ブログ

AI reviews request content and suggests improvements to help applicants draft better requests.

1. Issue: Unable to select a consultant on the web form

A BPO provider specializing in online inquiry support with a dedicated team of 30 operators. They receive online consultation requests through a web form, and a designated operator notifies the client of the schedule on the same day.

However, the company received frequent requests from repeat customers who wanted to book with the same operator they had previously consulted with. The web form lacked a function to specify an operator, which became a source of dissatisfaction.

On the other hand, simply adding a designation feature would require publicly sharing operators’ names and contact information, which was difficult to implement due to personal information protection concerns. Therefore, there was a need for a system that could flexibly accommodate customer requests while ensuring a secure assignment process.

2. Solution: AI-powered automatic assignment of a contact person

The process owner added a field to the web form where customers could input their preferred operator’s name or email address. An AI system then cross-references this input with internal company data and automatically assigns the most relevant operator.

This setup allows customers to communicate their preferences while ensuring that the operator’s personal information is not disclosed externally.

Matching clients with preferred consultants boosts trust, security, and overall satisfaction.

Before

View details of the workflow diagram

The process starts upon submission of the web form.

Automated acknowledgment generation

Create a confirmation record for the submitted content.

Thank-you message generation

The AI process creates an automated reply email with an acknowledgment message.

Send a confirmation email

Send the created email.

Operator email setup

Notify the assigned operator.

Edit notifications

The assigned operator drafts the notification.

Notification email

The reply email created by the operator is sent to the client.

No Response

It is processed if the operator determines a reply is not needed.

After

View details of the workflow diagram

The process starts upon submission of the web form.

Automated acknowledgment generation

Create a confirmation record for the submitted content.

Thank-you message generation

The AI process creates an automated reply email with an acknowledgment message.

Send a confirmation email

Send the created email.

Operator email setup

Notify the assigned operator.

Customer emails → Custom domains

If the request from the client includes information about a preferred operator, the AI will use this data to automatically assign the most relevant one.

Edit notifications

The assigned operator drafts the notification.

Notification email

The reply email created by the operator is sent to the client.

No Response

It is processed if the operator determines a reply is not needed.

3. Customers Case Study

Honda Motor Co., Ltd.

Used for Company-wide Approval Flows such as general affairs applications, training recepti…

View More

Subaru Corporation

In automobile development, an environment to simulate performance and reliability was estab…

View More

MITSUBISHI PENCIL CO., LTD.

Moving Complex Business that had been processed by Notes to the cloud workflow. Approximate…

View More

4. Other Business Applications

We will enable AI-based reviews for the following tasks:

5. Related Posts

AI analysis of surveys ensures objective proposals, speeding up negotiations and sales efficiency.

1. Issue: Misguided Proposals Based on Subjective Judgment

As an IT service sales partner, the agency engages prospects through targeted email proposals to drive new business negotiations.

To gauge dissatisfaction and identify areas for improvement regarding these proposals, they also send a survey consisting of a 5-point rating scale and open-ended comments.

Interpreting survey responses has been highly subjective, leading to inconsistent evaluations by sales representatives. This often results in certain comments being either downplayed or overly emphasized.

Consequently, customer feedback is frequently misrepresented in subsequent proposals, leading to a mismatch with customer expectations. This necessitates numerous proposals to be made before advancing to the consideration phase.

2. Solution: AI-based Survey Response Analysis

To solve this problem, the process owner incorporated generative AI (ChatGPT) into the proposal distribution flow.

Customer surveys (5-point rating and free-form comments) are automatically analyzed by AI, and areas for improvement and next sales actions are suggested.

In addition, an objective satisfaction rating (1-5) is now calculated based on these ratings and comments.

This enables salesrepresentatives to objectively consider their next proposal.

Reduced proposal volume accelerated negotiations, directly enhancing sales efficiency.

Before

View details of the workflow diagram

0.Manual start / HTTP start

Manual start, or start via HTTP request from an external system.

q_key

A Key is set for each survey.

Canceling the investigation

The investigation will be canceled if there are any input deficiencies, such as the sales representative’s name being blank.

email

Satisfacton survey request emails will be sent.

Satisfaction Survey FORM

An answer form for the survey is issued based on the evaluation chosen by the customer, and the customer is asked for comments.

Satisfaction 1=5

The star rating is converted into a numerical value. For example, two stars (★★) becomes “2”.

postGoogleChat

Responses to the questionnaire will be posted to Google Chat.

After

View details of the workflow diagram

0.Manual start / HTTP start

Manual start, or start via HTTP request from an external system.

q_key

A Key is set for each survey.

Canceling the investigation

The investigation will be canceled if there are any input deficiencies, such as the sales representative’s name being blank.

email

Satisfacton survey request emails will be sent.

Satisfaction Survey FORM

An answer form for the survey is issued based on the evaluation chosen by the customer, and the customer is asked for comments.

Satisfaction 1=5

The star rating is converted into a numerical value. For example, two stars (★★) becomes “2”.

AI evaluation prompt

The contents of the survey response are inserted into a prompt for analysis instructions, and then formatted.

AI evaluation(ChatGPT)

The formatted prompt is passed to the AI (ChatGPT), which analyzes the following:

Calculation of overall satisfaction (1-5)/Extraction of key issues and requests/Suggestion of the next sales action

postGoogleChat

Responses to the questionnaire will be posted to Google Chat.

3. Customers Case Study

Honda Motor Co., Ltd.

Used for Company-wide Approval Flows such as general affairs applications, training recepti…

View More

Toho Gas Network Co., Ltd. (Negotiation and Design Section)

500 Applications Per Month Completely Digitized! Reduced Labour and Eliminated Printing and…

View More

MITSUBISHI PENCIL CO., LTD.

Moving Complex Business that had been processed by Notes to the cloud workflow. Approximate…

View More

4. Other Business Applications

We will enable AI-based reviews for the following tasks:

5. Related Posts