Close



Frequently Asked Questions



Frequently Asked Questions

Clients



Clients

Users



Users

Insights



Insights

Insight | Google Search Console

Google Search Console

Insight | Google Business Profile

Google Business Profile

Insight | Google Ads

Google Ads

Insight | Google Analytics

Google Analytics

Insight | Website

Website

Insight | Facebook Ads

Facebook Ads

Insight | Microsoft Ads

Microsoft Ads

Automation Jobs



Automation Jobs

Automation | Google Search Console

Google Search Console

Automation | Google Business Profile

Google Business Profile

Automation | Google Ads

Google Ads

Automation | Google Analytics

Google Analytics

Automation | Website

Website

Automation | Facebook Ads

Facebook Ads

Automation | Microsoft Ads

Microsoft Ads

KPI Management



KPI Management

KPI Management | Google Analytics

Google Analytics

KPI Management | Google Ads

Google Ads

KPI Management | Google Business Profile

Google Business Profile

KPI Management | Facebook Ads

Facebook Ads

KPI Management | Microsoft Ads

Microsoft Ads

KPI Management | Google Sheets

Google Sheets

Budget Tracking



Budget Tracking

Budget Tracking | Google Sheets

Google Sheets

Anomaly Detection



Anomaly Detection

Data Warehouse



Data Warehouse

Data Warehouse | Google Looker Studio

Google Looker Studio

Data Warehouse | BigQuery

Google BigQuery

Data Warehouse | Google Business Profile

Google Business Profile (Formerly Google My Business)

Data Warehouse | Google Search Console

Google Search Console

Data Warehouse | Facebook Ads

Facebook Ads

Local Listings



Local Listings

Reviews



Reviews

Settings



Settings

Integrations



Integrations

Integrations | Google Looker Studio

Google Looker Studio

Integrations | Slack

Slack

Integrations | Zapier

Zapier

Integrations | Make

Make

Integrations | Webhook

Webhook

Comments



Comments

Comments | Slack

Slack

Extensions



Extension

Extension | Explorer

Branch Explorer

Recent Updates



Account Settings

Settings

Acknowledging and Resolving Insights

Insights

Add comment from Slack

Comments | Slack

Adding a User

Users

An overview of Local Listings

Local Listings

An overview of Reviews

Reviews

Analysis

Anomalies Bulk Action

Anomaly Detection

Anomaly Algorithm

Anomaly Detection

Integrations | Webhook

Anomaly Detection Insight

Insights

Anomaly Detection Settings

Anomaly Detection

Anomaly Job Common Errors

Anomaly Detection

Attributes

Local Listings

Authentication

Integrations | Make

Auto Resolving

Insights

Automatic Schema Updates

Data Warehouse

Automation Job Common Errors

Automation Jobs

Automation: Facebook Ads Destination URL Checker

Integrations | Webhook

Automation: Google Ads Change History

Integrations | Webhook

Automation: Google Ads Destination URL Checker

Integrations | Webhook

Automation: Google Analytics Change History

Integrations | Webhook

Automation: Google Business Profile Answer

Integrations | Webhook

Automation: Google Business Profile Change History

Integrations | Webhook

Automation: Google Business Profile Pending Updates

Integrations | Webhook

Automation: Google Business Profile Question

Integrations | Webhook

Automation: Google Review

Integrations | Webhook

Automation: Google Review Change History

Integrations | Webhook

Automation: Microsoft Ads Destination URL Checker

Integrations | Webhook

Automation: Page Status Checker

Integrations | Webhook

Automation: Robots.txt Change Detection

Integrations | Webhook

Automation: Search Console Activity

Integrations | Webhook

Automation: Search Console Keyword Movement

Integrations | Webhook

Automations Bulk Action

Automation Jobs

Budget Campaign Dynamic Filter

Budget Tracking

Budget Tracking

Budget Tracking

Budget Tracking

Integrations | Webhook

Budget Tracking

Budget Tracking

Local Listings

Local Listings | Media

Calendar

Social Posts

Cancel Subscription

Settings

Review Reply AI Models

‍
‍

Personalities

While crafting a review response, you can select from a number of different Personalities.

Personalities shape the response's overall tone, giving you another way to personalise it and align your responses better with your brand voice. You can change Personalities by selecting them from the Personality dropdown in the top right corner of the reply generator.

Our reply generator interface, which displays the current Model and Personality, and the generated reply.

We offer the following Personalities for both models:

- Professional: The default Personality. When selected, the model will reply with a professional tone, avoiding more casual or bubbly sounding responses.
- Upbeat: When selected, the model will reply with a more casual and energetic tone.
- Neutral: When selected, the model will try to balance casual and professional, resulting in a more down-to-earth response.

‍

Model Selection

Our platform offers a choice of two different models when generating review responses:

Fundamental

This model strikes a balance between speed and creativity when generating replies. It's designed to quickly produce suitable responses, and it doesn't take into account your previous replies.

Strengths: The Fundamental model focuses on producing replies quickly, so it's great for responding to simple reviews in bulk.

Weaknesses: As this model doesn't use your previous replies as a basis for its own, it will guess at the most suitable response style based on your Personality selection.

Advanced

This sophisticated model employs Retrieval-Augmented Generation (RAG) to create highly personalized responses. It leverages your existing review replies to generate content that is finely tuned to your brand voice and communication style.

Strengths: The Advanced model is broad in its capabilities, and will craft its response to match the structure, brand voice, and tone of your previous review replies, whilst still applying your Personality selection. It also tends to be more open and creative than the Fundamental model in its responses.

Weaknesses: This model needs to compile and read over existing responses in your account before formulating its own, meaning it "thinks" for longer, resulting in longer generation times.

The choice between these models depends upon your subscription plan and specific needs for review management. Both aim to streamline your response process while maintaining a personal touch in your customer communications.

‍

What is RAG?

Our Advanced AI model uses Retrieval-Augmented Generation (RAG), a technique that allows us to use your existing reviews and their replies to craft custom responses. RAG makes use of embeddings, which are numerical representations of a text's meaning, to search for similar reviews and provide them as examples to the model. This helps the model build an understanding of how previous replies are structured, and guides the response, adding to the brand voice that the model uses when crafting the review reply.

As an example, let's say customer A submits a review about a glass vase. If customer B does the same at a later date, the embeddings for both of those reviews would produce a similar number to one another - they would be in what we call proximity - and therefore be related to each other. Our RAG process then captures this relationship, and provides to our model customer A's review, and its reply, as an example of how to respond.

*Advanced AI Model logic flow, with the skipped steps shown for the fundamental model.*

‍

Was this article helpful?



Nice one!

Thanks a lot for your feedback! If you’d like a member of our support team to respond to you, please send a message here



Please try again

Oops! Something went wrong while submitting the form.



Nice one!

Thanks a lot for your feedback! If you’d like a member of our support team to respond to you, please send a message here



Please try again

Oops! Something went wrong while submitting the form.

Help Center

Review Reply AI Models

Personalities

Model Selection

Fundamental

Advanced

What is RAG?