Questetra BPM Suite

ブログ

  • When AI Struggles, Human Judgment Provides the Solution

    When AI Struggles, Human Judgment Provides the Solution

    Prompt changes stop AI misrouting vague emails, routing them to staff review and improving response speed.

    1. Issue: Errors in AI-Driven Respondent Selection

    A trading company handles a wide array of office essentials, including copy machines and printers. To streamline their office phone reception, the company adopted a call answering service. Calls to their main number are handled by an operator, and the outcomes are shared with the administration department via email. An AI-powered system has been integrated to further enhance efficiency by prioritizing calls and selecting appropriate respondents.

    However, this system presents a persistent challenge. When operator-generated emails are addressed to a vague recipient address such as “To Support Staff” or “To HR Department,” the AI attempts to force-select a respondent from its list of respondents.

    This often results in response requests being misdirected to entirely unrelated individuals. Crucially, when the AI incorrectly selects a respondent for a critical inquiry, it can significantly delay the request from reaching the appropriate person, leading to slow response times.

    While a certain degree of AI error is unavoidable, there is a clear demand for improvements to prevent the occurrence of unnecessary operational burdens.

    2. Solution: Modifying the AI Prompt to Output “No Respondent”

    To mitigate erroneous AI-driven respondent selection, the process owner modified the AI’s prompt. Specifically, when an email from an operator contains a vague recipient designation like “To [Department] Staff”, the AI is now configured to output a hyphen (“-“), signifying that there is no respondent, rather than attempting to select a candidate from the list of respondents.

    Furthermore, a mechanism has been implemented to automatically branch to the “1. Respondent Determination” step whenever the AI outputs a hyphen. This configuration ensures that emails with ambiguous recipient designations, particularly those containing critical inquiries, are automatically routed to a member of the administration department to manually select the respondent.

    Preventing incorrect AI judgments in ambiguous cases shortens staff identification time and improves customer response speed.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    x1. Acquire Email Content

    Upon receipt of an email with the “phone” label in Gmail, its content is read.

    x2. Importance Assessment by AI

    The AI analyzes the email content to determine if it is a sales inquiry. The data item “Judgment Result” is set to “not important” for sales inquiries and “important” otherwise.

    x3. Acquire Respondent List

    User information registered in the workflow platform (Respondent List) is retrieved.

    x4. Respondent Determination by AI

    The AI analyzes the email content and selects a respondent (email address) from the Respondent List obtained in “x3. Acquire Respondent List.”

    x5. Set Respondent

    Based on the respondent (email address) selected in the “x4. Respondent Determination by AI” automated process, the handler for the “2. Record Response Outcome” process is set.

    g1. AI Judgment Result

    The path is selected based on the value of the “Judgment Result” data item:
    – If “not important”, proceed to “1. Respondent Determination”.
    – If “important”, proceed to the email transmission event (“m1. Urgent Response Request”).

    m1. Urgent Response Request

    An email is sent to administration department members and the respondent determined in “x3. Respondent Determination by AI”, prompting them to handle the “2. Record Response Outcome” process.

    1. Respondent Determination

    An administration department member determines the “Respondent” based on the email content. The respondent determined in “x4. Respondent Determination by AI” is pre-filled.

    2. Record Response Outcome

    The respondent reviews the email content and records how the inquiry was handled.

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    x1. Acquire Email Content

    Upon receipt of an email with the “phone” label in Gmail, its content is read.

    x2. Importance Assessment by AI

    The AI analyzes the email content to determine if it is a sales inquiry. The data item “Judgment Result” is set to “not important” for sales inquiries and “important” otherwise.

    x3. Acquire Respondent List

    User information registered in the workflow platform (Respondent List) is retrieved.

    x4. Respondent Determination by AI

    The AI analyzes the email content and selects a respondent (email address) from the Respondent List obtained in “x3. Acquire Respondent List.”

    x5. Set Respondent

    Based on the respondent (email address) selected in the “x4. Respondent Determination by AI” automated process, the handler for the “2. Record Response Outcome” process is set.

    g1. AI Judgment Result

    The path is selected based on the value of the “Judgment Result” data item:
    – If “not important”, proceed to “1. Respondent Determination”.
    – If “important”, proceed to the email transmission event (“m1. Urgent Response Request”).

    m1. Urgent Response Request

    An email is sent to administration department members and the respondent determined in “x3. Respondent Determination by AI”, prompting them to handle the “2. Record Response Outcome” process.

    g2. Respondent Set?: The path is selected based on the value of the “Respondent” data item:
    • If “Respondent” is not set (i.e., “-“), proceed to “1. Respondent Determination”.
    • If “Respondent” is set, proceed to “2. Record Response Outcome”.
    1. Respondent Determination

    An administration department member determines the “Respondent” based on the email content. The respondent determined in “x4. Respondent Determination by AI” is pre-filled.

