Tidio’s Product Recommendations is an exciting AI innovation, where Lyro recommends products to your visitors when they ask for specific product advice.
This guide focuses on making Product Recommendations possible by connecting your product database via OpenAPI - an advanced resource for developers. If you are using Shopify, we have a dedicated integration method that will allow you to use Product Recommendations for your store without OpenAPI. Please see our detailed guide on that method here.
In this article, you will learn:
- Who Product Recommendations (via OpenAPI) is available for
- What conversation types can be handled
- What developer resources are needed
- How to set up Product Recommendations in Tidio
- How to pause Product Recommendations
- What the limitations are
Who can use Product Recommendations (via OpenAPI)?
When integrated through OpenAPI, the Product Recommendations tool is platform-agnostic. That means anyone can use it, regardless of the platform they're using, as long as they can implement the available OpenAPI resources. This makes it a powerful tool at your disposal, although you will need your own developer to integrate it properly with your business. Once integrated, Product Recommendations can work with any e-commerce backend, whether it's a custom-built CMS or a plugin such as WooCommerce or BigCommerce.
Product Recommendations lets your Lyro AI agent assist your visitors with product questions. For Lyro to answer these questions, you will need to connect your product database with your Tidio project - which is done through OpenAPI. This will allow your product database to be utilized as knowledge for Lyro. Please note that Lyro understands your product information in multiple different languages!
To use Product Recommendations, you also need to be a subscriber of the Lyro AI Agent package in Tidio (or the custom Plus package, of course). The relevant developer resources will become available for use on your Tidio project then.
Please note that the Product Recommendations tool is not available during the initial free trial.
Please note: Lyro can detect a visitor's current URL automatically, which allows you to use this information in product-related responses. This is especially valuable if Lyro is asked about a product that the visitor is currently viewing on your website. Lyro will be aware of the product being browsed and won't need to ask the visitor about the details first, nor use any previously-recorded data.
Conversation types handled by Product Recommendations
Using Product Recommendations, Lyro can help your visitors in the following ways:
- Specific product search - find a specific product
- Broad product recommendation - help choose products
- Product variant recommendation - find products with variant limitation
- Complementary product recommendation - find products that work well together (if mentioned in product description)
- Alternative product recommendation - find products with similar properties
- Product comparison - compare two (or more) products
- Price range recommendation - find products based on price point
- Seasonal product recommendation - find new products or products in collections
Developer documentation for OpenAPI
The first step is to share our official API documentation with your developer(s).
This article covers only the product part of the OpenAPI. That is the part of the documentation that's necessary for Product Recommendations to work, and it's available to all subscribers of the Lyro AI Agent package.
Setting up Product Recommendations
To begin your setup, navigate to the Lyro AI Agent section in your Tidio panel, and open the Products tab:
Inside, you will see two available options: Shopify product sync (which is described separately in this guide) and Add products via API (which is being covered here):
In addition to that, you can also choose between two different business models at the top: E-commerce or I provide services:
At the moment, only the e-commerce option is readily available; if you select the services option, you will be asked for the type of services you offer (e.g. real-estate listings, travel, courses), and you will be added to our waiting list.
Once you select the e-commerce option, click the Add products via API tile. You will see a popup where our API documentation is linked, so that you can share it with your developer(s):
At this point, it is up to your developer(s) to configure and implement the necessary API, which will connect your product database with Lyro.
Once that is done and ready, you will be notified about it inside the popup - allowing you to hit the Done button and confirm the connection:
Finally, your product database will become visible in the Products tab, along with some basic details (and the option to decide whether the database should be used by Lyro and/or Copilot).
From now on, Lyro (and Copilot) will be able to connect with your product database and refer to your products during conversations.
Pausing Product Recommendations
You can temporarily disable Product Recommendations anytime, from within the Products tab inside your Lyro AI Agent section. Notice the Used by options at the bottom, where you can disable (or enable) the Lyro and Copilot switches:
This allows you to keep Lyro (and/or Copilot) from using your Product Recommendations database. You can switch any of these options back on again whenever you like.
Product Recommendations limitations
Lyro AI Agent subscription
Using Product Recommendations is only possible if your project is subscribed to the Lyro AI Agent package.
Visitor currencies
Via API, you are able to set a default currency (e.g. USD) for your store, as well as a price for each of your products. However, for Lyro to display other currencies that are more appropriate to your different visitors (e.g. Euro), you will need to share both currency and currency_rate for each visitor, in real time, via Widget SDK (which is covered in our OpenAPI documentation). If this is not set up, Lyro will always use your default currency and pricing instead.
Comments
0 comments
Please sign in to leave a comment.