AI automates thank-you messages, reducing staff workload and improving efficiency.
1. Issue: The Effort of Writing Thank You Notes for Visitors
A membership-based gym chain with 30 locations across Japan offers a successful free trial program that significantly contributes to new member acquisition. While member management is centralized, each branch handles free trial registration and management independently.
The Kyoto branch has implemented a unique workflow system that includes a web form for trial sign-ups and automated booking confirmation emails. After a free trial, reception staff ask visitors about their interest in joining. However, many attendees don’t commit on the spot and prefer to decide later. This makes sending a prompt thank you email crucial to keep their interest high.
It’s been observed that sending a personalized thank you email, including a message from the assigned trainer, on the same day as the trial has significantly improved visitor impression and led to an average 5% increase in membership conversion rates. The thank you email sending function is also integrated into the workflow system.
Despite its proven effectiveness, the current process of trainers individually crafting these thank you messages is time-consuming and labor-intensive, leading to increased overtime hours. Furthermore, this task presents a significant psychological burden for trainers who struggle with writing. Therefore, efficiency is urgently needed to maintain the positive impact on conversion rates without overworking staff.
2. Solution: Automating Thank You Message Generation with AI
The process owner will revamp the workflow to enable automatic thank you message generation using AI (ChatGPT).
Based on these inputs, the AI will automatically generate the thank you message. This change eliminates the need for trainers to compose messages themselves.
Automating thank-you messages reduces workload and stress for trainers, improving productivity and overall business efficiency.
Before
View details of the workflow diagram3.Membership Confirmation
We’ll confirm your membership after your trial session concludes today.
4.Post-Trial Thank You (If Membership is Pending)
The assigned trainer will enter feedback for the trial participant, limited to approximately 100 characters.
A thank-you email containing feedback from your assigned trainer will be sent to all visitors.
5.Delayed Membership Enrollment
Should a visitor express a desire to join at a later date, we’ll process their membership enrollment. (This option will automatically expire after a set period.)
Post-Trial Review
Trainers who provided the free trial will check the membership outcome (whether the visitor joined or not) and enter their reflections.
After
View details of the workflow diagram3.Membership Confirmation
We’ll confirm your membership after your trial session concludes today.
Keyword Entry (If Membership is Pending)
The assigned trainer will enter three keywords gathered from the visitor during the consultation.
AI will generate the thank-you message.Review Message
The reception staff will review the generated message and make minor wording adjustments.
A thank-you email containing feedback from your assigned trainer will be sent to all visitors.5.Delayed Membership Enrollment
Should a visitor express a desire to join at a later date, we’ll process their membership enrollment. (This option will automatically expire after a set period.)
Post-Trial Review
Trainers who provided the free trial will check the membership outcome (whether the visitor joined or not) and enter their reflections.
Automating risk workflows ensures all high-risk cases are addressed promptly, reducing missed actions and accelerating response times.
1. Issue: Slow Initial Responses
In a cloud-based company, every employee can keep track of each client’s usage. Specifically, the Usage Aggregation Process workflow app automatically posts usage graphs (Looker Studio reports) for each client to the internal chat tool, Collab Chat. On top of that, each graph comes with an account cancellation risk assessment generated by AI.
The Customer Success team manually initiates the Risk Action Process (risk response workflow) when risk mitigation is needed. However, with the recent increase in the number of clients, there have been instances where the Risk Action Process is not being initiated. The root cause of this is that team members are unsure how to make a decision. For example, time can pass while they consider that maybe no risk mitigation is necessary if they feel that there was a similar risk in the past.
2. Solution: Initiate Countermeasures Immediately Upon High-Risk Identification
The process owner changed their approach to initial risk response measures.
The new rule is to initiate the Risk Action Process for all high-risk assessments, meaning risk countermeasures will be considered within the Risk Action Process. Even if a risk was previously addressed or is currently being handled, any usage graph data (client data) determined to be high-risk will now be passed to the Risk Action Process. Within this process, the risk control policy will then be decided.
Specifically, an automated step to launch the Risk Action Process was added downstream in the workflow diagram.
This process improvement ensures that all client data identified as high-risk by either the AI-generated system or human assessment is automatically passed to the Risk Action Process. Additionally, a new option, “5. Previously Addressed / Currently Being Handled”, was added to the Risk Control Policy management item within the downstream Risk Action Process.
1. Risk Avoidance
2. Risk Reduction
3. Risk Sharing
4. Risk Retention
5. Previously Addressed / Currently Being Handled
Automated risk processes eliminate missed cases and enable faster responses to cancellation risks.
