Site Merchandising Assistant: what this AI agent does and how to use it
Recommends which products to feature on category pages from sales, stock and newness. Who it's for, the questions it answers, the data it needs and how to switch it on.
Try the Site Merchandising Assistant live demo →
What it does
Product pages sell when the data is complete. These agents audit your catalog's quality. The Site Merchandising Assistant agent is the specialist for this job: recommends which products to feature on category pages from sales, stock and newness.
Who it's for
Your team. It runs in the console for your staff and through the REST API. It is a team agent, so it is never exposed to shoppers.
Questions it answers
Ask it in any of our languages, for example:
- "Which 8 dresses should lead the Dresses page this week?"
- "What should we feature on the home page?"
- "Which products should we stop featuring?"
The live demo shows these as sample prompts in your language, on a fictional store's data.
How it works
- It understands the question in the language it was written in, even when your catalog is in another language.
- It looks things up with tools, never from memory:
- Read-only sql over your retail data (sandboxed per workspace)
- Sales analytics by category, channel or period
- It answers from your data, in your brand voice and currency, and shows which tools it used.
- Rules stay in code. Prices, eligibility and permissions come from your data and settings; the agent explains them and can't invent them. Why this matters.
The data it needs
Products, Orders, Order lines, Inventory. As soon as these tables are loaded, the agent is ready to switch on. Files can use your own column names: they're mapped automatically. See Connect your data.
Works well with
- Catalog Quality Auditor: Finds products with missing prices, images, descriptions or attributes.
- Promo Code Explainer: Explains which promotions are running, what they apply to and why an offer did or didn't apply.
- Checkout Help Assistant: Helps shoppers with payment options, promo codes, delivery choices and checkout questions.
Your team can use them side by side in the console, or call each one through the API.
Turn it on
- Load the data it needs.
- Install Site Merchandising Assistant from the Agent catalog and add your own instructions (guide).
- Test it in the Playground, in every language you serve.
- Invite your team or call it from your own systems.
New to ServiceBuddy? Start with how onboarding works.
Try it, and related AI Agent Buddies
E-commerce & digital
Site Merchandising AssistantRecommends which products to feature on category pages from sales, stock and newness.
E-commerce & digital
Catalog Quality AuditorFinds products with missing prices, images, descriptions or attributes.
E-commerce & digital
Promo Code ExplainerExplains which promotions are running, what they apply to and why an offer did or didn't apply.
E-commerce & digital
Checkout Help AssistantHelps shoppers with payment options, promo codes, delivery choices and checkout questions.
More about E-commerce & digital
Promo Code Explainer: what this AI agent does and how to use it
Explains which promotions are running, what they apply to and why an offer did or didn't apply. Who it's for, the questions it answers, the data it needs and how to swit…
Checkout Help Assistant: what this AI agent does and how to use it
Helps shoppers with payment options, promo codes, delivery choices and checkout questions. Who it's for, the questions it answers, the data it needs and how to switch it…
Catalog Quality Auditor: what this AI agent does and how to use it
Finds products with missing prices, images, descriptions or attributes. Who it's for, the questions it answers, the data it needs and how to switch it on.
Related articles
AI agents for quick commerce & dark stores
1 live agent (Basket Completion Nudger) and 8 on the roadmap: what each does, the data it needs and the questions it answers.
AI agents for it & data
1 live agent (Report Request Assistant) and 8 on the roadmap: what each does, the data it needs and the questions it answers.
AI agents for omnichannel & fulfilment
4 live agents (Reserve and Try Assistant, Collection Order Chaser, Endless Aisle Ordering…) and 5 on the roadmap: what each does, the data it needs and the questions it …
AI agents for brand & creative
3 live agents (Naming and Tagline Generator, Heritage Storytelling Writer, In-store POS Designer) and 7 on the roadmap: what each does, the data it needs and the questio…
AI agents for category management & buying
2 live agents (Category Strategy Writer, Buy Depth Recommender) and 16 on the roadmap: what each does, the data it needs and the questions it answers.
The ServiceBuddy catalogue: 608 AI Agent Buddies for retail
Every use case in the catalogue, grouped by business function and retail segment: 107 live today, the rest on the roadmap.
AI agents for customer insight & research
3 live agents (Basket Affinity Analyst, Customer Lifetime Value Model, Style Preference Profiler) and 5 on the roadmap: what each does, the data it needs and the questio…
AI agents for replenishment & forecasting
8 live agents (Safety Stock Optimiser, Phantom Inventory Detector, Seasonal Build Planner…) and 15 on the roadmap: what each does, the data it needs and the questions it…
AI agents for training & internal comms
5 live agents (New Range Briefing Pack, Micro-learning Builder, Role-play Sales Trainer…) and 9 on the roadmap: what each does, the data it needs and the questions it an…
Refund Status Tracker: what this AI agent does and how to use it
Tells customers where their refund is, when it will land and why it might be delayed. Who it's for, the questions it answers, the data it needs and how to switch it on.
Human handover summariser: what this AI agent does and how to use it
Prepares a crisp case summary for a colleague taking over a customer, with the suggested fix. Who it's for, the questions it answers, the data it needs and how to switch…
Modest Fashion Edit: what this AI agent does and how to use it
Curates modest outfits by occasion, fabric weight and coverage preferences from the current range. Who it's for, the questions it answers, the data it needs and how to s…

















