🐍2025

🚀 Coming soon

This quarter’s major update introduces multiple AI enhancements combined with brand-new automation designs, enabling you to create smoother and more seamless conversation experiences. For example, after a conversation ends, you can automatically guide contacts to a specified bot flow and design satisfaction surveys and follow-up interactions as needed.

In addition, these updates include AI data analytics to help you better understand customer needs and improve service efficiency. These improvements not only enhance user experience but also provide businesses with more flexible communication solutions, ensuring every interaction delivers a positive impact.

🤖 New AI Agent bot templates are live

We’re simultaneously launching brand-new bot templates. They progressively demonstrate each AI Agent’s combinations and new settings, helping you understand how to build smoother conversation flows. You can apply the templates directly, then adjust and expand them as needed.

🤖 Enhanced AI bot flows

  1. AI custom agents now supportCustom output format, allowing you to specify text or numeric formats as needed and store the result in a variable. If you need to use the variable data, reference it according to the attribute you set, for example:{{ response.name }}.

  2. AI Vision Agent now also supportsCustom output format, enabling you to build more complete and diverse scenario applications such as invoice recognition, business card information extraction, product image identification, etc., greatly improving downstream automation capabilities.

  3. Calling a Webhook can now store execution results into variables for subsequent exception checks or other use cases. On success, returns 1, on failure, returns 0.

🤖 AI Insights adds “Service Reason” analysis and automated application

In service records, AI Insights now adds a possible “Service Reason” analysis item. AI will automatically select items that match the company’s built-in service reasons based on the conversation content, for agents to manually choose, shortening judgment time and improving operational efficiency. In addition, it can be paired with automated flows for automatic application, further reducing manual workload.

📊 Dashboard AI Information

The dashboard adds an “AI” category, and expands multiple analytical insights:

  1. AI conversation status:Used to analyze AI agents’ participation and resolution effectiveness in conversations, to measure their coverage and actual problem-solving ability, helping assess whether AI truly reduces the burden on human service.

  2. AI response status:Shows whether AI can find an answer, used to observe whether the AI knowledge base is complete.

  3. AI response quality:Used to observe AI’s response performance, evaluating the accuracy and usefulness, and whether it meets customers’ expectations and actual needs.

Through the dashboard’s trend charts and trajectory analysis, you can visually observe changes in AI response effectiveness, and evaluate the completeness of knowledge content and the improvement trend of AI comprehension quality.

⚡ Automation conversation upgrade: new “On flow end” event and “Go to conversation script” action

The “Conversation” automation has been upgraded with a new “On flow end” event, which can be automatically triggered after the entire conversation flow completes, such as initiating subsequent actions after a satisfaction survey. In addition, a new action “Go to conversation script” has been added, enabling you to design more extended interactions after the conversation ends, such as follow-up questions, product recommendations, or introducing new flows, creating a more complete, continuous conversation experience.

🔗 Tracking Links × LIFF: Build a tailored customer journey

Tracking Links now support integration with LIFF. When customers open the URL and complete authorization, the system will automatically direct them to the specified chatbot flow. You can create dedicated customer journeys based on different tracking links, which is especially suitable for scenarios like on-site event sign-up guidance and marketing flow design, making the overall interaction smoother.

🚫 Call blocklist

You can now set specific numbers directly in the system. When an incoming number matches the blocklist, the call will be automatically rejected after entering ACD.

💬 Conversation queueSupportsBatch operations

In some scenarios, you may need to process multiple conversations at once. The new feature allows you to perform the following actions for conversations still in chatbot status :

  1. Uniformly transfer to the live agent queue, so a human agent can take over subsequent service.

  2. Directly end the conversation and mark as completed, to quickly clear the queue and keep the system tidy.

This feature effectively saves operation time and improves the customer service team’s handling efficiency.

💪🏼 New features and improvements

  1. When creating or editing a template, you can now preview in real time the application results of Markdown and other effects, making it easy to confirm whether the format and presentation meet your needs.

  2. In “Conversation Scripts”, the Reply email operation now supports entering HTML styles, allowing you to directly apply layouts and formats, improving email layout and readability.

  3. To accommodate future ongoing expansions, we redesigned the list interfaces of custom fields, automation, and Webhook scripts. The new interface has clearer sorting logic and display structure, and adds corresponding descriptions, making operation and maintenance more intuitive and clear.

  4. The settings interfaces for “Service Reasons” and “Service Records” have been changed from the originalseparate page navigationto an interactive modal window. This avoids having to re-execute actions like “Load more” after each data change, thereby reducing repeated loading and operation time, and improving overall efficiency.

