Skip to main content
Sign up
Coming soon

Product recommendations across channels

Generates catalog-aware product recommendations tailored to user cohorts and evaluates their performance with A/B experiments.

Authored by Intempt Technologies

Recipe curators

Agentic workflow

7 steps Blu runs end to end. It drafts a plan and nothing runs until you approve it.

  1. 1

    Build the recommendation model

    Blu builds a step

  2. 2

    Place them on each surface

    Blu builds a step

  3. 3

    Split shoppers into cohorts

    Blu builds a step

  4. 4

    Test against the alternatives

    Blu builds a step

  5. 5

    Build the email modules

    Blu builds a step

  6. 6

    Follow up with high-intent browsers

    Blu builds a step

  7. 7

    Track what recommendations earn

    Blu builds a step

About this recipe

When to use it

A recommendation engine that only lives on the product page misses two-thirds of the surfaces where it could actually drive a sale. This builds catalog-aware recommendations that work across web, email, and app.

What it delivers

Builds catalog-aware product recommendations that surface consistently across web, email, and app, rather than being confined to a single channel.

How you prompt this

Describe the outcome in your own words and Blu Agent maps it to this recipe, or run it by name. It drafts a plan first and nothing runs until you approve it.

Tell Blu Agent what you want

“Generates catalog-aware product recommendations tailored to user cohorts and evaluates their performance with A/B experiments.”

recipe.md preview

Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.

Sign up to read the full recipe.md and run it with Blu Agent.

Sign up to see the full recipe

Inputs & outputs

What the recipe needs before it runs, and what it leaves in your workspace.

Inputs

  1. Nothing declared beyond an Intempt workspace. Blu asks for anything else it needs as it goes.

Outputs

    How the recipe runs

    Blu follows the steps in order and shows you each one before anything goes live.

    1. 01Build the recommendation modelConfigure recommendation engine sourcing from product catalog with collaborative-filtering and item-similarity models.
    2. 02Place them on each surfaceConfigure personalization rules serving recommendations on PDP, cart, post-purchase, and email surfaces. Use the result of "Build the recommendation model".
    3. 03Split shoppers into cohortsSegment users into recommendation cohorts (new visitor, browsing, returning, lapsed) for tuned strategies. Use the result of "Build the recommendation model", "Place them on each surface".
    4. 04Test against the alternativesAdd A/B variants comparing personalized recs vs trending products vs editor's-pick. Use the result of "Build the recommendation model", "Place them on each surface", "Split shoppers into cohorts".
    5. 05Build the email modulesGenerate email modules that surface recommendations within campaign and journey emails. Use the result of "Build the recommendation model", "Place them on each surface", "Split shoppers into cohorts", "Test against the alternatives".
    6. 06Follow up with high-intent browsersBuild a journey delivering personalized product picks to high-intent browsers. Use the result of "Build the recommendation model", "Place them on each surface", "Split shoppers into cohorts", "Test against the alternatives", "Build the email modules".
    7. 07Track what recommendations earnCompose a dashboard tracking recommendation CTR, attributed revenue, and per-surface performance. Use the result of "Build the recommendation model", "Place them on each surface", "Split shoppers into cohorts", "Test against the alternatives", "Build the email modules", "Follow up with high-intent browsers".

    Install Intempt and run it

    1. 1

      Sign up

      Create a free Intempt workspace.

    2. 2

      Connect your data

      Add the sources this recipe reads from.

    3. 3

      Ask Blu

      Type /personalization-recs in Blu once this recipe is live there.

    4. 4

      Review and approve

      Blu builds each step and waits for your OK before anything goes live.

    Related recipes

    Intempt TechnologiesDiscovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Intempt TechnologiesPost demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Intempt TechnologiesReturn rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    More recipes by Intempt Technologies

    Discovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Post demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Product swap in a sceneReplaces the product in a shot you already have with a different one, keeping the scene, lighting and shadow the same.View recipe

    Got a play worth sharing?

    Publish it to the Intempt Recipe Marketplace and earn when other teams run it.

    Submit a recipe