Show what they buy next.
Recommendations run on the same profiles and catalog as your journeys and experiments. No standalone tool to maintain.
44%
avg CTR lift
~10min
catalog setup
3×
more revenue per session
Cashmere Crew Sweater
$245
Leather Ankle Boot
$320
Adania Pant
Based on recent views
$99
BLU · LIVE INSIGHT
Cart upsell CTR is 44% above baseline — same collab-filter algo on PDP feed
Pick the algorithm and filters for every feed
Configure recommendation feeds per placement — homepage best sellers, PDP similar items, category trending. Choose sorting strategy, time range, and include / exclude / pin rules.
Homepage Best Sellers
PDP Similar Items
Category Trending
New Arrivals Feed
Spring Collection — Meta
3 designs · 2 variants
Google Shopping — All Products
1 design · Single variant
TikTok + Pinterest — Summer
0 designs · Single variant
Configure the recommendation feed algorithm and filters.
Feed name
What products should the customers view first?
Choose an algorithm that determines which items to recommend.
Sorting strategy
Time range
"Our most-loved picks - people can't get enough of these."
Best for: Homepage Fallback: Most Popular — Newest
What additional filters would you like to apply?
Narrow recommendations using Include, Exclude, or Pin...
One feed builder for every surface — homepage, PDP, cart, email, post-purchase.
Algorithm per placement
Best sellers, trending, similar items, frequently bought together, or personalized ranking — pick the right model per slot.
Time range and sorting strategy
Tune feeds by purchase window, view recency, or popularity decay. Last 7 days, last 30 days, or custom.
Include, exclude, and pin filters
Drop out-of-stock items, hide already-purchased products, exclude categories, or pin promotional SKUs to specific slots.
Fallback chain
Set graceful fallbacks — Most Popular → Newest — so every visitor sees a relevant feed even with sparse data.
Same feed builder powers homepage, PDP, cart, and email. No separate tools, no separate models.
Ingest your catalog. Start serving in minutes.
Connect your store and product data flows in automatically — title, price, status, inventory, and attributes. Catalog stays in sync as products change. No standalone tool to maintain.
Ask BluFeature adoption varies significantly across tiers
Dashboard and Reports maintain 90%+ adoption. Content Collaboration and Subscriptions features show under 40% adoption and may need onboarding improvements. Enterprise users engage with 3.2x more features than free-tier users.
| Image | Title | Price | Status | Created by | Last updated | ID | |
|---|---|---|---|---|---|---|---|
 | Adania Pant | $99 | Draft | CKCasey Kim | Oct 24, 2023 · 1:13 PM | 2369467908154 | |
 | Floral Wrap Dress | $185 | Active | SCSarah Chen | Nov 02, 2023 · 2:45 PM | 2369467940922 | |
 | Cashmere Crew Sweater | $245 | Active | ARAlex Rivera | Dec 01, 2023 · 9:30 PM | 2369467973690 | |
 | Leather Ankle Boot | $320 | Active | JLJordan Lee | Jan 10, 2024 · 7:50 PM | 2369468006458 |
Catalog ingest is built in. No warehouse, no ETL, no manual product feeds.
Auto-sync product data
Title, price, image, status, inventory, and custom attributes ingest from your store and stay current.
Drafts, active, and archived states
Recommendations only serve active SKUs — drafts and archived items are excluded automatically.
Custom attributes for filtering
Tag products with margin, brand, collection, or any attribute to power downstream filters and segmentation.
Same data layer as profiles
Catalog and customer profiles share one storage layer — recommendations always know what's in stock and what each customer bought.
Trending and popular feeds ship the same day catalog connects. Personalized feeds tune in within days.
Ask Blu which feeds are working — and why
Surface the feeds driving CTR and revenue, find under-performing placements, and get cross-sell recommendations grounded in your actual catalog and behavior.
BluWhat are the key usage patterns across our product features? How do different user segments interact with features?
Looking at your Intempt platform, here's how different user segments typically interact with your core features:
Primary Feature Usage by Role
VP Marketing/Head of Growth (45% of usage)
• Journey Builder: 68% weekly active usage for lifecycle campaigns
• Segmentation: 78% daily usage for audience targeting
• Analytics Dashboards: 82% daily usage for performance monitoring
• Email/SMS Messaging: 71% weekly usage for campaign execution
VP Product/Product Managers (32% of usage)
• Behavioral Tracking: 85% daily usage for user activity
Ask BluFeature adoption varies significantly across tiers
Dashboard and Reports maintain 90%+ adoption. Content Collaboration and Subscriptions features show under 40% adoption and may need onboarding improvements. Enterprise users engage with 3.2x more features than free-tier users
| Image | Title | Price | Status | Created by | Last updated | |
|---|---|---|---|---|---|---|
| Adania Pant | $99 | Draft | CK | Oct 24, 2023 · 1:13 PM | |
| Floral Wrap Dress | $185 | Active | SC | Nov 02, 2023 · 2:45 PM | |
| Cashmere Crew Sweater | $245 | Active | AR | Dec 01, 2023 · 9:30 PM | |
| Leather Ankle Boot | $320 | Active | JL | Jan 10, 2024 · 7:50 PM | |
 | Silk Camisole - Blush | $110 | Active | MP | Feb 15, 2024 · 2:00 PM | |
 | Wide Leg Trouser - Navy | $175 | Draft | CK | Mar 05, 2024 · 4:30 PM |
Recommendations get the same agent layer as journeys and experiments.
