Health & wellness
Product questions answered. Health questions go to people.
The AI answers from your product data, policies and orders. It's set up not to give medical advice: health questions go to your team.
Illustration: on WhatsApp, a customer asks a wellness store whether its plant protein is vegan and how many servings a bag has. Inside Kanesh, the AI reads the product in the Shopify catalogue, checks the draft and replies with the published facts and a product link. When the customer asks whether she can take it with her thyroid medication, the AI doesn't answer the question: following the store's rule, it hands the conversation to a person on the team with the reason.
Two kinds of questions, two kinds of answers.
Questions about the product can be answered from your label. Questions about the person's health can't, and the AI shouldn't try.
“Is the plant protein vegan? How many servings are in a bag?”
- What the answer needs
- The information you've published for that product.
- In Kanesh
- AI answer from your product information
“How do I take it?”
- What the answer needs
- The directions on your label, quoted as written.
- In Kanesh
- AI answer from your label information
“Can I take this with my blood pressure medication?”
- What the answer needs
- A person, because the AI doesn't answer this.
- In Kanesh
- Handoff by your rules, with the reason
“Is it OK to take during pregnancy?”
- What the answer needs
- A person, every time.
- In Kanesh
- Handoff by your rules, with the reason
“When will my order arrive?”
- What the answer needs
- Live status and tracking, shared only after checking who's asking.
- In Kanesh
- Order status after verifying the customer
“Which flavours does it come in, and is there a bigger size?”
- What the answer needs
- Flavours, sizes and stock from your catalogue.
- In Kanesh
- Suggestions from your catalogue
Product answers. People for anything about health.
The AI stays inside what you publish. You draw the line between product and health questions, and the AI follows it.
Answers from your label and policies
The AI is instructed to answer only from your product information, directions of use and policies, with each reply checked before sending.
- Source
- product information you upload
Health questions handed to a person
Situations you define, like symptoms, medication, pregnancy or health conditions, go to your team with the reason, not an AI answer.
- Source
- your handoff rules
Replies checked before they're sent
Every reply is checked against your data and rules before sending, and a person answers what your published information can't back up.
- Source
- your data and rules
Suggestions by flavour, format and size
The AI can suggest products from your live Shopify catalogue by flavour, format or size, leaving health needs to a person.
- Source
- your Shopify catalogue
Order status after verification
“When will my order arrive?” gets live Shopify data, including tracking, once the AI has checked the customer is on the order.
- Source
- live Shopify orders
Campaigns only to people who opted in
WhatsApp campaigns go only to opted-in customers, and each opt-in is stored with the exact text accepted and how it was given.
- Source
- your opted-in audience
What stays with your team
The AI is set up to talk about your products and orders, not about someone's health. Under your rules, these go to a person, with the reason and the context:
- Symptoms, medication, pregnancy or any health condition
- Choosing a product for a health need
- Changing, cancelling or refunding an order
- Anything your published information doesn't cover
- Anything your own rules send to a person
- Your product claims: you approve them under EU rules such as Reg. (EC) 1924/2006, and the AI answers only from the content you approved
AI on products. People on health.
Here the line matters more than speed. You decide which topics always go to a person; every reply is checked against your data and rules.
- Health, medication and pregnancy questions routed to a person by your rules
- Answers based on the information you've published
- Replies checked against your data and rules before sending
- Opt-ins stored with the exact text the person accepted
Questions from health and wellness brands
Does the AI give health or medical advice?
How do we decide what goes to a person?
Does Kanesh make our product claims compliant?
Can we send campaigns on WhatsApp?
Which languages does the AI reply in?
See what your conversations are missing.
See how your channels, team and AI work together. Let’s talk about your operation and your plan.