    2. Record Response Outcome

    The respondent reviews the email content and records how the inquiry was handled.

    You can move the slider

    3. Customers Case Study

    4. Other Business Applications

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

    Customer Support Ticket Management

    Account Issuance Process, API Launch Support

    Sales Lead Assignment

    Order Report Flow

    Inquiry Form Routing

    Inquiry Response Process, ChatGPT Collaboration

    5. Related Posts

  • Increase Trust With Electronic Signatures on Shareholder Certificates

    Increase Trust With Electronic Signatures on Shareholder Certificates

    Adding an electronic signature step ensures certificate authenticity, prevents tampering, and improves trust with investors.

    1. Issue: Absence of Electronic Signatures

    An unlisted company that does not issue stock certificates certifies shareholder status by issuing a Certificate of Shareholder Register Information to shareholders. This task is overseen by the Administration Department, which creates a PDF certificate based on the information on the shareholder register and sends it to the shareholder.

    Currently, certificates are not digitally signed, and some venture capitalists (VCs) have pointed out that the possibility of tampering cannot be ruled out. This situation not only increases the time and effort required to verify the information, but may also hinder the building of trust in capital alliances with VC firms.

    2. Solution: Add an Electronic Signature Step

    The process owner added an electronic signature step to the workflow, specifically, a step where an executive electronically signs the certificate after the management department has completed checking the certificate.

    This allows the executive in charge to manually add a digital signature and ensures the certificate is issued in the format required by the VC.

    Digital signatures enhance certificate authenticity, increasing trust with investors.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    • Shareholder requests via public web form
    • Certificate PDF generation
      • Certificate PDF automatically generated based on shareholder registry
    • 1. Request acceptance judgment
      • Determine if there are any deficiencies in the request content
    • 2. PDF double-check
      • Double-check performed by another member of the Administration Department
    • Email transmission

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    • Shareholder requests via public web form
    • Certificate PDF generation
      • Certificate PDF automatically generated based on shareholder registry
    • 1. Request acceptance judgment
      • Determine if there are any deficiencies in the request content
    • 2. PDF double-check
      • Double-check performed by another member of the Administration Department
    • 3. PDF electronic signature
      • Electronic signature applied by an executive
    • Email transmission
    You can move the slider.

    3. Customers Case Study

    4. Other Business Applications

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

    Supporting delivery notes for EC companies

    Customer Master Synchronisation Process, Google Sheet Integration

    Increased Customer Satisfaction

    Survey Request Response Process

    Insurance company claims processing

    Invoice Storage Process, ClimberCloud Integration

    5. Related Posts

  • Shareholder Certificates Created with Double Checks for Accuracy

    Shareholder Certificates Created with Double Checks for Accuracy

    Introducing a double-check system reduced certificate errors and improved accuracy and reliability in issuance.

    1. Issue: Errors in Certificate Issuance

    An unlisted company that does not issue share certificates instead issues certificates to its shareholders. After receiving a request to issue a certificate, the person in charge of the Administration Department extracts the necessary data from the shareholder registry, creates a PDF of the certificate, and sends it. This series of tasks was carried out by a single person.

    Occasionally, errors were made at the time of issuance, resulting in incorrect information being included in the certificate. These problems were caused by inadequate data extraction and verification, as well as a checking system that depended on one person, resulting in a loss of trust.

    2. Solution: Implement a Double-check System

    The process owner decided to introduce a double-checking system to improve the certificate issuance process.

    A step was added in the workflow app where another staff member reviews the certificate PDF after it is generated. This ensures that the PDF certificate is reviewed by two different team members.