  5. The “Service Result” selection interface in the service desk has been restyled to be consistent with “Service Reasons”. This lowers the learning curve, provides more consistent operations and layout, and enhances overall interface consistency.

  6. Tickets now add “Priority” as a filter condition, allowing agents to quickly view and manage tickets based on urgency.

  7. Strengthened validation for LINE Official Account settings to avoid the originally connected Account A being unexpectedly associated with Account B due to settings like replacing tokens, causing Account A’s friends and related data to malfunction.

  8. Two new security settings have been added to System Settings: High-security password combinations and Password reuse restrictions. Enterprises can enable them according to their own information security needs to strengthen overall account security.

  9. A new “Automatically quote previous email” feature has been added for the email channel in System Settings. After enabling, when replying to an email, the content of the previous email will be automatically brought into the input box. Agents can still edit or adjust it before sending, improving reply efficiency and conversational continuity.

  10. We plan to open some APIs originally limited to partners to general plan users, allowing more businesses to build more advanced automated flows. At the same time, we will launch a brand-new Developer Kit advanced paid item to help large enterprises build fully automated flows and handle special complex scenarios, improving overall operational flexibility and scalability.

Live chat historical contact notice

Planned for live chat contacts created before 2024 and with no message exchanges for over a year to undergocleanup.

Due to browser characteristics, related cookie and localStorage identification information have long exceeded their retention period. These live chat contacts can no longer initiate contact through the original channel, and their conversation records have lost practical meaning, so they will be removed together.

2.93.05.24

  1. For the situation where the new version of Outlook forces special encodings, handling mechanisms have been added, including compatibility adjustments for less-used or even non-mainstream BIG5 encoding. However, please use UTF-8 as the primary encoding format to ensure consistent and reliable display across mainstream browsers and different platforms.

2.93.05.03(10/02)

  1. If SSOhas been forcibly enabled, then in some scenarios requiring password reset (such as first login etc.), related prompts will no longer be shown to agents.

  2. Fixed a cache display issue after clicking “Save” when adding an employee and selecting Azure AD user binding .

  3. Adjusted that when adding a new employee, the default language will be automatically set based on the current operator’s own system language .

  4. Fixed an anomaly where keyword filtering could not display correctly during initial setup.

  5. Custom field style adjustment: changed Boolean-type custom fields from button style back to native radio style to avoid difficulty recognizing selected items in read-only/locked states, and to improve interface consistency and accessibility.

  6. Fixed customer import anomaly: fixed an issue where custom field data was not written correctly when adding customers with multiple conditions,

2.93.05.03(09/26)

  1. Messages now support Markdown escape syntax. You can, by adding a backslash (\) before Markdown characters, prevent them from being parsed as styling.

    For example:

    • \*text\* → Will display as *text* (instead of italic)

    • \**text\** → Will display as **text** (instead of bold)

    This method avoids accidentally triggering formatting and allows flexible character rendering, enabling more complex message content.

  2. After an administrator performs a monitor operation, the system will automatically lock the monitor button to prevent re-execution, thereby preventing conflicts caused by multiple monitoring sessions.

  3. The monitoring status will be displayed separately from the original call status. This avoids operation anomalies such as the transfer button disappearing when an agent is in a sub-call due to the administrator monitoring.

  4. Added a rule that when a sub-call is in progress, the hold operation cannot be performed to avoid conflicts under multiple states.

2.93.05.02 (09/22)

  • Fixed recordings from special external sources in call logs not playing properly.

  • Fixed Buttons in the Script-simulated bot

2.93.05.02 (09/16)

being unclickable. The original Growth plan will be renamed toMini The original to make it easier to distinguish and understand when adding other plans in the future. The original plan’s subscription benefits and available features remain unchanged.

  1. Fixed an issue in scripts where “Variable comparison” had timing differences in data updates under certain scenarios, such as via Webhook call returns and similar methods, but the decision node executed earlier, resulting in incorrect judgment outcomes.

  2. Strengthened the timeout message display for Employee API keys so users can more clearly understand the status.

  3. Fixed an issue in bot flows where “Judge inbound channel” could not be correctly determined. The main cause of this anomaly was related to a security mechanism. To prevent malicious actors from injecting disallowed strings via developer tools, the system has been adjusted and fixed.

