Signalchain
All you need to connect, connected
My role: Solo Designer/Researcher
Duration: 8 weeks.
Scope: Mobile app prototype
Tools: Figma, Adobe CC, Miro
Deliverables: Prototypes, user flows, research plan & synthesis .
Published: 09/10/25
The project
Signal Chain explores how a unified inbox can cut the cognitive tax of juggling 4–7 channels a day. Over 8 weeks, I conducted research, prototyped, and tested to understand how inbox contextual AI actions could speed up everyday replies while preserving agency. In moderated studies of quick personal replies, the prototype delivered 20% faster completion with 50% fewer interactions.
Problem statement
Everyday communication is fragmented across platforms, leading to inefficiency, missed messages, and a loss of control.
Goals
Consolidate personal channels in one mobile-first app; use AI to prioritise, retrieve, and organise; reduce hunting across apps while maintaining trust.
Role & responsibilities
End-to-end product designer—research synthesis, IA, flow diagrams & journey maps, interactive prototyping, usability testing.
Constraints
8-week timeline; AI behaviours simulated
The discovery phase
Building the foundation
User research summary
Interviews with potential users focused on multi-platform communication and app roles. A literature review covered communication in information-dense environments; a competitor audit examined project management tools, social media platforms, and AI email tools. These insights refined assumptions about merging work and personal communication, informing shallow IA and contextual actions.
Personas & user stories
After reviewing the interview transcripts and coding the data, I was able to build out personas that informed the project going forward. This process also involved understanding edge cases and building user stories.
A persona for Sarah Thompson, one of two developed. The personas acted like a North Star in the project; at each stage, it was important to ask if the choices made were beneficial to these potential user groups.
Key pain points
To streamline the experience, the design enabled inbox-level, contextual actions and AI retrieval, addressing user frustration with time lost hunting for older messages across various applications. Prioritization cues were incorporated to surface critical information first, solving the problem of important messages getting buried by notification noise. Finally, the scope was refocused on personal communications to prevent the unwanted blending of work and personal communications.
A screenshot of preliminary competitor research being done in Miro that was later expanded to include feature offerings and other relevant information.
Competitor/Literature insights
An audit of competitors (project management, social media, AI email) and a literature review on communication in information-dense environments, particularly how medical professionals manage patient data, revealed three key insights:
Prioritize situational awareness: UI should minimize extraneous information and use goal/task-oriented language.
Important actions in the inbox: Information architecture should be shallow, and contextual menus should assist users.
Reminders improve response rates: Follow-up prompts likely increase response rates.
These insights guided the development of user flows that quickly routed users to necessary replies.
Early prototyping
Testing assumptions finding paths forward
Although initial user sentiment favored a unified inbox for all communications, early paper/digital prototype testing revealed discomfort with merging work and personal messages in the same UI. This prompted a project refocus on personal communication.
An early digital wireframe showing a top menu option allowing for switching between work-related communication and personal messages.
Interaction model updates
"Undo send" initially delighted users, but its on-screen presence caused frustration and cognitive overload. Redesigned as transient, it now is available briefly before dismissing by tapping the message itself. Next steps and revisions would include progressive onboarding for safety controls, like Slack's tips, making them prominent for new users then subtle for experienced ones, balancing functionality with less visual clutter.
First version of the undo send feature with a button that would appear after each message was sent.
Evaluations
Key insights & outcomes
During moderated studies of replying to SMS messages, the prototype was able to reduce time on task by 20% and required 50% fewer interactions. These savings were accomplished by allowing actions to take place directly through the inbox and reducing the layers of the information architecture.
20% reduction in time on task in moderated studies of quick replies to SMS messages
50% fewer interactions per task in moderated studies of quick replies to SMS messages.
Outcome vs. goal
The project exceeded the success criteria established during the early phases of the project—quick SMS replies were 20% faster and required 50% fewer interactions in moderated tests, and participants preferred versions that explained the AI’s rationale.
Before and after revisions to the tone of the AI in the prototype. The revised version has clearer, more transparent language of the information sources consulted.
Transparency and AI
Testing showed that features that explained how the AI reached its conclusions were preferred over versions that prioritized smaller word counts and hid this information, especially when dealing with personal communications. This built trust and eased users into the idea of an LLM having access to their communication.
Prototype
Message-to-reply flow
The following video shows the app's message handling. It covers receiving messages, getting AI response ideas, searching by content, and sending replies. This order shows how actions based on context and clear AI tips build user trust and speed. Purposeful loading states signalled retrieval steps and increased perceived reliability.
Flow: Receives message → Prompts user with action→ Finds answer → Generates reply and asks for confirmation
Key moments
The flow hinges on three patterns: proactive prompts, visible ‘thinking’ states, and confirm/edit gates. The use of non-content states and animations to communicate that thorough consideration is being given to the users prompt, and confirmation and editing options being presented to ensure the user retains feelings of agency in the process.
#1 Starting the AI engagement
The initial prompt to engage with the AI features proactively offers an action without forcing user engagement. Additionally, background blurs and footnote-style typography visually isolate the content for user interaction.
#2 Non-content state to communicate consideration
Breaking the action across various compositions helps convey the different actions being taken while also acting as a progress indicator and signifier of the direction and actions being taken by the AI.
#3 Confirmation and addressing agency
Once the message is drafted, the user is prompted to send as is or edit. This retains agency in the user and ensures that nothing is sent without consent from the user. This is integral to building trust in the process.
Accessibility considerations
Building within the guidelines
I differentiated each card component to enhance user comprehension, ensuring selection and deselection were indicated through color variations, borders, iconography, or typographical adjustments. Clearly discernible shadows were implemented. When color differentiated states, it was combined with WCAG compliant typographic elements and executed to provide adequate contrast for colorblind users, signifying a shift in state for improved visual feedback.
A screen illustrating the use of elevation and components using minimum touch targets and clear and action focused language.
Learning & outcomes
By the numbers
20% faster quick personal replies
50% fewer interactions in moderated tests
Delivered
High-fidelity app prototypes for most important flow
Research plan and summary
Next steps
Flesh out more other communication types within the prototype
Test using integrated LLM to better understand constraints such as hallucinations and unpredictable outputs
Further user testing with larger sample sizes
Key takeaways
AI language should prioritize transparency over brevity when building trust.
Contextual actions decrease time on task and increase and situational awareness in messaging.
Establishing clear personal / public boundaries creates trust in users.
Thanks for reading, let's connect!
info@gregmccarthystudios.com