    A double-check system significantly reduced errors in certificate issuance.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    • A shareholder submits a request through a public web form.
    • Automated PDF Generation
      • The certificate PDF is automatically generated based on the shareholder registry
    • 1. Request Acceptance Review
      • The request content is checked for any deficiencies to determine if it’s valid
    • Email Delivery

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    • A shareholder submits a request through a public web form.
    • Automated PDF Generation
      • The certificate PDF is automatically generated based on the shareholder registry
    • 1. Request Acceptance Review
      • The request content is checked for any deficiencies to determine if it’s valid
    • 2. PDF Double-Check
      • A different member of the administration department performs a double-check of the generated PDF
    • Email Delivery
    You can move the slider.

    3. Customers Case Study

    4. Other Business Applications

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

    Financial Institution Document Issuance

    Document Publishing Process, Using Google Drive

    Manufacturing Quality Control

    Satisfaction Survey, Start Receiving Emails

    Real Estate Contract Preparation

    Subcontracting Flow

    5. Related Posts

  • Boost Membership with an Extra Campaign Announcement!

    Boost Membership with an Extra Campaign Announcement!

    A gym boosted conversions by extending its no-fee offer via automated follow-up emails.

    1. Issue: Insufficient Outreach to Potential Members

    A membership-based gym chain with 30 locations across the country offers prospective members a trial program before they decide whether to sign up.While the studio gauges interest after the trial, few individuals sign up immediately. This has highlighted a need to boost their conversion rates.

    To address this, the Kyoto branch independently launched a “No Enrollment Fee Campaign”. This initiative waived the enrollment fee for anyone who joined within seven days of their trial. The campaign successfully increased the branch’s membership conversion rate by 1.5 times compared to before its implementation.

    However, a new challenge has emerged: this campaign doesn’t effectively reach potential members who don’t sign up within the initial seven-day window.

    2. Solution: Automated Email for Extended Campaign Offers

    First-First Fitness Studio’s Kyoto branch is supercharging its “No Enrollment Fee Campaign” to better engage potential members. They’ll launch a special email campaign targeting individuals who didn’t sign up immediately after their trial. This email will announce a seven-day extension of the “No Enrollment Fee” offer, giving them another chance to reconsider joining.

    To make this happen, the process owner will revamp the workflow system. It’ll automatically dispatch the “Campaign Extension Email” seven days after a free trial if the prospective member hasn’t yet enrolled.

    The plan boosts conversions by extending the “No Enrollment Fee” offer, giving trial members a second chance to join.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    • 3.Membership Confirmation
      • We’ll confirm your enrollment after the trial on the same day
    • 4.Enter Keyword (for Pending Membership)
      • The assigned trainer will input three keywords gathered from the prospective member
    • The AI will generate a thank-you message
    • 5.Content Confirmation
      • The receptionist will review the generated text and make minor adjustments to the phrasing
    • A thank-you email containing feedback from the assigned trainer will be sent to the prospective member
    • 6.Later Enrollment
      • We’ll process the membership application if the candidate wishes to join at a later date. This option automatically expires if 7 days pass from the trial date.
    • 7.Feedback
      • The trainer who provided the free trial will check the membership outcome and enter their reflections

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    • 3.Membership Confirmation
      • We’ll confirm your enrollment after the trial on the same day
    • 4.Enter Keyword (for Pending Membership)
      • The assigned trainer will input three keywords gathered from the prospective member
    • The AI will generate a thank-you message
    • 5.Content Confirmation
      • The receptionist will review the generated text and make minor adjustments to the phrasing
    • A thank-you email containing feedback from the assigned trainer will be sent to the prospective member
    • 6.Later Enrollment
      • We’ll process the membership application if the candidate wishes to join at a later date. This option automatically expires if 7 days pass from the trial date.
    • Send campaign extension email
      • If 7 days have passed since the trial date, an email will be sent
    • 7.Final Judgment
      • After the extension email is sent, we’ll process the membership if there’s an enrollment request
    • 8.Feedback
      • The trainer who provided the free trial will check the membership outcome and enter their reflections
    You can move the slider

    3. Customers Case Study

    4. Other Business Applications

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

    Webinar Sales Follow-up

    Seminar Registration

    Demo Follow-up

    Seminar Attendance Management, Approach Priority AI Judgment

    Sample to Order

    Product Shipping Process

    5. Related Posts

  • Automatically Updating the List of Call Handlers

    Automatically Updating the List of Call Handlers

    To ensure the AI functions correctly, we need to prepare accurate data.

    1. Issue: The Heavy Burden of Updating Call Handler Lists

    BizyBizy Corporation, a leading provider of office essentials like copiers and printers, has been actively enhancing its phone answering operations. They’ve adopted an answering service where operators handle calls to the main number, and the results are shared with the administrative department via email. Recently, BizyBizy further boosted efficiency by integrating an AI-powered system for automatic call assignee selection.

