Overview
Customers don’t always put what they want into words; sometimes they send a photo, a screenshot, or a half-finished sentence. Using Google’s Gemini models, MHS Links AI makes sense of both text and images and grasps the question correctly.
Gemini’s contribution is on the understanding side: what the request is, what the customer needs, what the image shows. The content of the answer, however, comes only from the information your business has uploaded: when the assistant doesn’t know something, it doesn’t make it up, and hands the conversation over to your team instead.
What You Can Do
Strong Language Understanding
Even in short, messy, or casually written messages, the assistant picks up the core of the request.
Image Analysis
Photos and screenshots that customers send are interpreted, so the question is understood correctly and routed to the right place.
Knowledge-Based Answers
Answers are based only on the information you upload; the assistant doesn’t guess about things it doesn’t know.
Multilingual Understanding
Customers can write in any of more than 95 languages, and the assistant replies in the same language.
Setup Steps
- 01
Describe Your Use Case
On the setup call, we look together at the kinds of messages and images your customers send.
- 02
Leave the Model Settings to Our Team
Our team handles model selection and settings; no technical steps are required from you.
- 03
Prepare the Knowledge Source
Your services, prices, and frequently asked questions are added to the assistant’s knowledge source.
- 04
Test and Go Live
Answers are checked with sample messages and images; once you approve, the assistant goes live.
Requirements
- Your service, pricing, and FAQ information
- Examples of the types of images your customers often send
- Topics you want the assistant to hand over to your team
Data and Security
- The assistant answers only from the information you upload. When it doesn’t know something, it doesn’t make things up; it hands the conversation to your team.
- Image analysis is used to understand the context of the question; the content of the answer still comes from your information.
For details, see our Privacy Policy.
Which Plans Include It?
This integration is planned as part of your setup, based on your needs. We’ll work out together during setup which plan it’s added to and how.
Write to usFrequently Asked Questions
It interprets the image to understand what the customer is asking, then answers based on the information you’ve uploaded or routes the conversation to the right person.
No. The assistant uses the image to understand the context of the question; assessments that require expertise are passed to your team.
Each model has its own strengths; Gemini is especially strong at language understanding and image analysis. Our team determines the best configuration for your business during setup.