  4. Fixed a dashboard issue with “Periodic text customer service transfers” display.

  5. Fixed an issue where the download link belonging to a file-type message could not be opened.

  6. Fixed, in some filter conditions, the customer dropdown display.

  7. Adjusted the dashboard’s “Conversation queue”fixing an issue where, after viewing historical conversations, viewing the same record again did not display the latest updated data.

2.93.05 (Q3 Major Update)

This major version update focuses on enhancing AI application capabilities, adding multiple intelligent features to further improve agents’ assistance efficiency and decision support during processes.

Specifically for the practical needs of frontline elite agents, we also launched multiple designs to optimize response speed and operating flows,greatly shortening handling time and improving task completion efficiency. This wave of upgrades is not just about adding features, but fundamentallyamplifying agents’ business value and professional power, helping teams advance in both service quality and operational efficiency.

🧠 New feature: AI Insights

Service records now add the “AI Insights” feature, enabling quick extraction from conversation information of:

  • Sentiment: Identify the customer’s emotional state in the conversation

  • Intent: Determine the customer’s needs and goals

  • Summary: Automatically condense the conversation to help quickly grasp the key points

This feature helps staff understand service records more efficiently, improving response speed and accuracy. This feature will be free to use for a limited time. We welcome you to try it and provide feedback. You can also pair it with automation: when the service record is completed, you can automatically trigger AI Insights to organize information.

🖊️ Service Desk adds beta feature “AI Quick Reply”

The Service Desk has added a beta feature “AI Quick Reply”. This feature automatically generates reply suggestions based on the content and context of a single message or a series of historical messages, helping agents respond quickly to customers.

With AI Quick Reply, agents don’t need to spend time drafting word-by-word, yet can easily provide appropriate responses, improving service efficiency and corporate consistency.

🤖 Chatbot scripts support “Global Nodes”, “Reply Email”, and “AI Vision Agent” features!

  1. The chatbot’s “Conversation Script” now supports adding Global Nodes, which helps reduce messy flow designs and unnecessary complex loops, making script structures clearer and more maintainable. Two types of global nodes are currently provided:

    • Contact idle with no interaction: Automatically triggers when the contact does not reply or interrupts the conversation within the specified time.

    • No node matched: When, after execution, the flow does not meet any set conditions, the node’s default action is executed automatically.

    Once set, global nodes will beapplied to the entire script flow, without needing to be repeatedly created in each node, effectively improving script design efficiency and consistency.

  2. Conversation scripts add a “Reply Email” node, for the email channel, enabling the following scenarios:

    • Prioritize replying with a canned message, for example, automatically replying “We have received your email, please wait for further processing.”

    • Support specifying the sender to reply with, making the email reply process more flexible and efficient.

    This feature can effectively shorten customer waiting time and increase the degree of automation for email replies.

  3. Chat scripts add a beta AI feature “AI Vision Agent”. This feature can analyze messages sent by customers and process the conversation into specified textual results to help create more application scenarios.

📞 Join forces with the elite sales team to reach new heights, multiple feature enhancements fully launched

This time, we once again joined forces with our partner company’s elite sales team, achieving outstanding results during the performance peak, coupled with multi-channel marketing strategies to deliver stellar performance. To continue supporting elite sales staff in quickly addressing business challenges, we have also launched multiple enhancements to accelerate team performance and continuously break performance ceilings.

  1. New options for auto-ready time to comprehensively improve call acceptance efficiency To meet elite agents’ need for high-efficiency operations and ensure every incoming call can be promptly routed to sales, the system will add “1 second” and “5 seconds” auto-ready time options. Users can adjust to shorter ready intervals as needed to speed up response and maximize sales opportunities.

  2. Quick Dial menu goes live, further simplifying outbound flows A “Quick Dial” dropdown has been added on the customer list page to further simplify the overall outbound operation. Only two actions are needed to dial out, greatly reducing cumbersome operations, helping elite agents execute outbound tasks more efficiently, and improving daily contact efficiency and response speed.

  3. New paid feature “Auto Dialer” goes live to improve contact efficiency and reduce manual burden Automatically makes outbound calls and, after connection, automatically transfers to a live agent for follow-up handling. It can effectively achieve the following goals: reduce repetitive manual operations, filter valid calls to avoid invalid numbers and connections, becoming the best support for high-frequency contact teams.

  4. New Dynamic Tab view mode goes live to improve execution efficiency Customer and ticket interfaces will introduce a brand-new view mode.Custom fields originally located separately under “Other” and the “Contact” page will be consolidated into the “Basic” tab for centralized display, reducing page switching and making important information clear at a glance. At the same time,the original tab buttons will still be retained. Clicking them will automatically switch to the “Basic Info” page and scroll to the corresponding field position, maintaining continuity with existing operation habits. This effectively reduces mouse movement and clicks, speeds up data switching and browsing, and comprehensively improves operational efficiency and agent experience.

