Portfolio / Salesforce Personalization Core / AI Recommendations Engine
AI/ML Setup Agentic AI Recommenders Salesforce

The recommenders that decide what a customer sees — and the agents that help marketers set them up.

A companion case study to the Personalization Core platform redesign. Three connected surfaces that turn a deeply technical configuration problem — scoping a product or content catalog, defining filter rules, choosing a recommender strategy — into something a marketer can do with a conversation and a few clicks.

3 surfaces Catalog filters · NL agent filters · Recommender setup agent
Sole IC Senior PD on the recommendations workstream
2023–present Designed alongside the Core redesign
Case study being updated · design images coming soon

The decisioning brain behind every Personalization Campaign.

Salesforce Personalization is a real-time decisioning engine — it picks the right product, article, or piece of content for each customer in the moment. Recommenders are the configurable strategies that drive that decision: collaborative filtering, content-based scoring, behavioral signals, business rules, and combinations of all of the above.

Marketers don't think in terms of cosine similarity or graph traversal. They think: "I want first-time visitors to see our most-viewed seasonal items, but exclude anything we're running low on." The product had to bridge that gap — between marketer intent and a working ML strategy — without dumbing down what the engine could actually do.

The configuration core was the spine. Recommenders are where the AI actually shows up — the surface marketers reach for when they want a smarter answer than "show everyone the same thing."
1 Content variants 2 Decisioning 3 Delivered
1 Content Variants
Seasonal hero offer
Top-rated picks
Recently viewed
Cross-sell bundle
2 Decisioning Logic
Recommender strategy
ML scoring · rules · filters · signals
Qualifying audience
Who is eligible to see each variant
3 Delivered in the moment
● First-time visitor
Sees seasonal hero offer — in stock, region-eligible.
● Loyal customer
Sees cross-sell bundle tuned to past behavior.
Many content variants pass through the recommender's logic and an audience qualifier — each customer is delivered the single best-fit variant, in real time.

Catalogs are big. Rules are deep. Marketers aren't engineers.

Three problems sat on top of each other — each made the next one worse.

Problem 01 Catalogs are massive and messy Customers had product catalogs with hundreds of fields, nested categories, regional variants, inventory states, and thousands of attributes. Scoping the right items for a recommender required deep filter logic the legacy UI couldn't express.
Problem 02 Filter rules required a developer Building anything beyond a single AND/OR clause meant calling Professional Services. Marketers wrote tickets, waited days, and got back something they couldn't tweak themselves.
Problem 03 Recommender setup was a wall of jargon "Pick a strategy" meant choosing between collaborative filtering, content-based, popularity, hybrid — without any guidance on which one fit the goal. Most marketers picked whatever the previous campaign used and hoped.
Problem 04 Trust gap with AI When the engine made a recommendation, marketers couldn't see why. No preview, no explanation, no way to course-correct. AI without auditability is AI marketers won't ship.
Surface 01 Configuration

Complex filters to scope items, products, and content — without writing a query.

A visual filter builder that handles nested groups, mixed AND/OR logic, dynamic value pickers (resolved against the live catalog), inventory-aware operators, and reusable saved filter sets. Marketers can build the kind of scoping logic that previously required engineering — and read it back out as something that looks like a sentence, not a query plan.

  • Nested AND/OR groups with clear visual hierarchy
  • Catalog-aware value pickers — typeahead from real fields, not free-text
  • Live count: "Matches 2,431 of 18,920 items" as you build
  • Inline preview drawer — see exactly which items qualify
  • Reusable saved filter sets — share across recommenders
  • Diff view when a filter is edited mid-campaign
Visual coming Catalog filter builder — nested rule groups, live match count, item preview drawer.
Surface 02 AI · Natural language

Describe the filter in plain English — the agent builds the rules.

A conversational layer that sits on top of the visual builder, not instead of it. The marketer types "show me men's running shoes under $120 that are in stock in the EU and have at least 50 reviews" — the agent proposes the filter graph, populates the visual builder, and shows the live match count. The marketer can then edit visually, refine in chat, or both. The agent is a starting point, not a black box.

  • Mixed-mode editing — chat OR drag, never trapped in one
  • Agent shows its work — every clause maps to a visual rule
  • Ambiguity surfacing — "Did you mean SKU price or list price?"
  • Catalog-grounded — agent only suggests fields and values that exist
  • Iterative refinement — "now exclude clearance items"
  • Auditable — every agent action shows up in the campaign history
Visual coming Agent chat translating an NL prompt into a filter graph, with the visual builder updating in real time.
Visual coming Ambiguity-resolution dialog — agent asking a clarifying question grounded in the catalog schema.
Surface 03 AI · Agent-led setup

An agent walks the marketer from goal → strategy → working recommender.

The marketer states an outcome — "recommend products that pair well with what's in the cart" — and the agent leads a guided setup: it proposes the right strategy (cross-sell, complementary, behavioral), suggests scoping filters, picks reasonable defaults for cold-start and fallback, and previews the live output against real customer profiles. The marketer ends with a tunable recommender, not a decision tree they have to navigate alone.

  • Goal-first prompt — strategy is inferred, not picked from a menu
  • Reasoning sidebar — why this strategy, what it'll do
  • Live preview against synthetic + real visitor profiles
  • Cold-start & fallback handled by default, surfaced for edit
  • Tunable post-setup — every agent decision becomes an editable control
  • Hand-off to the visual configuration core when the marketer wants to dig in
Visual coming Agent-led recommender setup — conversation, reasoning sidebar, and a live decisioning preview against sample visitor profiles.

Four rules I held the line on.

Principle 01 Agent + visual, never agent-only Every agent action is reflected in an editable visual control. No black-box "AI did a thing" — marketers can always see and tweak the result.
Principle 02 Ground the agent in the schema The agent never invents fields. It only proposes filters, values, and strategies the catalog and engine actually support — so trust isn't broken on the first run.
Principle 03 Show the matches, always A recommender setup without a live count and a preview drawer is a leap of faith. Every step shows what the engine would actually return — before the marketer commits.
Principle 04 Auditability is a feature Every agent decision lands in the campaign history with reasoning attached. When a campaign underperforms, the marketer can see exactly which call to question — and which to trust.

From "file a ticket" to "ship a campaign in an afternoon."

The recommendations workstream took the most technical surfaces in the product and made them the most marketer-friendly. Filter rules that previously required Professional Services became something a marketer could draft in a chat box. Recommender setup went from a wall of strategy options to a guided conversation. And every AI action stayed editable — which is what made the AI shippable in an enterprise org that had every reason to be cautious.

More information about the public Salesforce Personalization product: salesforce.com/marketing/personalization

© 2026 · aditya yellamraju · handcrafted, then robot-polished no designers were replaced in the making of this site
Vibe coded · Claude