AI now auto-assigns responders to inquiry emails, reducing workload and improving efficiency.
1. Issue: Selecting Call Handlers is Time-consuming
There is a company that offers a wide range of office essentials, including copiers and printers.The company utilizes a Representative Phone Answering Service where professional external operators handle phone calls as if they were in-house employees. They then report the call’s content via email. This service ensures a courteous initial response that only professionals can provide.
Recently, an AI-generated system was integrated into their call answering operations to automatically classify the priority of these report emails. This new system automatically notifies the management department when a report email requiring urgent attention arrives, thereby reducing the risk of delays in responding to inquiries.
Upon receiving these notifications, the Management Department assigns responders based on the priority of the report emails, starting with the most urgent. However, they ultimately need to allocate responders for all inquiry resolution emails, which results in a significant workload.
Currently, we’re managing within our capacity. However, we anticipate an increase in projects due to business expansion, which raises concerns about an even heavier workload. If this burden continues to grow, it risks interfering with other crucial operations.
While the current workload is manageable, the company anticipates an increase in cases due to business expansion, raising concerns about an even greater burden. If this burden continues to grow, there’s a risk it could disrupt other critical operations.
2. Solution: Automating Responder Selection with AI
To address these issues, the process owner integrated an AI-generated system into their workflow to automatically assign responders. Specifically, the AI analyzes the content of report emails and selects the most suitable responder from a prepared list. Following this, the selected responder is automatically set as the processor for the Record Response Outcome step.
This new system automates the entire process, from the arrival of an operator’s email regarding an important call to the assignment of the Record Response Outcome step to an internal team member. As a result, the management department no longer needs to manually select responders for critical calls, minimizing the impact on other operations as the business expands. Ultimately, this enables efficient and low-burden operations.
Automating responder selection reduces manual work for management, allowing them to focus on more important tasks.
Before
View details of the workflow diagram
x1. Retrieve Email Content
When an email with the label “Phone” arrives in Gmail, its content is read.
x2. Urgency Assessment by AI
The AI analyzes the email content to determine if it’s a sales solicitation. The result is then assigned to the data field “Judgment Result”, if it’s a sales pitch, it’s set to “not important”; otherwise, it’s set to “important.”
g1. AI Judgment Result
The workflow path is selected based on the value in the Judgment Result data field, as follows:
If the Judgment Result is “not important,” the workflow proceeds to the “1. Assign Responder” step.
If the Judgment Result is “important,” the workflow proceeds to the “m1. Urgent Action Request” email sending event (which is technically referred to as a Throwing Message Intermediate Event).
m1. Urgent Action Request
An email is sent to the management department members, prompting them to accept and process the “1. Assign Responder” step.
1. Assign Responder
A member of the management department determines the “responder” based on the email’s content.
2. Record Response Outcome
The assigned responder reviews the email content and records how the inquiry was handled.
After
View details of the workflow diagram
x1. Retrieve Email Content
When an email with the label “Phone” arrives in Gmail, its content is read.
x2. Urgency Assessment by AI
The AI analyzes the email content to determine if it’s a sales solicitation. The result is then assigned to the data field “Judgment Result”, if it’s a sales pitch, it’s set to “not important”; otherwise, it’s set to “important”.
x3. Responder Selection by AI
The AI analyzes the email content and selects the appropriate responder (their email address) from a prepared list of contacts.
x4. Setting the Responder
Based on the responder’s email address selected in the “3. Responder Selection by AI” automated process, the handler for the “2. Record Response Outcome” step is set.
g1. AI Judgment Result
The workflow path is selected based on the value in the Judgment Result data field, as follows:
If the Judgment Result is “not important,” the workflow proceeds to the “1. Assign Responder” step.
If the Judgment Result is “important,” the workflow proceeds to the “m1. Urgent Action Request” email sending event (which is technically referred to as a Throwing Message Intermediate Event).
m1. Urgent Action Request
An email is sent to the management department members, prompting them to accept and process the “1. Assign Responder” step.
1. Assign Responder
A member of the management department determines the “responder” based on the email’s content.
2. Record Response Outcome
The assigned responder reviews the email content and records how the inquiry was handled.
AI filters inquiry emails, separating spam from real leads for faster response.