  5. Service Results adds “Recent Options” quick action feature The Service Desk now adds a “5 most recently selected service results” function, helping agents directly select recently used items from the list and submit in one click when processing similar cases consecutively, significantly improving classification switching efficiency and workflow smoothness.

  6. Customer list adds “Orders” filter conditions The customer list now adds order-related filters, supporting creation time, total amount, ordered products, etc., helping you quickly and accurately find specific target customer groups and improve marketing and customer service efficiency.

🔀 Assignment logic and dynamic assignment enhancements

  1. Assignment logic enhancement To address the more complex skills and assignment conditions faced by mid-to-large enterprise users, the assignment logic has been strengthened. Previously, the mechanism would unconditionally allow some conversations to enter the “Assigning” state and then sequentially find suitable agents. Now it filters out “conversations that ready agents can take” during the initial screening,thereby reducing the risk of assignment jams caused by poorly designed skill assignment conditions or uneven staffing.

  2. Improved fairness of dynamic assignment The compensation mechanism “Dynamic Assignment” for assignment jams has been strengthened by adding a sorting mechanism based on agents’ cumulative assignment counts. The system will prioritize agents with lower cumulative assignments to improve fairness and avoid overloading a single agent.

  3. New “Conversation Queue Logs” feature to fully grasp conversation dynamics A new, independent “Conversation Queue Logs” item has been added to view current and historical conversation logs across message channels. With this feature, you can quickly grasp each conversation’s assignment status, processing progress, and related information, greatly improving service transparency and team collaboration efficiency.

💬 Markdown formats supported in live chat messages

In the Live Chat channel, message sending supports some Markdown syntax to highlight text and improve readability. Supported formats are as follows:

  • Bold text:**My Bold Text**

  • Italic text:*Italic Text*

  • Strikethrough text:~~Strikethrough text~~

  • Heading 1:# This is a h1 header

  • Heading 2:## This is a h2 header

  • Heading 3:### This is a h3 header

  • Dial link:[tel](+886-912-345-678)

  • Email link:[mail]([email protected])

Markdown syntaxis only supported in the live chat channel. Other non-instant messaging platforms (e.g., LINE) are not supported and may not display correctly or may be ignored on those platforms.

💪🏼 New features and improvements

  1. The email template selection interface has been redesigned from a dropdown to an interactive modal. The new interface can display more template information and reserves flexibility and space for future feature expansion, improving user experience and operational efficiency.

  2. When replying to emails, recipients in the original email’s “BCC” will be automatically populated by default.

  3. Live chat extensions now have an independent management item. Compared to before, after creating an extension, you can nowshare the same extension module across multiple live chat channels, without having to configure each one individually, greatly improving efficiency and consistency.

  4. The dialer interface has been fine-tuned,with clearer display when being monitored,improving recognizability, and adjusted button spacing makes the interface more compact yet with larger clickable areas.

  5. Enhanced foolproof design for phone operations: when a sub-call operation (such as three-way conference, coaching mode, etc.) is already in progress, clicking sub-call operations is disabled to avoid call interruption.

  6. The logic for determining whether call recordings can be played has been adjusted. Previously, it relied only on user permissions and and call duration to decide, which in certain scenarios might cause a misunderstanding that a recording exists. This update adds a more precise recording result determination mechanismto avoid situations of “has duration but actually no recording,” ensuring the display matches the actual recording status.

  7. Adjusted explanatory text for some conversation script nodes to besemantically closer to contextual use,and removed wording that might mislead users.

  8. In response to the increasing availability of the “Conversation Queue Logs” feature , the original sorting of conversation queues in the dashboard will no longer automatically switch based on status. Because this design was too implicit in the interface, causing confusion and potentially resetting user-set sorting, it has been adjusted to always sort by creation time, to improve consistency and predictability.

  9. The service record list will add a “Status” column, currently including the following statuses:In progress, Completed,This design also reserves room for future enhancements, making status management more flexible and sustainable.

  10. In bot scripts, the minimum customer idle minutes setting has been changed from 5 minutes down to 1 minute. This adjustment allows users to design more flexible conversation flows.

  11. Added support for Instagram channel Story messages and Reel messages.

  12. Fixed the display and functions of the phone contact buttons for employees and service records.

  13. Adjusted an issue where, when a personal signature is designed in multiple sections, re-entry was required after applying a template.

