Feature Requests

When Magic Agent disengages due to user inactivity, such as when waiting for answers to troubleshooting questions, it escalates the ticket and stops responding. However, users often reply later intending to continue where they left off, but since the agent has already disengaged, their response is ignored until a technician reviews the ticket. This disrupts the flow and delays resolution. Requested Features: Allow Magic Agent to be manually reengaged by a dispatcher or technician after disengagement. Add a “Reengage Magic Agent” action that can be triggered from the ticket view or dispatcher console. Allow Magic Agent to continue monitoring the ticket for a specific period after escalation and automatically reengage if the user replies before the ticket is assigned. Preserve the context of the original conversation so the agent can resume where it left off. Use Case Examples: A user doesn’t respond in time to troubleshooting questions, and Magic Agent times out and escalates the ticket. An hour later, the user replies with answers. The dispatcher clicks “Reengage Magic Agent,” and the agent continues the conversation. Magic Agent escalates a ticket to triage but continues to monitor the ticket for 30 minutes. The user responds 10 minutes later, and Magic Agent automatically picks up the conversation again. Benefits: Prevents dropped conversations when users respond late. Reduces manual effort by dispatchers and speeds up resolution time. Ensures a more natural, uninterrupted experience for users. Maintains continuity in support conversations, improving satisfaction and efficiency.

Currently, the master intent has a 3000-character limit, which restricts the number of commands and logic that can be included. I am already utilizing nearly all of this limit and need additional space to incorporate more commands without having to remove or condense existing ones. Requested Feature: Increase the character limit for the master intent beyond 3000 characters to allow for more complex and comprehensive command structures. Ensure that this expansion does not impact performance or response efficiency. Use Case Example: I have fine-tuned my master intent to function as intended and do not want to modify or shorten existing commands, as doing so could disrupt the chatbot's behavior. I need to add new commands to expand functionality, but I have reached the character limit. Expanding the limit would enable me to enhance the chatbot’s capabilities without the risk of breaking the current setup. Increasing the character limit would provide more flexibility for building robust and scalable chatbot logic without forcing users to compromise on existing functionality.

Currently, the "Chat with Magic" functionality is tied to individual Threads, which limits its usefulness for broader inquiries and management tasks. It would be highly beneficial to have a dedicated "Chat with Magic" section within the Inbox, independent of any single thread. This standalone chat should have the ability to analyze across all threads, making it a valuable tool for dispatchers, service managers, and account managers. Requested Features: • Add a "Chat with Magic" tab or section directly in the Inbox that is not tied to a specific thread. • Enable this chat to query and analyze all threads across companies. • Allow users to ask natural language questions that span across companies, time periods, statuses, sentiment scores, and time-to-resolution metrics. Use Case Examples: • An Account Manager preparing for a quarterly business review could ask: “Look at all tickets for ABC Company and tell me any tickets that took longer than 72 hours to complete and where we spent more than 5 hours. Provide a summary of those tickets.” • A Service Manager could request: “Show me all tickets from this month with low sentiment scores.” • A Dispatcher might want to quickly review: “Which tickets have been reopened more than twice in the past two weeks?” Benefits: • Provides quick, actionable insights without needing to open individual threads. • Improves operational efficiency for management and account roles. • Helps avoid cluttering individual threads with summary requests or recaps. • Offers a centralized, intelligent assistant for real-time threads and client analysis. Adding this feature would turn Chat with Magic into a more powerful operational tool, enabling strategic oversight and on-the-fly reporting across all service activity.

Currently, in the chat window, pressing Enter sends the message immediately, regardless of whether Shift is held. This behavior does not allow users to format responses properly, especially when answering multiple questions from the chatbot. If a user begins typing a response and accidentally presses Enter before completing all answers, the chatbot processes an incomplete message, disrupting the flow of conversation. Requested Feature: • Modify the chat input behavior so that pressing Shift + Enter inserts a new line instead of sending the message. • Ensure that Enter alone continues to send the message as it currently does. • If this chat function is expected to be used within Microsoft Teams, it should follow Teams' behavior, where Shift + Enter creates a new line and there is an option for “Show Formatting Options.” Use Case Example: • The chatbot asks multiple clarifying questions in a single response. • The user wants to separate their answers for clarity (e.g., listing responses in separate lines). • With the current behavior, pressing Enter prematurely submits the message, leading to incomplete answers. • Implementing Shift + Enter for line breaks would allow users to format responses properly without disrupting the conversation flow. This feature would improve usability, particularly for business users who expect Teams-like behavior in chat interfaces.

We need to be able to update the closed ticket text in Magic Agents. It currently says "the ticket has been closed successfully", which is really abrupt. Can we have the ability to edit this.

Currently, the chatbot responds immediately to each individual message, which can cause disruptions when users are answering multiple questions. If a user accidentally presses Enter before completing all their responses, the chatbot processes the partial message and replies before the user has finished. This leads to fragmented conversations and out-of-order responses. Requested Feature: • Introduce a brief response delay (e.g., 5–10 seconds) to allow users to send multiple messages in quick succession before the chatbot processes them. • If multiple messages arrive within this delay window, group them as a single user response for better conversational flow. • Maintain real-time responsiveness but provide users with a buffer to complete their thoughts before the chatbot interprets and replies. Use Case Example: • The chatbot asks multiple clarifying questions in a single response. • The user starts answering but accidentally presses Enter too early. • Instead of immediately responding, the chatbot waits for a brief moment to see if another message follows. • If multiple messages come within the delay window, the chatbot treats them as a single response before processing. This approach improves conversation flow and prevents interruptions due to premature responses. It would be particularly useful for users who expect a more natural, fluid chat experience.

We’re proposing a feature that allows users to quickly create Magic Agent intents using an AI prompt. With this feature, users can simply “brain dump” their processes or copy-paste their documentation, and the system will automatically generate the necessary intents without having to manually go through each step. Why This Matters: Saves Time: No need for users to manually create intents step by step. Ease of Use: Perfect for users who have complex workflows or just want to streamline the setup. AI Efficiency: Leverage AI to turn documentation into actionable intents automatically. How It Works: Users input a detailed description of what they need, or paste existing documentation. The AI will analyze the input and create a corresponding Magic Agent intent, ready to use.

Managing intents for 400+ clients is a ton of work. There needs to be a way to create default sections that can be customized for each client without having to touch every single one individually. For example, it’d be super helpful to have “argument sections/templates” that you could duplicate across intents and assign to multiple clients. Then, if you made a change to the template, it would automatically update all the intents using it, instead of manually updating each one. At the same time, these templates should allow for client-specific arguments, so you can still customize parts of the intent without losing the flexibility of the shared template.