1. Issue: Delayed Response to Inquiries
A comprehensive provider of office essentials such as copiers and printers has significantly streamlined its inquiry management process. The company utilizes a representative telephone answering service, where professional external operators handle incoming calls on behalf of employees and report the contents of the calls by email. This not only reduces the burden of initial call handling for staff but also ensures a polite and professional first point of contact for callers.
Recently, the company implemented an automated system that integrates report emails from the answering service directly into its workflow system.This crucial enhancement plays a vital role in preventing missed inquiries and ensures that all communications are tracked and addressed efficiently.
Despite these improvements, the company now faces a new challenge: more than half of the automatically imported report emails are sales solicitations. This creates a significant problem where genuine inquiries from potential customers get buried amidst the spam.
As a direct result, the company is unable to respond promptly to valuable leads, leading to a serious risk of missing out on crucial business opportunities.
2. Solution: AI-Powered Urgency Assessment
The process owner has successfully integrated an AI-powered automatic classification system into their workflow for handling report emails.
Specifically, as soon as a report email enters the workflow system, an automated AI step analyzes its content and classifies it as either a sales solicitation or not. Based on this classification, the processing path automatically diverges.
With this setup, “report emails” identified as sales solicitations are categorized as not important. Conversely, all other emails are classified as important. Furthermore, whenever an email is classified as important, a notification email is automatically sent to the relevant administrative department, prompting their immediate attention.
Before
View details of the workflow diagram
x1. Retrieve Email Content
When an email with the label “Phone” arrives in Gmail, its content is read.
1. Assign Responder
A member of the management department determines the “responder” based on the email’s content.
2. Record Response Outcome
The assigned responder reviews the email content and records how the inquiry was handled.
After
View details of the workflow diagram
x1. Retrieve Email Content
When an email with the label “Phone” arrives in Gmail, its content is read.
x2. Urgency Assessment by AI
The AI analyzes the email content to determine if it’s a sales solicitation. The result is then assigned to the data field “Judgment Result”, if it’s a sales pitch, it’s set to “not important”; otherwise, it’s set to “important.”
g1. AI Judgment Result
The workflow path is selected based on the value in the Judgment Result data field, as follows:
If the Judgment Result is “not important”, the workflow proceeds to the “1. Assign Responder” step
If the Judgment Result is “important,” the workflow proceeds to the “m1. Urgent Action Request” email sending event (which is technically referred to as a Throwing Message Intermediate Event).
m1. Urgent Action Request
An email is sent to the management department members, prompting them to accept and process the “1. Assign Responder” step.
1. Assign Responder
A member of the management department determines the responder based on the email’s content.
2. Record Response Outcome
The assigned responder reviews the email content and records how the inquiry was handled.
Human labeling of high-risk AI outputs improves prediction accuracy, reduces misjudgment, and enables continuous AI optimization.
1. Issue: Insufficient Verification of Prediction Accuracy
A company providing cloud services has a system that ensures all employees can understand the usage status of each contracted company. This widespread access to customer usage data promotes transparency and likely supports better decision-making across the organization.
This company has a robust system in place for sharing customer usage data company-wide. Every week, Looker Studio graphs detailing each contracted company’s usage are automatically posted to OpenChat. What’s more, these posts include a multimodal generative AI’s churn rate risk assessment, rated on a scale of A to E.
This system helps teams like Customer Success prioritize checking high-risk customers’ usage to devise churn rate reduction strategies. Similarly, the Field Sales team uses it to propose additional services to loyal, low-risk clients.
However, a critical issue remains: the AI’s risk assessment accuracy isn’t sufficiently verified. There’s a perceived misjudgment rate of about 30%. To prepare for future business expansion, it’s crucial to gradually establish a framework to improve the AI’s prediction accuracy.
2. Solution: Diligent Data Labeling
The process owner has decided on a clear initial strategy: human data labeling will first be applied to high-risk (D-E) assessments.
* “Data labeling” is the process where humans identify and add information to various forms of data. For example, this could involve determining if a photo contains a horse, if a video includes footage of a fire, or if a spot on an X-ray image is a tumor. This labeled data is indispensable for training artificial intelligence models.
To improve the validation of AI-driven risk assessments, this company has refined its workflow. Here’s a breakdown of the key changes:
New Workflow Adjustments: – Added an OR Gateway for Branching: High-risk assessment reports are now concurrently routed to multiple paths. – Automated Subject Line Modification: Reports automatically receive a “Risk_” label in their subject line. – Introduced Human Review Step: A new human task allows for “agree” (Risk) or “disagree” (no risk) judgments on the AI’s high-risk assessment. – Automated Subject Line Modification for Disagreements: Reports flagged as “disagree” automatically get a “Wolf_Risk_” label (indicating a false alarm or “wolf in sheep’s clothing” risk).