    However, managing this AI system presents its own set of challenges. The AI relies on a pre-established “responder list” for its selections, but this list needs constant updates due to changes in staff because of new hires, departures, or transfers.

    Maintaining this list has become a significant burden for the process owner. When updates are delayed, the AI can’t select the right person for calls, especially for unregistered employees. This means staff often have to manually handle calls to compensate for the AI’s selection errors, undermining the very efficiency the system was designed to achieve.

    2. Solution: Automate List Updates Using Platform User Information

    To tackle these challenges, the process owner integrated a system into the phone answering workflow that automatically generates the responder list based on the workflow platform’s user information.

    This change ensures the responder list is always kept up-to-date.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram

    x1. Acquire Email Content

    When an email with the Phone Call label is received in Gmail, its content is read.

    x2. Importance Determination by AI

    The AI analyzes the email content to determine if it is a sales solicitation. The data item Judgment Result is set to “not important” if it’s a solicitation, and “important” otherwise.

    x4. Responder Determination by AI

    The AI analyzes the email content and selects a responder (email address) from a pre-prepared responder list.

    x5. Set Responder

    Based on the responder (email address) selected in the “x4. Responder Determination by AI” automated step, the processing handler for the “2. Record Response Outcome” step is set.

    g1. AI Judgment Result

    Depending on the value of the Judgment Result data item, the path is selected as follows:

    • If “not important,” proceed to the “1. Determine Responder” step.
    • If “important,” proceed to the email sending event (note*) “m1. Urgent Response Request.”
      *Accurately referred to as [Message Sending Intermediate Event (Email)].

    m1. Urgent Response Request

    An email is sent to administrative department members and the responder determined in “x3. Responder Determination by AI,” prompting them to process the “2. Record Response Outcome” step.

    1. Determine Responder

    Administrative department members determine the “responder” based on the email content. At this point, the responder determined in “x4. Responder Determination by AI” is pre-filled.

    2. Record Response Outcome

    The responder confirms the email content and records how they handled the inquiry.

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram

    x1. Acquire Email Content

    When an email with the Phone Call label is received in Gmail, its content is read.

    x2. Importance Determination by AI

    The AI analyzes the email content to determine if it is a sales solicitation. The data item Judgment Result is set to “not important” if it’s a solicitation, and “important” otherwise.

    x3. Acquire Responder List

    User information registered in the workflow platform is acquired (Responder List).

    x4. Responder Determination by AI

    The AI analyzes the email content and selects a responder (email address) from the responder list acquired in “x3. Acquire Responder List.”

    x5. Set Responder

    Based on the responder (email address) selected in the “x4. Responder Determination by AI” automated step, the processing handler for the “2. Record Response Outcome” step is set.

    g1. AI Judgment Result

    Depending on the value of the Judgment Result data item, the path is selected as follows:

    • If “not important,” proceed to the “1. Determine Responder” step.
    • If “important,” proceed to the email sending event (note*) “m1. Urgent Response Request.”
      *Accurately referred to as [Message Sending Intermediate Event (Email)].

    m1. Urgent Response Request

    An email is sent to administrative department members and the responder determined in “x4. Responder Determination by AI,” prompting them to process the “2. Record Response Outcome” step.

    1. Determine Responder

    Administrative department members determine the “responder” based on the email content. At this point, the responder determined in “x4. Responder Determination by AI” is pre-filled.

    2. Record Response Outcome

    The responder confirms the email content and records how they handled the inquiry.

    You can move the slider

    *This process improvement story is a work of fiction. Any resemblance to actual persons, organizations, or events is purely coincidental.

    3. Benefits

    Improved Accuracy

    Because the responder list is always up-to-date, the AI can accurately select the appropriate responder. This prevents human error and manual mistakes, enabling precise task execution.

    Expedited Customer Response

    With the immediate selection of the correct responder, the speed of customer service improves. This leads to higher customer satisfaction and strengthens trust.

    Cost Reduction

    By reducing the labor and time spent on manual update tasks, personnel and operational costs are lowered. As a result, corporate profitability improves.