Feed performance insights
Ask Blu which placements drive the most revenue, where CTR is decaying, and what algorithm change to try next.
Cross-sell strategy
Get cross-sell and bundle suggestions grounded in your actual purchase data — not generic 'people also bought' patterns.
Skills you can invoke
Run pre-built skills like 'Cross-sell strategy', 'Product affinity map', or 'Recommendation placement' with one click.
Grounded in your data
Every answer cites the catalog, segment, or feed it pulled from — no hallucinated SKUs, no invented metrics.
Operators ship feed changes the same hour they ask. No analyst ticket, no SQL.
Ask Blu anything about your recommendations
Type a question or invoke a skill. Blu picks algorithms, builds cross-sell strategies, and finds feeds that are decaying.
▎How it works
From catalog to served feed, in minutes
PRODUCT SOURCES
Shopify
Products · prices · inventory
BigCommerce
Catalog · variants · stock
Custom CSV
Upload · auto-map fields
Catalog API
Sync via REST · webhook
▎Step 01
Connect store and catalog
Add your store integration in minutes. Products, prices, and inventory ingest into the same data layer that powers profiles and journeys.
▎Step 02
Build feeds with algorithms and filters
Pick a sorting strategy, set a time range, and add include / exclude / pin rules. Each placement gets the right algorithm.
▎Step 03
Serve, measure lift, and iterate
Render feeds on web, email, or app. Track CTR, add-to-cart, and revenue per placement — and A/B test against control.
Real results, not just tech
We drive measurable outcomes in the first 90 days. Beyond the platform.
“We were losing visitors before they signed up. Intempt's personalized experiences changed that - we started meeting people where they were instead of guessing. Once they're in, Intempt's automated email takes over and keeps the relationship moving. Acquisition and retention finally feel like one connected motion instead of two separate problems.”
Jim Stromberg, CEO
StockInvest
Case Study
StockInvest needed to turn anonymous traffic into registered users before any retention strategy could work. With Intempt's Experiences, they personalized the anonymous visitor flow, surfacing the right content and CTAs to boost signup conversion. Once users signed up, automated Journeys nurtured them through onboarding and deeper engagement, steadily increasing lifetime value.
▎Why teams switch
Intempt vs the recommendations patchwork
Most teams stitch a recommendations vendor with a separate CDP and email tool. Here's the side-by-side.
▎Pricing
From $24/mo per seat. Unlimited feeds.
No per-recommendation fees. No traffic caps on Pro and above. One platform replaces 2–3 tools.
Explore more products
Everything else that turns a recommendation into revenue.
Show what they buy next.
Connect your catalog in 10 minutes. Serve your first personalized feed by tomorrow.
Recommendation questions, answered
Frequently asked questions
Everything operators ask before switching their recommendation engine.
Intempt supports collaborative filtering (users who bought X also bought Y), content-based filtering (similar product attributes), trending/popular items, frequently bought together, and personalized rankings based on individual browsing and purchase history. You can combine algorithms or let AI auto-select the best one per placement.
Recommendations can appear on product pages, cart pages, homepage, category pages, search results, email campaigns, and post-purchase flows. Each placement can use a different algorithm and be personalized independently based on the viewer's profile and context.
Yes. You can exclude out-of-stock items, already-purchased products, specific categories, or products below a price threshold. You can also pin specific products to recommendation slots or boost items based on margin, inventory, or promotional priority.
Every recommendation placement tracks impressions, clicks, click-through rate, add-to-cart rate, and revenue attributed. You can compare algorithm performance, A/B test different recommendation strategies, and see which placements drive the most conversion.
Once your product catalog is ingested, recommendations can start serving immediately using trending and popular algorithms. Personalized recommendations improve as behavioral data accumulates — typically within days of deployment, depending on traffic volume.
Connect your store via the same integration layer that powers profiles and journeys. Products, prices, inventory, and attributes flow into the catalog automatically and stay in sync as your store changes.
Yes. Recommendations share the unified profile and segment library with experiments, journeys, and personalization. A 'high-LTV' segment in journeys is the same segment in recommendation feeds — no audience sync required.
Yes. Render personalized recommendation feeds inside email campaigns using the same algorithm, segment, and filter rules you use on-site. Each email recipient gets a feed personalized to their profile at send time.
Yes. Run experiments on which algorithm, placement, or filter performs best. Recommendations share the experimentation engine, so lift is measured against control with the same statistical rigor.
Recommendations run on the same unified profile as the rest of Intempt — no separate data sync, no warehouse round-trip. Behavior, purchases, and consent all live in one place. SOC 2 Type II, encrypted at rest and in transit.