To these enhancements, every high-risk assessment report now carries either a “Risk_” or “Wolf_Risk_” label. This critical improvement empowers all employees to validate the generative AI’s prediction accuracy (and its misjudgment rate), fostering transparency and accountability in the AI’s performance.
Analyzing and labeling AI errors improves prediction accuracy while enabling continuous prompt optimization.
* Data labeling is the essential process where human
AI randomly assigns inquiries to balance workload and improve team morale.
1. Issue: Uneven Task Assignment
An IT company uses Augmented Reality (AR) technology to deliver interactive services for education and training. To handle customer inquiries related to their cloud services, the company has a dedicated team made up of one leader and five members. Customers submit their inquiries through a web form, and the team responds via email.
However, the current task assignment system for inquiry responses has become uneven, leading to a sense of unfairness within the team. Members who are assigned a heavier workload complain of being overburdened, while those with fewer assignments express anxiety about not being trusted. This imbalance is creating a negative impact on team morale and overall efficiency.
This sense of unfairness can lead to serious team operational problems. It risks lowering team members’ motivation, decreasing productivity, and increasing the risk of staff turnover. Therefore, it’s urgent to implement measures to address and eliminate this unfairness.
2. Solution: AI-Powered Random Assignment
The team leader, the process owner, realized they were unconsciously assigning a disproportionate number of tasks to veteran members who appeared more experienced and available.
To address this, they’ve decided to eliminate the manual “1. Assign Responder” step, previously handled by the leader. In its place, a new, AI-driven process has been introduced.
Under this new process, “x1. Select Responder by AI,” the AI will randomly choose one email address from the five team members. The member associated with the selected email address will then be automatically set as the responder for the “2. Draft Response” step in the subsequent “x2. Set Responder” stage.
Before
View details of the workflow diagram
s1. Inquiry Reception
The customer initiates an inquiry by filling out a web form, providing their email address and the details of their question.
1. Assign Responder
The team leader decides which member will be responsible for drafting the response to the inquiry.
2. Draft Response
The member chosen in the “Assign Responder” step creates the draft response to the customer’s inquiry.
3. Review
The drafted response from the “Draft Response” step is reviewed. This likely involves checking for accuracy, completeness, tone, and adherence to company guidelines.
2′. Rework Response
If issues are identified during the “Review” step, the response is sent back for revisions based on the feedback.
m1. Send Response
Once the response is finalized (after review and any necessary rework), an email containing the answer is sent to the email address the customer provided in the inquiry form.
After
View details of the workflow diagram
s1. Inquiry Reception
The customer initiates an inquiry by filling out a web form, providing their email address and the details of their question.
x1. Select Responder by AI
From the five team members’ email addresses, the AI randomly selects one. This is the core of the new fairness initiative, removing manual bias from the assignment.
x2. Set Responder
The member corresponding to the email address chosen in “x1. Select Responder by AI” is automatically set as the processor for the “2. Draft Response” step. This ensures a seamless transition from AI selection to task execution.
2. Draft Response
The member chosen in the “Assign Responder” step creates the draft response to the customer’s inquiry.
3. Review
The drafted response from the “Draft Response” step is reviewed. This likely involves checking for accuracy, completeness, tone, and adherence to company guidelines.
2′. Rework Response
If issues are identified during the “Review” step, the response is sent back for revisions based on the feedback.
m1. Send Response
Once the response is finalized (after review and any necessary rework), an email containing the answer is sent to the email address the customer provided in the inquiry form.
Create opportunities for reporters to self-identify discrepancies in their past timecard data.
1. Issue: Mistakes in Timecard Entries
SharaShara Systems is a company that specializes in custom system development for businesses. Employee payroll is calculated based on attendance data. If there are any discrepancies in this data, it directly leads to errors in salary payments. Therefore, the administration department rigorously checks the content to ensure accuracy.
However, as SharaShara Systems is in a growth phase, the number of employees has increased, leading to a rapid surge in the volume of attendance reports that need checking. As a result, the number of errors discovered is also trending upwards. Furthermore, with active new hiring, both the quantity of attendance reports and the incidence of errors are expected to continue rising in the future.
Overlooking attendance discrepancies significantly increases the risk of incorrect wage payments, which can severely damage a company’s credibility and brand value. Therefore, it’s crucial to implement concrete measures immediately to mitigate this risk.