    4. Other Business Applications

    The mechanism of utilizing user information registered in a workflow platform can be applied to the following types of operations:

    Information Security Training

    • After the training manager determines the training content and schedule, a mechanism can be built where users registered in the workflow platform (which can be limited to specific departments) are automatically assigned as handlers for the “Result Report” step.
    • This streamlines the management of training progress and prevents coordination errors among responsible parties.

    Year-End Tax Adjustment

    • After the administrative department sets the year-end tax adjustment schedule, a mechanism can be built where users on the workflow platform are automatically assigned as handlers for the “Document Submission” step.
    • This mechanism facilitates the dissemination of submission deadlines and the tracking of progress, leading to increased operational efficiency.

    Event Planning

    • After the content and schedule of internal events are determined, a mechanism can be built where users registered in the workflow platform (limited to specific departments if necessary) are assigned as handlers for the “Participation Confirmation” step.
    • This enables quick and reliable confirmation of participation, contributing to the smooth operation of events.
  • Create a Streamlined Shipping System Though Automation

    Create a Streamlined Shipping System Though Automation

    Surging orders overwhelmed rotating staff, so tasks are auto-reassigned after two hours to prevent delays.

    1. Issue: Shipping Delays Due to Overwhelmed Staff

    A traditional inn, known for its exceptional cuisine and prime location near major tourist attractions, is now facing a new challenge. The recent launch of their signature hot pot soup in vacuum-sealed frozen packs has been a huge success, leading to a surge in orders via phone, fax, and their website.

    While their current system attempts to balance the workload by rotating shipping assignments among the team, the sheer volume of new orders means that assigned staff are frequently overwhelmed, causing significant backlogs.

    2. Solution: Automated Task Handoffs Based on Staff Availability

    The process owner implemented a system that automatically reassigns shipping tasks to the next available staff member, if the initially assigned person can’t complete the work within two hours. This ensures that tasks are handed off proactively before delays occur, as assignments are rotated sequentially within the shipping team.

    Automatically reassigning handlers prevents backlogs and ensures on-time shipping.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    1. Order Information Entry (Manual)

    The team manually inputs customer order information.

    2. Primary Shipping Task (Main Handler)

    The main shipping handler carries out the shipping tasks. Once complete, a shipping confirmation email is sent.

    x1. Subject Line Configuration

    The workflow system sets the subject line for communications, including the order ID and order date.

    x2. Primary Handler Assignment

    The workflow system designates the main shipping handler by rotating assignments among the shipping team.

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    1. Order Information Entry (Manual)

    Staff members manually input order information.

    2. Shipping Task (Primary Handler)

    The primary shipping handler performs the shipping tasks. A shipping confirmation email is sent upon completion.

    2′. Shipping Task (Secondary Handler)

    The secondary shipping handler performs the shipping tasks. A shipping confirmation email is sent upon completion.

    x1. Subject Line Setting

    The workflow platform sets the subject line with the order ID and order date.

    x2. Primary Handler Assignment

    The workflow platform designates the primary shipping handler from the shipping team on a rotating basis.

    x3. Exclude Primary Handler from Candidates

    The workflow platform adds a rule to exclude the primary handler from further assignment considerations.

    x4. Secondary Handler Assignment

    The workflow platform designates a secondary handler, excluding the primary shipping handler.

    You can move the slider

    3. Customers Case Study

    4. Other Business Applications

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

    Customer Support Operations

    Automatic Update Salesforce Customer Master

    Inventory Management Operations

    Equipment Management Process, Using QR Codes

    Event Preparation Operations

    Event Participation Acceptance flow

    5. Related Posts

  • ノイズ記録・分析で社内ヘルプ改善

    ノイズ記録・分析で社内ヘルプ改善

    1. 課題：ノイズ案件の記録・分析ができない

    キビキビ商事の情報システム部は、社内のITインフラを支えるヘルプデスクとして、総勢20名のスタッフが社員からの技術的な問い合わせに日々対応しており、1日あたり20〜30件の相談を処理しています。

    近年、「会議室の使い方」や「家庭のWi-Fi設定」など、部門の管轄外と考えられる“ノイズ問い合わせ”が増加しています。

    しかし、案件データを“ノイズ問い合わせ”として分類・記録する仕組みがなく、傾向を把握できていないため、予防策にもつながらず、同様の問い合わせが繰り返されていました。

    2. 解決策：案件ステータスの自動分類

    プロセスオーナーは、ワークフローに案件ステータスを分類・記録する仕組みを導入しました。

    〔1.一次回答を入力〕〔2.二次回答文を入力〕といったヒューマン工程の前後に自動工程を挿入し、進行に応じて『一時対応中』『二次対応中』『対応済』『ノイズ』のいずれかがステータスとして設定されます。

