - how far the recommendation moves the current price.
- New Unit Margin %, New Unit Margin % pp change, and Unit Margin % Change (%) - the margin at the recommended price, and the change against the starting margin.
- Confidence - High, Medium, or Low, reflecting how strong the model’s signal was for that SKU.
- Elasticity Tier and Elasticity - which fit the price response came from, and the coefficient used. Item is a fit on that SKU’s own history and is the strongest; Group borrows from a cluster of similar SKUs; seasonal variants (for example Item Low Season) fit a specific part of the year; Category Default is the fallback where a SKU has too little signal for any of the above. The tier is your quickest read on how much evidence sits behind a recommendation.
- Δ Sales Units, Δ Sales Value, Δ Gross Profit, and Δ Gross Margin % - the forecasted impact of the change over the selected horizon. See Sales forecast and price impact.
Common pitfalls
- Sparse sales history - SKUs with very few transactions get low confidence and small recommended changes. That’s intentional. For SKUs too thin to model on their own, the optimizer borrows demand signal from a cluster of similar SKUs rather than dropping out, so sparse items still get a sensible, lower-confidence suggestion.
- Recommendations go through approval, not straight to live - Price Optimization proposes prices; you review, adjust, and publish them through the price approval workflow. Nothing goes live without your sign-off.
- Goal mismatch - if you set Goal = Revenue, expect the model to drop prices on elastic SKUs. If you set Goal = Profit, expect the opposite. Pick the goal that matches the decision you’re making. Maximize Revenue no longer enforces a built-in cost floor, so on a very elastic SKU it can propose a price below unit cost - add a margin floor rule on the Rules tab if you need a hard lower bound. Maximize Profit still respects margin by design.
Related
- Agents overview
- Dynamic Pricing
- Inventory-aware pricing with GMROI - the GMROI goal and its days-of-supply guardrails
- Pricing rules guide - the 8 rule types with worked examples
- Modelling - the account-level demand model parameters behind the recommendations
- Review and approve price changes
- Sales / Transactions data requirements
- Metrics glossary
- Runs