  14. The selection limit for script event tracking on the dashboard has been increased from 3 to 20, and now supports selecting up to 31 days of data range. Meanwhile, a new data download featurehas been added, allowing you to more conveniently save and analyze event tracking data, improving subsequent review and application efficiency.

  15. To comply with web accessibility guidelines and future derivative features, the trigger for the contextual function menu for a single message (e.g., AI translation) will change from hover to click, improving operational consistency and usability.

2.82.10.6(08/07)

  • Navigation bar phone interface optimization: After dialing, the entered phone number will be automatically cleared to avoid mis-dials and reduce operations.

  • Message template character count display fix: The character limit display has been adjusted to 500to match the actual rule, replacing the previously incorrect display of 2000.

2.82.10.5(07/27)

  • Quick phone options: Added support for non-numeric search keywords, improving search flexibility and ease of use.

  • Ticket interface fix: Fixed an issue where, after ticket creation, tab text appeared blank due to a display anomaly.

2.82.10.4 (07/11)

  1. Fixed adjusted validation rules for WeChat platform which previously caused authorization and reply malfunctions.

  2. Fixed the date filter logic for “Team Transparency Logs”.

  3. Fixed duplicate display when loading the next page of data in “Message Templates”.

  4. Fixed an issue where, when setting a rich menu, the “Switch Rich Menu” operation could not correctly select an existing rich menu.

  5. Fixed the dashboard’s “Service Source Statistics”numbers not displaying.

  6. In the customer list, the “Recent Service Records” and “Next To-Do” fields will now display time down to “HH:mm”.

  7. Adjusted an issue where remarks might fail to save due to version differences when manually creating service records.

  8. Fixed an issue where “Segmented Messaging Campaigns” could not select a channel.

  9. Fixed an issue where completed “Service Records” could not be edited.

※ To ensure the fixes take effect, please log out and log back in, or manually refresh the page to load the latest version.

2.82.10 (Q2 Major Update)

This season, we are launching many practical new features to create a more complete and smoother service experience!

These include several experimental features and AI applications, helping you build a more professional customer service team, optimize service processes, improve response efficiency, and make interactions with customers more immediate and smooth.

✨ Brand-new AI features debut,helping you do more with less!

A variety of new AI features help you write sentences, express ideas, and quickly complete various tasks. Whether it’s customer service conversations, content creation, or data organization, FIRST LINE AI can intervene instantly and assist precisely, greatly improving efficiency.

Unlike some market products that access AI via plugins and repackage solutions or products, FIRST LINE adopts native deep integration, seamlessly combining with the system’s core functions, truly achieving out-of-the-box clarity and a smooth, end-to-end experience. From operation to results, the overall experience is smoother and more natural—your best starting point for AI-empowering your team.

For example, by simply adding knowledge base articles, AI can instantly apply them to responses, and customer service staff can simultaneously view and use them in the system. No AI training expertise is needed throughout—easily achieving information integration and intelligent collaboration in one go.

  • “AI Judgment Agent” — Further advances in comprehension and judgment

    The “AI Judgment Agent” can more precisely grasp context and user intent. It can not only determine whether instructions meet conditions, but in specific scenarios can proactively produce judgment conclusions, greatly improving practicality and intelligent performance.

  • New feature live: — “Custom AI Agent” node

    You can now freely build dedicated AI text applications based on your actual needs! Through custom prompts, whether it’s boosting work efficiency, simplifying business processes, or crafting a unique marketing campaign, you can do it easily.

  • AI Answer Agent node — new feedback option settings In the “AI Answer Agent” node, you can now decide whether to enable “feedback options” and set related messages. On some channels, by turning off feedback, you can further save message costs.

  • Upgraded AI model that understands you better

    A more powerful AI model for translation, transcription, and more, withstronger understanding and more accurate expression, aligning more closely with your intent, reducing misunderstandings and errors, and greatly improving user experience and communication efficiency.

🎉 Limited-time free trial program

In response to the AI model upgrade, we will open some AI features (such as AI Writing) for a limited-time free trial,available directly to all paid and discounted users without additional application.

We sincerely invite you to provide valuable feedback during use to help us build a more powerful and needs-aligned FIRST LINE AI, enabling the smart work experience to continuously evolve.

🧠 New feature live: AI Training Center

Here you can view customer questions, suggested answers, and related references. More importantly, you can tag and review this content to ensure the AI improves over time and provides more accurate, trustworthy, and up-to-date knowledge. This not only enhances response quality but also makes AI answers closer to real needs.

