Shopping Muse leverages AI technology to offer users a unique product discovery experience through interactive conversations and personalized product guidance. Powered by advanced transformer and LLM models, the system engages your users with natural language conversations. Whether they're searching for specific products, fashion styles, or gifts for special occasions or holidays, Shopping Muse provides tailored suggestions to meet their needs.
Onboard Shopping Muse
- Open the Shopping Muse app, and then click Create Muse.
- A wizard appears to guide you through customizing your assistant’s tone of voice and brand name—these settings define how your Shopping Muse behaves.
When setup is complete, the Shopping Muse dashboard appears. You can adjust your initial choices at any time by clicking Customize.
Get your API key
As of July 3, 2025, Shopping Muse is available only through the assistant API and requires an API key. You can integrate the API without writing code by using Experience Web campaigns, where the API key is built into the template for web environments.
- In Settings › API keys, click New Key.
- Give your key a name, and optionally, add notes.
- Select a source:
- If you're implementing Shopping Muse using an Experience Web template, select Client-side.
- If you're implementing the API via your server, select Server-side.
- Select Experience API in the ACL area, and click Save.
Implement Shopping Muse and go live
Depending on the size of your product feed, Shopping Muse can take up to 24 hours to complete the initial training on your products. During this process, Shopping Muse learns about your brand and products and how to recommend them.
Implement using an Experience Web campaign template
Dynamic Yield offers several out-of-the-box conversational templates that seamlessly integrate Shopping Muse APIs—often alongside other Experience OS features and products. These templates are no-code and ready to go live immediately.
Learn more about the templates and their implementation guidelines
Implement via API
Dynamic Yield enables you to integrate conversational experiences across various non-web channels such as mobile apps, point of sale systems, WhatsApp, and more. This also applies when custom use cases require it—for example, embedding Shopping Muse into a search listing page.
Learn more about the templates and their implementation guidelines
Reports
Dashboard report
The Shopping Muse report you see on your dashboard enables you to track and monitor key e-commerce performance indicators, including sessions, clicks, and messages sent. It also includes post-message metrics with a 7-day attribution window for revenue, purchases, and average order value (AOV).
Full Report
For deeper analysis, use the full Experience OS report, which offers advanced analytics, detailed metrics, and flexible breakdown options with the same attribution method.
FAQ
Shopping Muse suggestions are influenced by the type of images it's trained on:
-
Wild Images: Product images featuring human models in atmospheric or inspirational backgrounds, often including additional products. For example, a picture of a model wearing a pair of jeans that also clearly shows sunglasses, a shirt, and shoes. In this case, the algorithm focuses on recommending items that match the overall style and look represented in the image.
If you use wild images, we suggest applying recommendation filters to align with the specific category of the item in context. - Studio Images: Clear images of the product against a clean background. The algorithm prioritizes recommending similar products based on attributes like color, texture, material, and style. Studio images typically yield better results.
Note: By default, the model processes the image_url column in your catalog. If you want to use different images, contact your customer success manager or Support for help with custom configuration.
-
The model requires access to your image CDN to download and process your image. Have your technical team add the following IP addresses to your allowed list:
-
- 18.197.234.165
- 3.127.189.219
- 18.158.108.19
-
- 18.192.189.87
- 18.195.163.252
- 3.92.38.28
-
- 3.227.221.249
- 54.145.37.112
- 75.101.154.167
-
- If the CDN does not respond within 5 seconds for a specific image, that image is skipped.
- Maximum image size is 10 MB
- The image path must be explicit. For example:
Correct: https://mydomain.com/myimage.jpg
Incorrect: //mydomain.com/myimage.jpg or //myimage.jpg
The model we use for the Shopping Muse response is proficient in many languages. However, its performance tends to be best in the following languages:
-
- English
- Spanish
- French
- German
-
- Dutch
- Italian
- Portuguese
-
- Russian
- Chinese (Simplified)
- Japanese
Shopping Muse can handle most other languages with varying degrees of proficiency, including Arabic, Polish, Hebrew Korean, Turkish, and many more. The model’s capabilities are extensive but can vary depending on the complexity and nuance required in a specific language.
Product recommendation quality does not vary between languages.
Shopping Muse incorporates multiple safeguards to ensure its responses are always brand-safe and aligned with your values. The model is trained specifically for each brand, guaranteeing consistency in voice and tone. Moreover, Shopping Muse only recommends products that are pre-approved by your team.
In addition, Shopping Muse employs a micro-service architecture. The product recommendation task, responsible for suggesting relevant products to the user, and the assistant task, which responds in natural language, are entirely separate. The LLM does not have access to product meta data. Therefore, Shopping Muse can't, for example, incorrectly claim that a specific product is available for free due to any penetration tactics.
All personalization calculations are done on Dynamic Yield servers and comply with regional limitations such as GDPR. Users' personal data is not shared with the LLM or third parties.
No. No specific brand or user data is used for training Shopping Muse.
JPEG, GIF, HIEC, PNG, and AVIF. The maximum image size allowed is 2 MB.
No, Dynamic Yield does not save any of the images uploaded by users. We encode the images into a base64 representation and search for similar-looking products. When the process is complete, we don’t save either the image or its base64 representation.