    これにより、スタッフが一次回答時に『ノイズ』ボタンを押すと、ステータスは「ノイズ」に分類され、その情報は案件データとして自動的に記録されます。

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    ワークフロー図の詳細を見る
    問合入力[FORM]

    社員が問い合わせ内容をフォームに入力します・

    受付通知受信

    問い合わせの受付の通知を受信します。

    1.一次回答文を入力

    社内ヘルプデスクの担当者が1次回答を入力します。

    ノイズ…終了、暫定回答→返信＆2次回答、最終回答→最終回答を返信

    一次回答（最終）

    一次回答内容をメールで通知し、終了します。

    一次回答（暫定）

    一次回答内容をメールで通知し、終了します。

    2.二次回答文を入力

    技術対応担当者が二次回答文を入力します。

    二次回答（最終）

    二次回答内容をメールで通知し、終了します。

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    ワークフロー図の詳細を見る
    問合入力[FORM]

    社員が問い合わせ内容をフォームに入力します・

    受付通知受信

    問い合わせの受付の通知を受信します。

    1.一次回答文を入力

    社内ヘルプデスクの担当者が1次回答を入力します。

    Status:ノイズ

    1.でノイズを選択した場合、案件ステータスが『ノイズ』に設定されます。

    Status:対応済

    1.で最終回答を選択した場合、案件ステータスが『対応済』に設定されます。

    Status:二次対応中

    1.で返信＆2次回答と選択した場合、案件ステータスが『二次対応中』に設定されます。

    一次回答（最終）

    一次回答内容をメールで通知し、終了します。

    一次回答（暫定）

    一次回答内容をメールで通知し、終了します。

    2.二次回答文を入力

    技術対応担当者が二次回答文を入力します。

    Status:対応済

    2.で二次回答を選択した場合、案件ステータスが『対応済』に設定されます。

    二次回答（最終）

    二次回答内容をメールで通知し、終了します。

    中央のバー操作で比較できます

    3.効果

    問い合わせ傾向の可視化

    分類されたノイズ情報を蓄積・分析することで、再発防止や業務改善に役立ちます。

    ノイズ対応の時間短縮

    不要な問い合わせを迅速に見極められるようになり、対応時間の削減につながります。

    対応方針の標準化

    ノイズの判断基準が明確になり、全スタッフが統一的な対応を取れるようになりました。

    4. その他の業務への応用

    サプライチェーン問い合わせ

    不要な在庫確認などを除外することで、優先度の高い対応に集中できます。

    カスタマーサポート

    標準的な問い合わせと個別対応を分けることで、重要顧客への対応力が高まります。

    人事への社内問い合わせ

    繰り返される一般的な質問を判別することで、戦略的業務への時間確保につなげられます。

    5. 提案資料

    当社サービスの導入を検討いただく際の提案書サンプルです。課題に対する解決策の概要を記載しています。実際の相談内容に応じて、内容を個別にカスタマイズして提供いたします。

    helpdesk-noise-20250714ダウンロード

  • 取り下げ通知で無駄作業を無くそう

    取り下げ通知で無駄作業を無くそう

    取り下げられた問い合わせを対応中のスタッフに自動通知することで、対応不要な案件の作業を即時中止可能に。気付かずに回答作業を続けてしまう無駄を防ぎ、業務効率の低下を防止。

    1. 課題：回答作成の労力が無駄になる

    キビキビ商事の社内ヘルプデスクでは、社員からのITに関する問い合わせをWebフォームで受け付けており、1日あたり20〜30件に対応しています。

    このフォームには、ユーザーが自ら問い合わせを取り下げる機能があります。しかし、取り下げられたことはヘルプデスクのスタッフに通知される仕組みになっていません。そのため、スタッフは取り下げに気づかず、回答作成作業を続けるケースが発生していました。

    その結果、不要な作業が発生し、業務全体の効率低下を招く要因となっていました。

    2. 解決策：即時共有される「取り下げ通知」

    この問題を解決するために、プロセスオーナーは、ワークフローに通知機能を追加しました。

    具体的には、問い合わせが取り下げられた時点で、自動的にスタッフ全員にメールで通知される仕組みです。通知には、問い合わせの件名やID、取り下げ日時が記載されており、スタッフは中止の詳細を即時に把握できます。

