Calm guard
Calmguard is an iOS keyboard extension that will analyze emotional tone in real-time and offer users an opportunity to reconsider sending impulsive, emotionally charged texts.
Problem Space
Problem Statement
How can we reduce emotional communication breakdowns and prevent relationship strain by using AI to filter angry or harmful messages?
Problem Background
Texting, especially in emotionally charged situations, can lead to communication breakdowns, misunderstandings, and lasting harm in personal and professional relationships. There is a need for a tool that helps individuals manage impulsive responses and navigate emotionally challenging conversations. This AI tool will analyze text in real-time for signs of anger, frustration, and harmful intent, offering users a chance to pause and reflect before sending the message. By addressing emotional tone in texting, we can prevent escalations and foster healthier communication habits.
Research Insights
During research regarding AI filtering angry or harmful messages to reduce emotionally charged communication, a mix of synchronous and asynchronous interviews revealed the following information:
Frequency of Emotional Messaging: Participants reported varying frequencies of sending emotionally charged messages, ranging from rarely (once a month or less) to several times a week, with some only texting when deeply frustrated.
Consequences of Emotional Messaging: The consequences were often negative, leading to misunderstandings or strained relationships, but for 28% of participants, fallout was reportedly temporary - 14% of which still leaned negative. Regret was common after sending such messages.
Receptiveness to Rethink Prompts: Responses to prompts for rethinking messages were mixed—while many found them helpful for avoiding regret or miscommunication, others found them annoying or intrusive. Most would consider using them to prevent conflict.
Desired Features: Key features included "breather" popups, delay timers, and message highlights, which would give users time to reflect before sending. Some also liked the idea of rewording suggestions to soften tone.
Response to AI Suggestions: Many were open to AI suggestions to prevent harm, but concerns about AI being too controlling were raised. Most preferred to manually review suggestions and decide whether to accept them.
Comfort with AI Assessing Emotional Tone: Comfort with AI varied—some were open to it for improving communication, while others preferred manual control due to concerns about AI’s emotional accuracy.
Preferred Notification Methods: Participants preferred non-intrusive methods like pop-up alerts, gentle reminders, or message highlights. They wanted flexibility and subtlety in how these notifications were presented.
Landing on the Solution (Optional but recommended)
This research highlights the diverse ways in which individuals approach emotionally charged messaging and their varied responses to AI-assisted tools designed to help manage emotional tone. The findings reveal that while emotional texting is a common behavior, its frequency and consequences differ significantly among users, with some experiencing regret or misunderstandings and others feeling neutral or even positive about their interactions.
The majority of participants expressed openness to receiving prompts to rethink their messages, recognizing their potential to prevent harm and foster more emotionally intelligent communication. Features such as rephrasing suggestions, delay timers, and breather pop-ups were seen as helpful, though concerns about potential intrusiveness were raised. It is clear that users would prefer these tools to be optional, non-invasive, and customizable to their needs.
Furthermore, comfort with AI assessing emotional tone was generally positive, provided that it doesn’t overstep boundaries or feel like an accusatory intervention. A balance of subtlety and clarity is crucial in ensuring that users feel empowered rather than restricted by the technology.
Overall, the research suggests that AI tools for managing emotional messaging can provide significant value if designed with a focus on user control, flexibility, and thoughtful intervention. Future iterations should take into account the need for personalization, user comfort, and contextual appropriateness to maximize their effectiveness in fostering healthier and more mindful digital communication.
User Flows/Mockups (Optional but recommended)
Future Steps
“This is what we learned from speaking to customers ..”
“Possible additional problems to address”
Images - screenshots, marketing assets, etc.
Learnings
Product Manager Learnings:
Arjun Thiruchchelvarajah
Co.Lab was a great experience to really force me to take action. I feel like I work well when things are required of me, so having this platform and skills training to really demand results was exactly what I needed. I am so grateful for being exposed to different technologies and tools that helped me facilitate my work as a PM.
Designer Learnings:
Designer Learnings:
Jo Sturdivant
- Adapting to an Established Team: Joining the team in week 6 of 8 was challenging, as I had to quickly adapt to existing workflows, dynamics, and goals. This mirrors real-world situations where you often integrate into teams mid-project, and flexibility is essential.
- Work-Blocking for Efficiency: With only two weeks to complete the project, I learned the importance of a structured work-blocking system. This approach allowed me to manage my time effectively and meet deadlines under pressure.
- Making Data-Driven Design Decisions: Unlike my past projects, I had to rely on research conducted by others. This was a valuable experience in using pre-existing data to guide design decisions, helping me focus on the core insights without starting from scratch.
Developer Learnings:
Developer Learnings:
Vanady Beard
&
As the back-end developer, I learned how important it is to create efficient and reliable systems that support the entire application. This experience also taught me the importance of optimising the database and ensuring the backend is scalable and easy to maintain.
Developer Learnings:
Stephen Asiedu
&
As a back-end developer, I've come to understand the importance of being familiar with various database systems and modules. This knowledge enables me to build diverse applications and maintain versatility in my work. I've also learned that the responsibility for making the right choices rests on my shoulders, guided by my best judgement.
Developer Learnings:
&
Developer Learnings:
Maurquise Williams
&
- Process of Creating an MVP: Developing a Minimum Viable Product (MVP) taught me how to focus on delivering core functionalities balancing between essential features and avoiding scope creep.
- Collaboration in a Real-World Tech Setting: This experience taught me how to collaborate efficiently in a fast-paced tech environment, keeping the team aligned and productive, even while working remotely across time zones.
- Sharpening Critical Thinking and Problem-Solving Skills: This experience honed my ability to think critically and solve problems efficiently. By tackling challenges and finding quick solutions, I sharpened my decision-making and troubleshooting skills in a dynamic, real-world setting.
Developer Learnings:
Jeremiah Williams
&
All in all this experience was very awesome I learned that in coding with others being transparent is key
Developers Learnings:
Justin Farley
&
I learned how important communication is when working with a team. Communication provides understanding, advice, ideas, and much more. While working with the product team, I’ve found that communication keeps everything flowing smoothly. Working with a team also showed me that every member brings something different to the table and we all have to work together in order to align and meet our end goal.