ブログ

AI-generated draft advice reduces supervisor workload and speeds inquiry responses.

1．Issue: Delayed responses due to backlog of requests for advice

2．Solution: AI-Generated Advice

To address this issue, the process owner has implemented an AI service step. At the same time, the prompts that the AI ​​uses to generate advice were set using a prompt generator.

This means that when a request for advice is made, a preliminary suggestion will be automatically generated by the AI, and the supervisor can refer to it when providing advice.

Supervisors’ workload is reduced as AI prepares draft advice for review and adjustment.

Before

View details of the workflow diagram

• Process triggered by email arrival
• 50-character summary by AI agent
  • Email content is summarized
• Draft response by AI agent
• 1.Create response document
  • Send reply email
  • Request review from supervisor
• 2.Advice
• Send email

After

View details of the workflow diagram

• Process triggered by email arrival
• 50-character summary by AI agent
  • Email content is summarized
• Draft response by AI agent
• 1.Create response document
  • Send reply email
  • Request review from supervisor
• Draft response by AI agent
• 2.Advice
• Send email

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

AI summarizes emails in subject lines so operators grasp inquiries quickly and respond faster.

1．Issue: Reading comprehension workload

2．Solution: Automatically summarize inquiry details in the subject line using generative AI

The process owner incorporated a step into the workflow in which the email body is automatically summarized using generative AI.

Upon receiving an email, the AI initially analyzes its content and produces a concise summary of about 50 characters. This summary is then displayed in the subject line of the “Offered” list. Consequently, respondents can grasp the main point of the inquiry by reading the summary before needing to open and examine the complete email.

Faster responses to inquiries by quickly identifying case details, enabling smoother handling.

Before

View details of the workflow diagram

• Process starts when email arrives
• 1.Enter reply
  • Send reply email
  • Request supervisor review
• 2.Review response
• Send email

After

View details of the workflow diagram

• Process starts when email arrives
• 50-character summary by OpenAI
  • The contents of the email are summarized
• 1.Enter reply
  • Send reply email
  • Request supervisor review
• 2.Review response
• Send email

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

AI analyzes and summarizes daily reports, highlighting issues and helping managers give timely feedback.

1. Issue: Insufficient feedback

2. Solution: Use AI to analyze the problem

The manager and process owner addressed the issue by enhancing the workflow. The improvement included incorporating an AI to summarize and analyze daily reports.

The summary and analysis are as follows:

1. Tasks: The tasks the staff members are working on
2. Content: Report on the progress and current status of the work
3. Points of Interest: AI Analysis
   • Explicit negative signs: Clearly expressed challenges or stagnation
   • Implicit negative signs: Indirect issues and concerns
   • Ambiguous next action: What staff should do next is unclear.
4. Suggested Advice: Example of an advice sentence for members

This feature arranges and presents to managers the issues identified in their subordinates’ daily reports.

Before

View details of the workflow diagram

• Start the process automatically at 7:00 AM
• 1x. Determine business day
  • If it is determined to be a holiday, the process branches and ends
• 1. Daily report input
• 2. Confirmation
  • Review the content and provide feedback
• 3. Resubmit (in case of return)
• 4. Feedback confirmation

After

View details of the workflow diagram

• Start the process automatically at 7:00 AM
• 1x. Determine business day
  • If it is determined to be a holiday, the process branches and ends
• 1. Daily report input
• 2x. AI summary & analysis
• 2. Confirmation
  • Review the content and provide feedback
• 3. Resubmit (in case of return)
• 4. Feedback confirmation

#{#q_daily_report}
--
Please summarize the daily report you entered above in bullet points.
In the following order: 1: Tasks, 2: Content, 3: Points of Interest, 4: Suggested Advice.
--
3: Please describe the Points of Interest when the following analysis A~C applies.
The item names should be: Explicit negative sign, Implicit negative sign, Ambiguous next action.
More than one is acceptable. If none, please indicate “None”.

Analysis method
--
A: Explicit Negative Sign: If the daily report clearly states the issue, please address this point.
E.g. Expressions such as "no progress" or "not started"

B: Implicit negative signs: If the contents of your daily report contain negative expressions that are not directly related to the issue, pick up on those points.
E.g. Expressions such as "It's taking a little time" and "It's taking a while."。

C: Ambiguous next action: Please pick up things where the next action or person is not clear.
E.g. “We will continue to respond tomorrow,” or other expressions lacking specific details.
--
4.For the Suggested Advice, please write 3: Suggested improvement advice for the Points of Interest.
3: If there are no points of interest, please write “None”.
–
Please output in Markdown format.
The Markdown format is as follows.