    これにより、スタッフは対応中の案件が不要となったことをすぐに確認でき、速やかに作業を中止し、次の対応に移行できるようになりました。

    Before

    Basic Edition
    Advanced Edition
    Professional Edition
    ワークフロー図詳細を見る
    問合入力

    一般社員が、社内ヘルプデスクに問い合わせます。

    AI回答

    AIにより一次回答が行われます。

    受付通知

    一般社員に、受付通知が自動送信されます。

    問合取下

    問合内容が取り下げられます。

    全終了

    全てのフローが強制終了されます。

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    ワークフロー図詳細を見る
    問合入力

    社員が社内ヘルプデスクに問い合わせます。

    AI回答

    AIにより一次回答が行われます。

    受付通知

    受付通知が自動送信されます。

    問合取下

    問合内容が取り下げられます。

    取下通知

    ヘルプデスクスタッフに、取下通知が自動送信されます。

    全終了

    全てのフローが強制終了されます。

    中央のバー操作で比較できます

    3. 効果

    無駄な労力の削減

    取り下げ通知により、不要な回答作成を未然に防止できます。

    対応判断の即時化

    取り下げの有無をリアルタイムで把握できるため、複数案件への対応時に優先順位が迅速に判断できます。

    情報共有の強化

    取り下げ通知により、案件の状況が即時に共有され、スタッフ間でスムーズに作業を分担できます。

    4. その他の業務への応用

    顧客サポート

    顧客からの問い合わせが取り下げられた際に即時通知することで、無駄な対応を防ぎ、業務を効率化できます。

    製品開発部門

    プロジェクトの中止や仕様変更を関係者に即時通知することで、不要な作業を早期に止め、リソースを優先タスクへ集中できます。

    総務部門

    会議のキャンセルや日程変更をリアルタイムに通知することで、参加者の時間調整が容易になり、スケジュール管理の精度が向上します。

    5. 提案資料

    当社サービスの導入を検討いただく際の提案書サンプルです。課題に対する解決策の概要を記載しています。実際の相談内容に応じて、内容を個別にカスタマイズして提供いたします。

    cancel-notice-20250703ダウンロード
  • Create Thank You Emails with AI to Save Time!

    Create Thank You Emails with AI to Save Time!

    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

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    3.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

    Basic Edition
    Advanced Edition
    Professional Edition
    View details of the workflow diagram
    3.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.

    You can move the slider

    3. Customers Case Study

    4. Other Business Applications

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

    Reviews of periodic reports

    Work Request Flow

    Reviews of proposals for customers

    Approval Process, Azure OpenAI Service Creation Assistance

    Reviews of internal business regulations

    Item Lending Process, View Lending List

    5. Related Posts

  • From Risk Detection to Smooth Mitigation

    From Risk Detection to Smooth Mitigation

    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.

    Before

    Basic Edition
    Advanced Edition
    Professional Edition

    After

    Basic Edition
    Advanced Edition
    Professional Edition
    You can move the slider

    3. Customers Case Study

    4. Other Business Applications

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

    Faster Invoice Approval

    Billing Process

    Auto Contract Renewal

    Subcontracting Flow

    Expense Automation

    Invoice Storage Process, ClimberCloud Integration

    5. Related Posts

  • AI Call Responder Selection

    AI Call Responder Selection

    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

    Basic Edition
    Advanced Edition
    Professional Edition
    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

    Basic Edition
    Advanced Edition
    Professional Edition
    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.

    You can move the slider

    3. Customers Case Study

    4. Other Business Applications

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

    Prioritizing Cases

    Project Report Request Process

    Support Center Ticket Assignment

    Approval Flow, ChatGPT Decision Assistance

    Setting Priority for Trouble Resolution

    Survey Acquisition

    5. Related Posts

  • AI Reliably Captures Calls

    AI Reliably Captures Calls

    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

    Basic Edition
    Advanced Edition
    Professional Edition
    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

    Basic Edition
    Advanced Edition
    Professional Edition
    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.

    Compare Before/After (You can move the slider)

    3. Customers Case Study

    4. Other Business Applications

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

    Sales Department: Prospect Management

    Project Report Request Process

    IT Support: Ticket Management

    Approval Flow, ChatGPT Decision Assistance

    Internal Request Processing

    Internal Training Management Process

    5. Related Posts