✨ Chatbots support the “Switch Rich Menu” action node

The chatbot flow now supports adding theSwitch Rich Menuaction node. You can dynamically designate specific rich menus based on conditions to provide more personalized interactive content for different users.

For example, based on customer tags, event dates, etc. designate different content. Combined with marketing activities, dynamically push different guided purchase menus to achieveprecise segmented marketing,With this feature, you can create a more flexible and highly interactive LINE marketing experience, increasing user stickiness and conversion rates.

✨ Tracking Link upgrade: automatically create customer records

Now, the “Tracking Link” feature has been further enhanced. When you set a LIFF app and corresponding LINE Official Accountin the tracking link, after the customer clicks the link and agrees to authorize, the system will automatically perform the following actions based on the LINE Official Account settings:

  • ✅ Create the corresponding customer record

  • 🏷️ Automatically apply default tags

This enhancement tightly couples marketing activities with the actual interaction flow while bringing in traffic, achieving more efficient automated operations.

🌐 Custom domain feature

This time, for Enterprise plan and non-on-premises enterprise userswe provide a custom domain featureallowing you to create dedicated URLs for the Help Center and knowledge base articles to strengthen brand consistency and user experience.

For example: if the original default URL is firstline.cc/helpyou can customize it to help.yourcompany.com/helpto create a more recognizable dedicated entry point.

This feature is especially suitable for enterprises aiming to enhance brand professionalism and unify website style.

📢 Help Center URL Structure Adjustment Announcement

To support the launch of new features, we will redesign the Help Center's URL structure to make it more systematic, readable, and aligned with content categorization logic.

Example of the new URL structure after adjustment:

  • Original URL:/helpdesk → New URL: /help

  • Original URL:/article/174 → New URL: /help/article/174

  • Original URL:/category/10/article → New URL: /help/category/10/article

  • Original URL:/sub-category/2/article → New URL: /help/sub-category/2/article

If you are currently usingthe old URL for embedded or redirect designs(for example embed or iframe , or hyperlinks that integrate the Help Center into the official website), we recommend that youupdate to the new URL structure as soon as possibleto ensure features are not affected.

※ From the date of this announcement, the old URLs will remain for one month, at which timethe new URL structure will be used across the board.

🔒 Brand-new Security Mechanism Settings

To comply with the security regulations of cooperating government and public agencies, we have added multiple account security-related mechanisms. These features will help improve account security and meet certain institutions' information protection policy requirements.

However, please note that some configuration methods are no longer considered best practice in current information security practice. We recommend enterprises enable related settings flexibly according to their actual needs and, where appropriate, combine them with modern authentication mechanisms such as SSO (Single Sign-On) to achieve more complete and trend-aligned security protection.

Personal Email Notification Settings

Now, in Personal Settings you canenable additional email notification functionality, to receive real-time notifications for specific scenarios, improving security and convenience. For example, scenarios like “successful login” or “insufficient FANCY points” help strengthen account monitoring and keep you informed of account status; we recommend enabling the corresponding notifications as needed.

Point Quotas Debut — Smarter Resource Management!

In this update, you can set periodic FANCY point usage limits for specific agents, such as “maximum 100 points per month,” making management easy without relying on memory!

Agents can now also view the system's total points and their own usage directly from the profile page in the top-right corner.

This makes point usage rules clearer, resource allocation fairer, and ensures advanced feature usage remains within reasonable limits. It's especially suitable for teams with different roles and diverse needs, helping companies manage AI resources more intelligently, flexibly, and efficiently!

🔐 Permission Update: Added Marketing-Related Permission Items

This update adds permission items related to the marketing module, including:

  • LINE Rich Menu

  • Tracking Links

  • Coupon Functionality

Through more granular permission divisions, you can effectively control users' operation rights within the marketing module, enhancing flexibility and security in account management.

💪🏼 New features and improvements

  • We redesigned some interfaces to avoid information being too scattered. For example, the employee edit interface will be reorganized according to functionality, reclassifying setting items to make workflows clearer and easier to use.

  • Strengthened mechanism toautomatically create service records when phone channels are connected. This reduces missed record creation caused by factors such as user network instability or loading delays, further improving overall user experience and data completeness.

  • Adjusted the filtering method in the notification center,the original “read” and “unread” options will be consolidated into two modes: “All” and “Unread”. “All” will display all notifications, while “Unread” will only display notifications not yet viewed, helping you focus faster on pending messages and improving notification review and tracking convenience.

