Skip to main content
Use this guide when launching recommendations into a new surface (for example homepage, PDP, checkout upsell, or email digest).

​
Setup

  1. Define the business goal for the new surface (CTR, conversion, AOV, retention).
  2. Create a dedicated context in Console -> Contexts.
  3. Configure context-level defaults (quantity, filters, boosts).

​
Common workflows

​
Validate context behavior in staging

  • Call GET /recommendations with the new context_id and representative user_id values.
  • Compare output quality with and without the context applied.
  • Confirm the right item categories and constraints are reflected.

​
Roll out progressively

  • Start with a small traffic segment.
  • Keep context-specific instrumentation so results can be measured independently.
  • Increase rollout percentage only after quality checks pass.

​
Keep context docs operational

For each context, maintain a short owner note with purpose, constraints, and KPI target so changes remain auditable.

​
Example app journey: Checkout upsell launch

  1. Merchandising defines checkout upsell objectives.
  2. Team creates context 205 with checkout-safe filters.
  3. Backend requests recommendations using context_id=205 during checkout.
  4. Events are tagged from checkout interactions and posted to /events.
  5. Analytics is filtered by the checkout context to evaluate lift.

​
Next steps