A regular is looking for something new. You send them last year's path.

Connected

Search or browse behavior that does not match the customer's established category, plan, or saved preference.

Example eligibility rule

Define a regular as someone with completed orders > 1 or recognized visits > 2 in the previous 90 days. Require at least two meaningful views or one search plus one detail view in the new category before offering a new path. Keep the usual path visible.

Reorder module, "continue the series", the beginner tour, last season's aisle: all correct for the old job. This session they searched a new category, invited a different role, or opened a different sport. History is a prior, not a prison.

Avoid this assumption

A "welcome back" with last year's merchandising is not recognition. This case changes the return path across visits. "They're ready to buy something new. You keep selling last time." focuses on recommendations during an active shopping session.

Retention personalization that only replays the last order trains people to ignore you. A fork (usual path or the new one this session named) is the test.

Reach

How many eligible people can you reach in the chosen channel and time period?

Cost

What will content, delivery, QA and ongoing maintenance cost?

Return

What incremental outcome would cover that cost, and what is it worth?

Planning inputs, not measured results. Estimate reach × incremental outcome rate × value per outcome, then subtract cost. Use a range and a consistent time period.

Example format: Experience

Split the first screen: usual, and the new job this session.

Compare lighter and deeper responses

Choose the lightest response that solves the need.

Assist: Offer useful help

Keep the usual module. Add a chip for the new thread they just started.

Adapt: Change a meaningful part

Split the first screen: usual, and the new job this session.

Transform: Tailor the journey

Lead with the new job, keep the usual one tap away, stop the old tour.

What to watch out for

• Wiping a loyal path because of one curious click.
• The beginner tour on a three-year customer.
• No way back to "the usual".

Control

History-first home or recs.

Treatment

Session-aware fork, with a holdout.

Success measure

Completion of the new job (new category purchase, new feature used).

Guardrail

Reorder or habitual conversion. Don't starve the path that still pays.

Among regulars who meet the new-interest rule, compare the session-aware fork with the usual returning experience. Measure completion of the new job and any decline in habitual conversion separately.

Win or lose, record what worked, for whom and why. What you learn becomes the next signal.

• Dynamic Yield Personalization and recommendations platform with a merchandising engine and Experience APIs for running recs and server-side experiments on any channel.
• Nosto AI commerce platform combining personalized search, recommendations, merchandising, and content/A-B testing under one data layer.
• Bloomreach Ecommerce Search AI-driven ecommerce search and discovery platform (Loomi AI) that personalizes ranking, recommendations, and merchandising from first-party shopper data.
• Insider One Cross-channel engagement platform (web, app, messaging) that builds a unified profile from attributes, real-time behavior, and precomputed predictive scores to drive personalization and campaign targeting.
• Sitecore Personalize Real-time web personalization and A/B/n testing inside Sitecore, driven by live behavioral and contextual signals.
• Algonomy Retail personalization suite (search, recs, dynamic listing pages, content/styling, social proof, shopping agent) built on the earlier RichRelevance/Manthan merger. Now operating under the ADA brand after ADA acquired Algonomy in July 2026.

They're ready to buy something new. You keep selling last time. Let this visit lead. Don't trap them in what they already bought.

A member still gets the generic homepage. Put reorder and their benefits first. The brochure can wait.