  • Improved the error prompt mechanism when the service desk “auto-save” fails. For cases when saving fails (e.g., required fields not filled, referenced data deleted, etc.) and the prompt was unclear, the system will nowshow a clearer error reason, helping users quickly identify issues and complete actions.

  • To align with the latest Azure AD setup process, we have adjustedthe description content for the “SSO Login” item in System Settings, making it clearer how the current Azure AD steps and field configurations correspond.

  • To-do item content now also supports AI-assisted writing and optimization! Quickly improve content to make your work records more complete and professional.

  • In response to situations like the pandemic,we launched various promotional plans, which caused some users to become confused about current plan detailsand even misunderstand customer service personnel. To improve the user experience, we have enhanced the “Billing Overview” interface to clearly present plan details, license quantities, and applicable benefits, along with explanations to make information more transparent and easier to look up.

  • Fixed an abnormal issue in the import function's drag-and-drop operation. Previously, an erroneous behavior occurred when dragging available fields into the template list.

  • Fixed an issue where using custom fields of type “relation” could cause the browser to freeze or become unresponsive in the view screen if related data was incomplete.

🛠️ Developer Notice: Webhook Response Time Adjustment

This update will restore the Webhook response time limit to 15 seconds, to ensure resources can be used fairly and effectively. Developers should note this adjustment and check whether their services comply with the new time limit.

2.78.11.03

📢 Webhook Mechanism Adjustment Announcement

To improve overall system stability and resource usage efficiency,FIRST LINE will make the following adjustments to the Webhook handling mechanism. Please pay attention and update related integration settings in time:

Cancel automatic retry mechanism

According to usage statistics,over ninety percent of failed Webhook requests still cannot succeed even after retries, which instead wastes server resources. Therefore, we willcancel the Webhook automatic retry mechanism entirely. If your service design relies on this mechanism, please adjust your logic promptly and ensure the availability and stability of the receiving server to guarantee timely processing of information.

Response time limit within 15 seconds

The original response time limit referenced mechanisms similar to LINE's Reply Token and adopted a flexible waiting time of 5 to 80 seconds. However, in practice this design can cause confusion, leading users to assume long delays are acceptable and resulting in implementation errors.

To improve consistency and clarity,Webhook requests must now uniformly complete responses within 15 seconds. Requests exceeding this will be considered failures (timeout) and the flexible waiting mechanism will no longer be retained.

  1. This regulation was previously announced in version 2.74.09; this is a reminder.

  2. The adopted 15-second Webhook response time limit was determined by comprehensively referencing practical standards of multiple mainstream platforms (e.g., LINE: 1 second, Facebook: 5 seconds, Microsoft Teams: 10 seconds, etc.), practical experience, and FIRST LINE user usage statistics.

Please review and update your Webhook implementation logic as soon as possibleto avoid future message loss or service interruptions due to noncompliance with the new standard. If your serviceis not affected by this adjustmentand has no related dependencies, you may safely skip this change.

2.78.11.02 (04/24)

  • Optimized the “Knowledge Base AI Extraction” feature by adding UTF-8 encoding checks and attempted automatic conversion mechanisms to ensure uploaded files can be correctly parsed by the AI.

  • Fixed Knowledge Base AI Content Extraction encountered interruptions when encountering special characters or symbols.

  • Fixed The “Enable” field for segment messaging campaigns had an abnormal display issue, which has been restored to normal display.

2.78.11 (Major Q1 Update)

🧠 AI Feature Enhancements and Improved Reply Capability

  • Single-message “AI Ask” enhanced contextual understanding: The “AI Ask” feature now has enhanced contextual understanding to help agents more quickly search for possible answers from the knowledge base, product data, and more, then organize them into reply messages.

  • Message rewrite feature enhancements: The message rewrite feature has been further improved and can now more easily generate messages ready for direct use, greatly increasing work efficiency. Agents can produce high-quality content faster when composing or editing messages, reducing editing time.

  • AI agent reply capability enhancements: The AI agent's reply capability has been strengthened to provide more accurate and useful responses so customers can get satisfactory answers and solutions more quickly.

🚀 Segment Messaging Upgraded Again — More Flexible, More Intuitive!

We are about to enhance the application ofsegment messagingto make communication more precise and efficient!

  • New type settings:Support for “one-time” and “automated”sending, which can be triggered automatically by events or schedules. You will be able to reach specific targets precisely through external integrations, such as remindinginactive contactsoror re-engaging unsubscribed users.

  • More intuitive interface:Filter conditions and channel steps are combined for clearer context and simpler operation!

