Ecommerce Ops Agent
A skincare storefront where the search bar is a conversation. Type what you want — the agent finds it, remembers you, and never recommends something you're allergic to.
Search by concern
Built to make a difference.
No filters, no dropdowns
"Moisturizer for dry, sensitive skin under 500" is the whole query. The agent infers intent from one sentence instead of five clicks through a filter sidebar.
Allergy-safe by code, not memory
State an allergy once — it's enforced as an unconditional rule on every search after that, in code. Not something a clever phrasing can talk the model out of.
Remembers you, not just the session
Skin type, concerns, allergies, and brand preferences are captured once and silently applied to every later search — no repeating yourself.
Never goes down on one provider
If the primary model has an outage, the agent fails over through five more tiers before giving up — the shopping experience doesn't break for the shopper.
A real, hosted storefront.
No demo video — these are live screenshots of the actual deployed app.
Storefront homepage
Product listing page
/help — the assistant's capability list
Core features.
Everything built into Ecommerce Ops Agent — no add-ons required.
Conversational product search
Filter the catalog by concern, skin type, ingredient, brand, or price — all from one typed sentence, no rigid query syntax.
Code-enforced allergy guardrail
Allergen filtering happens after every search call, unconditionally — not left to the model to recall mid-conversation.
Persistent shopper profile
Skin type, concerns, allergies, and brand preferences persist for the session and shape every recommendation after they're mentioned.
Cart actions through chat
"Add the CeraVe one to my cart" calls the exact same action as clicking the button — same table, same state.
Bounded, cost-safe context
Long conversations don't quietly balloon token cost or blow past the model's context window.
Six-model fallback chain
Five Gemini tiers tried in sequence, Anthropic last — a single exhausted quota or provider outage doesn't take the assistant down.
Rate-limited and input-validated
The LLM-calling endpoint is protected before any model is even called, not after.
What shopping over chat looks like.
Both flows below are verbatim, captured against the live agent and its real seeded catalog — not staged for marketing.
Search by concern
/help — discover what it can do
What a bolted-on chatbot usually gets wrong.
Built with.
Want to see it handle your query?
It's a real, hosted storefront — not a recording. Ask it something specific and watch it actually search, filter, and remember.