“Which of these is right for me?” is one of the most common questions on an online store’s WhatsApp, and one of the worst to answer with a list. Dumping ten links leaves the customer more lost than before. The choice assistant in ChatSense’s AI agent does what a good salesperson would: understands what the person wants and recommends a few options, explaining why each one fits.
How the agent steers the conversation
- Category first. When the customer names a type of product, the agent starts from the store’s category and asks one question at a time, only the one that really separates the options.
- Recommends from the description. The agent reads the description of each published product, along with name, categories and variants, and uses it to match what the customer asked for.
- Few options, with the reason. The reply brings a short list of up to 3 products, each with why it fits, the link and, if the store allows, the price read live.
- Models only on request. The agent does not dump variations: it shows models when the customer asks, chosen from the description.
And when nothing fits?
If no product matches the request, the agent says so honestly and asks what the customer would be willing to relax, instead of pushing something that does not fit.
What it takes to work
You need your Nuvemshop store connected to ChatSense (connecting has no extra cost). The lookup is read-only: the agent does not change products, stock, prices or orders. The merchant still decides, per store, whether the agent states prices, and the help with choosing respects that option. Since the assistant relies on product descriptions, the clearer your descriptions (what it is for, where it is used, care instructions), the better the recommendations.
Alongside the rest of the store’s support
The assistant sits next to what the agent already does on Nuvemshop: checking order, payment, shipping and tracking live for the buyer only, answering returns and shipping with the store’s policies, and handing over to the team with context. See also our post on Bling, Tiny and Nuvemshop integrations in support.
Frequently asked questions
Does the agent make up products or features?
It relies on the store’s published catalog and each product’s description. If nothing fits, it says so and asks what to relax.
How many products does it recommend?
A short list of up to 3, each with the reason it fits. The goal is to help decide, not to widen the doubt.
Does the agent show the price?
Yes, if the store lets the agent state prices. The value is read live from the store.
Does it work with other store platforms?
The choice help described here is for Nuvemshop stores connected to ChatSense.
Go further: see how ChatSense works for e-commerce, clinics; compare it with other tools on the comparison page and check the plans and pricing.
Want to see this working in your business? Book a 30-minute demonstration with the ChatSense team.