Personal Shopper: what this AI agent does and how to use it

Try the Personal Shopper live demo →

What it does

Shoppers rarely know the exact product name. These agents turn a question like "a black dress for a wedding under 80 euros" into real products from your catalog, in the shopper's own language. The Personal Shopper agent is the specialist for this job: finds products by intent, budget, colour and occasion; compares options and recommends the best fits.

Who it's for

Your customers. It runs in the branded shopper assistant on your website (one line of code) or on a shareable link, and through the REST API in your own app or contact centre. Your team can also use it in the console Playground.

Questions it answers

Ask it in any of our languages, for example:

• "A flowy summer dress for a beach wedding under $50"
• "White sneakers for men"
• "A gift for my mom who loves bags"

The live demo shows these as sample prompts in your language, on a fictional store's data.

How it works

1. It understands the question in the language it was written in, even when your catalog is in another language.
2. It looks things up with tools, never from memory:

• Semantic product search with filters (price, colour, category)
• Full product details

3. It answers from your data, in your brand voice and currency, and shows which tools it used.
4. 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. As soon as this table is 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

• Shop the Look Stylist: Builds a complete, coordinated outfit around any product or occasion using only real catalog items.
• Gift Finder: Turns "who it's for, occasion, budget" into a curated shortlist of gift ideas.
• Product Comparator: Compares 2–4 products side by side on price, colour, category, brand and suitability.
• Beauty Advisor: Recommends makeup, fragrance and personal-care products for a look, occasion or preference.
• Size & Fit Advisor: Helps shoppers choose a size from sizing policies and product details.

In the shopper assistant and the Playground, a router reads each message and hands it to the right agent, so connected agents work as one assistant.

Turn it on

1. Load the data it needs.
2. Install Personal Shopper from the Agent catalog and add your own instructions (guide).
3. Test it in the Playground, in every language you serve.
4. Go live on your website or a link, or call it from your own app.

New to ServiceBuddy? Start with how onboarding works.