2. Solution: Automatically extract reports from the past 14 days
The process owner determined it was crucial for employees to identify attendance reporting errors themselves at an early stage. To achieve this, a step was added to the workflow, automatically extracting attendance report data from the past 14 days before employees submit their clock-in times.
Now, every day, when employees access the screen to report their clock-in time, the past 14 days of their attendance data will be displayed.
Before
View details of the workflow diagram
s1. Weekday 7:00 AM (Timer Start Event)
The flow automatically starts for all employees every weekday at 7:00 AM.
1. Report Clock-In Time
Employees enter their clock-in time when they begin work.
x1. “Working” Status
The “Attendance Status” data field is set to “Working.”
2. Report Clock-Out Time
Employees enter their break time and clock-out time when they finish work. Their work hours are automatically calculated.
x2. “Work Finished” Status
The “Attendance Status” data field is set to “Work Finished.”
x4. Clock-In/Out Data AI Evaluation
AI evaluates the clock-in/out data and outputs the evaluation results.
3. Confirm Work Hours
The employee’s supervisor reviews the employee’s reported clock-in time, break time, clock-out time, and work hours.
They can also view the AI-generated evaluation results from “x4. Clock-In/Out Data AI Evaluation.”
2x. Handle Revisions
Employees review the reason for the revision and correct their clock-in time, break time, and clock-out time.
x3. “Leave” Status
The “Attendance Status” data field is set to “Leave.”
After
View details of the workflow diagram
s1. Weekday 7:00 AM (Timer Start Event)
The flow automatically starts for all employees every weekday at 7:00 AM.
x5. Extract All Employee Attendance Data
Attendance report data for all employees from the past 14 days is automatically extracted.
x6. Extract Applicant’s Attendance Data
From the data extracted in “x5. Extract All Employee Attendance Data,” only the applicant’s data is automatically extracted.
x7. Process Attendance Data 1
Unnecessary data is automatically deleted from the data extracted in “x6. Extract Applicant’s Attendance Data.”
x8. Process Attendance Data 2
The data processed in “x7. Process Attendance Data 1” is converted into Markdown format.
1. Report Clock-In Time
Employees enter their clock-in time when they begin work.
x1. “Working” Status
The “Attendance Status” data field is set to “Working.”
2. Report Clock-Out Time
Employees enter their break time and clock-out time when they finish work. Their work hours are automatically calculated.
x2. “Work Finished” Status
The “Attendance Status” data field is set to “Work Finished.”
x4. Clock-In/Out Data AI Evaluation
AI evaluates the clock-in/out data and outputs the evaluation results.
3. Confirm Work Hours
The employee’s supervisor reviews the employee’s reported clock-in time, break time, clock-out time, and work hours. They can also view the AI-generated evaluation results from “x4. Clock-In/Out Data AI Evaluation.”
2x. Handle Revisions
Employees review the reason for the revision and correct their clock-in time, break time, and clock-out time.
x3. “Leave” Status
The “Attendance Status” data field is set to “Leave.”
Compare Before/After
3. Benefits
Improved Payroll Accuracy
By automatically extracting 14 days of past attendance data, employees can now easily spot errors in their own time reports. This boosts the accuracy of attendance reporting, which in turn reduces payroll errors. As a result, you’ll see fewer incorrect salary payments and a lighter workload for the accounting department.
Protected Company Credibility and Brand Value
Incorrect salary payments are a direct hit to a company’s credibility. By reducing these errors, you can proactively prevent trust issues and safeguard your brand value.
Enhanced Employee Self-Management
Regularly reviewing their own attendance data helps employees develop a stronger sense of self-management. This reinforces attendance discipline, which is expected to lead to an overall improvement in attendance rates and productivity.
4. Other Business Applications
The mechanism of automatically extracting past work performance data and enabling it to be used to perform tasks can be applied to the following business operations:
Customer Support
Automatically pulling up past inquiry histories makes it easier to understand a customer’s previous issues and interests. This allows for more accurate and personalized support, potentially leading to higher customer satisfaction.
Information Security Management
Regularly checking and reporting on system account registration becomes even more efficient by referencing past report histories. Looking at this history helps you clearly identify differences from previous reports, enabling a quicker response if any improper registrations occur.
Expense Management
When making purchase requests for items within your department, you’ll be able to refer to past expense usage. This helps you understand the current budget consumption, making it easier to decide if a purchase is necessary or which items to choose.
