Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.retailgrid.io/llms.txt

Use this file to discover all available pages before exploring further.

Price Optimization suggests an optimal price per SKU using your historical sales data, competitor prices (if available), and a demand model. Use it when you want the system to recommend prices instead of writing the rules yourself. Unlike Rules Based Pricing, Price Optimization is suggestion-driven: it looks at how your prices have moved and how units have responded, and picks the price that maximizes a goal you set (revenue, margin, units).

​
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.
Use Rules Based Pricing instead when you have explicit constraints (margin floors, competitor parity, rounding patterns) you want enforced consistently.

​
Open Price Optimization

In any grid:
  1. Click Agents in the top toolbar.
  2. Select Price Optimization from the All Agents modal.
  3. The configuration panel opens with three tabs: Config by AI, Columns, Parameters.
The Run AI button (or Run button in manual mode) is enabled once Columns has the required mappings.

​
Configure in three tabs

​
Columns - map Price, Cost, and Sales history

The Columns tab maps grid columns to the algorithm’s reserved fields:
  • Price - the current selling price.
  • Cost - cost per unit.
  • Sales / Transactions - historical sales data the model reads to estimate elasticity.
  • Competitor price (optional) - if available, the model accounts for competitive position.
Without sales history the model has nothing to fit; without Cost the model can’t compute margin-based goals.

​
Parameters - set the goal and constraints

The Parameters tab defines what the optimizer is solving for and how aggressive it can be:
  • Goal - maximize Revenue, Margin, or Units.
  • Price change ceiling - cap how far each SKU can move from its current price (e.g. ±15%).
  • Margin floor - never recommend a price that would push margin below this percentage.
  • Time horizon - how far back to look for sales signal.
Defaults are conservative: small allowed changes, margin floor at current margin, 90-day horizon. Start there and widen only when you trust the recommendations.

​
Config by AI - describe what you want in plain language

The Config by AI tab lets you describe the optimization in plain language and have Retailgrid fill in the Parameters tab. Useful when you know the outcome but not which knobs to turn. Example prompt: “Maximize revenue across the KVI products without dropping margin below 18% or moving prices more than 10%.” Review the generated parameters before clicking Run.

​
Read the result

After a run, the grid shows new columns:
  • Optimal Price - the recommended price per SKU.
  • Expected Revenue Lift - estimated impact on revenue at the recommended price (vs. current price).
  • Expected Margin Change - margin pp change at the recommended price.
  • Confidence - how strong the model’s signal was for that SKU.
Click any Optimal Price cell to open the right-side Price Analysis panel - same panel pattern as Rules Based Pricing, with the optimization-specific fields (current price, optimal price, elasticity used, expected lift).

​
Common pitfalls

  • Sparse sales history - SKUs with very few transactions get low confidence and small recommended changes. That’s intentional.
  • Treating recommendations as rules - Price Optimization is suggestion-only. Apply the recommendations through your own pricing workflow; the agent doesn’t write them back as the live price.
  • Goal mismatch - if you set Goal = Revenue, expect the model to drop prices on elastic SKUs. If you set Goal = Margin, expect the opposite. Pick the goal that matches the decision you’re making.