  • Added “Segment Messaging Campaign” permission and marketing classification:We added permissions related to “Segment Messaging Campaigns” and categorized them under a new “Marketing” classification to make permission management and settings more convenient and clear.

For example, you can set automated messages for different scenarios. For instance, when a user cancels a subscription due to high cost, you can set up a “cancellation recovery” campaign. When the user unsubscribes, an API-triggered event can automatically send a discount coupon to the lost user. This upgrade makes your message management smarter and easily improves engagement!

🔐 Comprehensive Security Upgrade — Strengthened Protection Mechanisms!

Asfraud and phishing websitesthreats continue to increase, this update willsignificantly enhance cybersecurity protections, rolling out a series of strengthened measures to ensure your data remains secure.

  • Added team transparency logs:Specifically recordimportant read and write actions within the system, such asdeleting a customerand other critical operations, ensuring every step is traceable to reduce internal risk and enhance security.

  • Increased password length requirement: password length increased from the original 8 characters to 10 characters to strengthen account security.

  • Password updates in specific scenarios: In certain situations, the system will prompt and require users to change their passwords to enhance account security. For example, when an agent logs in for the first time and the password was set by an admin or system default, a password reset will be mandatory.

Mandatory employee email address update

In later versions, we will require employees to provide their email addresses to enable more secure password resets and receipt of immediate notifications, thereby reducing potential security risks.

📈 Dashboard Upgrades! More Comprehensive Data!

  • Adjustment of the “Personal Call Efficiency” value in phone metrics The personal call efficiency metric will be removed from the phone interface in the navigation bar. Considering future scalability and statistical frequency, and to avoid dispersing duplicate features, we will make “Personal Call Efficiency” a standalone dashboard tool. This tool will add four metrics: total outbound call time, total inbound call time, ACD call time, and total inter-extension call time, which will help agents understand detailed aspects of their personal call time.

  • Added “Periodic Text-to-Agent Transfer Count” Added a dashboard tool for “Periodic Text-to-Agent Transfer Count” to tally the total number of customer transfers to live agents across time periods within message channels. This will help managers better understand customer service conditions at different times and assist in adjusting scheduling or resource allocation. This statistic starts from version 2.78.11 and will be aggregated and reported the next day.

Brand-new shortcut design to help support experts work faster and more efficiently!

To help professional support staff improve operational efficiency, we redesigned keyboard shortcuts so you can switch and handle service requests more quickly.

  1. Adjusted some existing shortcuts, for example changing the service desk toggle to CTRL + B for more intuitive use.

  2. Added shortcuts for switching and answering services, such as CTRL + number, so you can jump quickly and respond in real time.

💪🏼 New features and improvements

  • For individual emails sent by customers, we have added a “View Original Message” feature, allowing you to view the original HTML and related information, making it easier to convey the complete content to technical support personnel and provide more accurate problem descriptions and technical assistance.

  • In the Dashboard's Conversation Queue, we added a “Dispatch Records” view so you can check a conversation's recent dispatch history to understand its dispatch status. To support this feature, we adjusted the size and style of existing action buttons to avoid accidental taps.

  • Now, in addition to email addresses, you can search email contacts by display name.

  • During phone calls, if an agent accidentally attempts to close the page or performs other actions, the system will use the browser's default function to ask the agent to confirm the close, preventing accidental interruptions to the call.

  • Fixed an issue where creating a service record from a call log did not automatically redirect to the service desk, ensuring a smoother process and automatic redirection to the service desk for subsequent handling.

  • Adjusted internal chat to prevent message display order errors that could be caused by time differences, ensuring messages are displayed in the correct order.

  • We have renamed the “On-site Store” channel to better match its actual function and use scenarios.

2.74.09.02

  • FixedIn the phone channel, before transferring a call, if you pressHoldfirst, the subsequent action would beautomatically canceled.

2.74.09.01

  • Fixed an issue where email channel scripts could not advance, ensuring flows execute properly and proceed to the next step.

  • Fixed a displacement issue that appeared in the history interface within the filter input box.

  • Fixed an issue where live chat on Mac browsers could not scroll properly under certain probabilities.

  • Fixed a variable overwrite issue in the feedback question for the “AI Answer Agent” node in conversation scripts.

  • When adding a LINE account, the naming method has been changed from numeric indexing to timestampto avoid conflicts caused by duplicate names.

  • Fixed an issue where Webhook scripts could not be added due to changes in URL verification rules

PreviousChangelogNextArchive

Last updated