While Aissistant is highly capable, it may occasionally produce suboptimal responses. Consequently, we advise our customers to initiate their use of Aissistant in auto-draft mode. This allows them to monitor and refine Aissistant's performance, ensuring it aligns with the standards expected of a human agent.

Calibration Procedure

We recommend the following procedure to calibrate your Aissistant for full automation:

Categorize your customer queries
Turn on “Respond only to tagged” options in Smart Tagger
Develop a smart tag for one of your primary queries.
Populate the assets with relevant information and provide precise instructions associated with that tag.
Monitor how Aissistant handles events associated with that tag.
Adjust the assets, tag, and instructions as necessary for optimization.
After Aissistant consistently manages events in this category without any problems, return to step 3 and select a different category. Repeat the process until all categories are addressed efficiently.
Turn on auto-pilot

Calibration Examples

To illustrate the process, we'll use our customer Open Goaaal as a case study to demonstrate the step-by-step enhancement of Aissistant's responses. Open Goaaal operates a Shopify store specializing in the sale of soccer goals in various sizes.

From draft to auto reply

Calibration Procedure

Calibration Examples

Example 1: Add more information to improve answers

Example 2: Resolve conflicted information

Example 3: Handover to human team