#### Business name
- Contents
- Contents
##### [For managers] Points of Interest
- 
##### [For managers] Suggested Advice
-
***

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

AI reviews call scripts objectively, improving consistency and quality.

1. Issue: Subjectivity in call script evaluation

The company provides sales support services and focuses on inside sales operations where sales operators call potential customers to set up appointments. The operators develop their individual call scripts, which are then reviewed by both themselves and their team leader.

However, the reliance on the reviewer’s experience and intuition resulted in a lack of clear evaluation criteria and objectivity. This made it challenging to utilize the reviews to enhance the script based on quantifiable data.

2. Solution: Introduce objective reviews with generative AI

To address this, the process owner implemented a system where a generative AI analyzes the script’s structure and phrasing after submission to determine if revisions are needed. The AI then clearly outlines any necessary changes.

The AI provides feedback, and the script writer reviews and resubmits the content if needed. The team leader then conducts a final check, ensuring a more objective and accurate review process.

AI ensures consistent document quality through standardized reviews, eliminating author-based variation.

Before

View workflow diagram details

1a. Update call script

Improve a call script already in use.

1b. Register new call script

Create a new call script.

x1. Assign ID

An ID will be automatically assigned to the call script.

x3-1. Set subject

The subject will be set automatically.

2. Check

The sales team leader will conduct the review.

1x. Revision

If the reader rejects the submission, the writer will revise the content and resubmit it.

x3-2. Add [Withdrawn] to the subject

The process will be terminated, and the subject will be automatically updated to “Withdrawal” if you cancel during the creation or modification of the call script.

After

View workflow diagram details

1a. Update call script

Improve your existing call script.

1b. Register new call script

Create a new call script.

x1. Assign ID

An ID will be automatically assigned to the call script.

x2-1.Generate prompt

Prompts are automatically generated based on your input.

x2-2. AI review

The AI reviews the call script based on the generated prompts.

x3-1. Set subject

The subject will be set automatically.

2. Check

The sales team leader will conduct the review.

1x. Revision

If the reader rejects the submission, the writer will revise the content and resubmit it.

x3-2. Add [Withdrawn] to the subject

The process will be terminated, and the subject will be automatically updated to “Withdrawal” if you cancel during the creation or modification of the call script.

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

Rotational task allocation balances operator workload and improves response speed.

1. Issue: A system that allows task avoidance

The contact center, staffed with 20 operators, handles email inquiries as part of its BPO outsourcing services.

Inquiries are handled by operators who take on the case themselves. When an operator is available, they select an inquiry from the waiting list and take it on.

Hourly paid operators are evaluated based on customer feedback. Positive evaluations are given for excellent service, while complaints result in negative evaluations.

Since the evaluation system doesn’t consider the number of cases handled, employees lack the motivation to take on cases proactively. This results in procrastination and a decline in overall productivity.

2. Solution: Rotate and allocate evenly

To address this, the process owner implemented a rotation allocation method. This new approach ensures inquiries are distributed equally, replacing the previous system where responders selected work voluntarily.

Each job is assigned a process serial number. The serial number is divided by 20, and the remainder plus 1 is used to assign the job to one of 20 operators. Each number between 1 and 20 corresponds to a specific operator. For example, Mr. E is assigned jobs numbered 5, Mr. N is assigned jobs numbered 14, and so on.

Workload is balanced among operators, improving response speed and reducing inquiry delays.

※ To calculate the number, use a Script Task

Before

View details of the workflow diagram

• Process started by receiving an email
• 50-character summary by OpenAI
  • The contents of the email are summarized
• 1. Enter your reply
  • Send a reply email
  • Request review from supervisor
• 2. Review the response
• Send email

After

View details of the workflow diagram

• Process started by receiving an email
• 50-character summary by OpenAI
  • The contents of the email are summarized
• Process serial number % 20 (remainder when divided by 20) + 1
• Update the TSV’s Nth line with the respondent’s information
• 1. Enter your reply
  • Send a reply email
  • Request review from supervisor
• 2. Review the response
• Send email

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