Jenkins

Remembering Without The Memory


Lean UX / Hypothesis Testing  ·  Iterative Prototyping  ·  Moderated Usability Testing  ·  Research-Driven Design

Your digital secretary for the messages you meant to answer.


Read more below

Project Overview

Project Contraints

This project was scoped as a Lean UX study within a 2.5-month academic timeline. Usability testing involved 3 participants, so findings are directional, not statistically validated, and all sessions were single-sitting Zoom calls, a controlled environment that's hard to reconcile with the real-world interruption and app-switching Jenkins is actually built for.

Platform constraints shaped the concept too: iOS's privacy restrictions cap automation at semi-automated flows, while Android supports it fully. And since testing focused on interface and usability preferences, questions like whether Jenkins actually reduces missed replies or relationship strain over time remain untested.

Role

UX Designer
UX Researcher

Members

Suleyman Sarigoz (me)

Industry

Communication

Timeline

2.5 Months

Tools

Figma
ChatGPT
The Lean Startup

The Problem

Busy professionals juggling emails, messages, and calls struggle to keep up with important conversations — not because they don't care, but because remembering to reply while mentally elsewhere ("prospective memory") is a losing battle against distraction and cognitive load. The cost isn't just a missed message. It's strained relationships, lost opportunities, and a nagging guilt that never fully goes away.


Importance of the Problem

"It takes 23 min to focus after getting distracted." - UCl.edu

"Workers who completed tasks in parallel took 30% longer and made 2x as many errors." - Richard L. Byyny, MD

"48% have had a relationship negatively impacted because of their slow response to messages." - Secure Data Recovery

The Solution ❤︎

Jenkins is an AI reminder agent that closes the gap between intention and action.

Instead of asking users to remember what they've forgotten, Jenkins surfaces it — synthesizing missed context across apps, filtering signal from notification noise, and prompting follow-up at the right moment.

The goal isn't more notifications. It's fewer, smarter ones: shifting the mental burden from recall ("did I reply to that?") to recognition ("oh right, there it is").

The Research

Literature Review

Reading Takeaways

Our brains struggle with 'Prospective Memory'—remembering to do something in the future while busy now. My research shows that chronic stress makes this worse. I designed Jenkins to shift the user from 'Recall' (trying to remember) to 'Recognition' (seeing a prompt), which lowers the mental effort needed to stay in touch.


Sources

Byyny RL. Information and cognitive overload: How much is too much? Pharos Alpha Omega Alpha Honor Med Soc. 2016 Autumn;79(4):2-7. PMID: 29481015.

Cantarella, G et al. “Prospective memory: the combined impact of cognitive load and task focality.” Brain structure & function vol. 228,6 (2023): 1425-1441. doi:10.1007/s00429-023-02658-3

Rice M, Hansen M, Thomas ML and Davalos D (2024) Neural correlates of prospective memory in
college students with anxiety. Front. Psychol. 15:1430373. doi: 10.3389/fpsyg.2024.1430373

Chen, Jierong et al. "An Effect of Chronic Stress on Prospective Memory via Alteration of
Resting-State Hippocampal Subregion Functional Connectivity." Scientific reports vol. 9,1 19698. 23 Dec. 2019, doi:10.1038/s41598-019-56111-9

Keywords From Readings

Prospective Memory (PM): Remembering to do things in the future.

* Little stress can help with PM, but chronic stress drastically decreases the PM performance. Busy students with high state anxiety, showed very low levels of PM performance. *

Cognitive Load: The mental effort used to process information.

Chronic Stress: Long-term, ongoing stress.

Intention Retrieval: Recalling what you planned to do.

State Anxiety: Temporary nervousness in a situation.

Intention Offloading: Using tools or cues to remember tasks.

* Recommendations were to create an environment that would promote the use of recognition rather than recall. *

Information Overload: Too much information to process effectively.

Multitasking Myth: The false belief we can focus on tasks equally at once.

* Multitasking is dividing focus into separate tasks, and slows down progress. *

Archetype - The High-Density Communicator

longshot20250826164855

Mindsets & States

Mindsets: Relational Responsibility

They value their professional and personal reputation deeply. They believe that "responsiveness equals reliability" and feel a strong sense of duty to their network.


Day-To-Day Mental States: Persistent Guilt & Hyper-Vigilance

During the journey, they fluctuate between "Avoiding" (due to being overwhelmed) and "Panicked Searching" (when they remember a missed message). This leads to a state of low-level chronic anxiety


Psychographics

Values

High achievement, career growth, and deep personal loyalty.


Attitude

Tech-reliant but tech-exhausted. They see their smartphone as both a vital tool and a source of constant "demand" on their time. 

Motivations & Goals

Relational Integrity

Maintaining "social capital" by never letting a high-stakes thread go cold.


Cognitive Efficiency

Achieving a "Clear Mind" state where they can focus on deep work without the nagging feeling that they've forgotten someone.


Opportunity Capture

Ensuring that time-sensitive professional prospects (like job offers) are acted upon immediately.


Thoughts & Feelings

Thinking

"I’ll definitely remember to do this at 5:00 PM when I'm home." (Overestimating future memory).


Feeling

"Digital Drowning." A heavy sense of guilt when seeing a 3-day-old message from a loved one or a recruiter.

Behaviors & Patterns

App Juggling

Rapidly switching between 3+ messaging ecosystems (SMS, Work Email, Personal IM).


Passive Interaction

They see a notification, process its importance, but "store" it in their short-term memory rather than acting, leading to Intention Decay.


Manual Workarounds

Taking screenshots or leaving notifications unread as a primitive way to "offload" memory.

Market Research

Existing solutions are limited—email plug-ins exist, messaging apps require manual work, calls have no support, and OS automations are effort-heavy.

Frame 20

Email

Tools like FollowUp, Boomerang, and Mailbutler remind you of unanswered emails.

Messaging

Most apps need Apple Reminders; only Telegram offers reminders, but manually.

Phone Calls

No solutions exist.

OS-Specific

iOS Shortcuts/Android Routines allow manual automations.

Brainstorm Potential Features

The mindmaps were made to brainstorm potential features.


First Mindmap

shows a broad features ranging from various use cases, operating systems, technology device, ideas needed to be researched.


Second Mindmap

shows the MVP features ranging from user flows, further research details. 


Legend 

 cannot be done
● requires further research 
for MVP

Hypothesis Prioritization Canvas (Lean UX)

PRIORITY MATRIX

Hypothesis Testing

Based on the "Hypothesis Prioritization Canvas" above, I created small experiments to undersand the feasibility of the features.

*iOS allows only semi-automation due to privacy rules, while Android supports full automation with flexible APIs.

risky hypothesis

Visual Inspiration Board

My Jenkins UI design is inspired by images highlighting organization through shapes, lines, colors, and typography.

The keywords that inspirated my inspiration board: High Contrast, Accessible, Bento Box, Organized

UI INSPIRATION 1

Key Pages

HOMEPAGE 3

Content Funnel Approach

Content follows a funnel approach: general on the homepage, more detail on the messages page, and specific app-based messages last.


Participant Feedback

3/3 participants loved the funnel approach from general to detailed calling it 'natural,'


UI Consistency Across Apps

Colors match app icons for consistency. AI notifications are presented neatly with a 'Bento Box' layout.

Custom Settings

Automatic and Tailored

Users can customize notification frequency or choose immediate reminders, addressing issues of bad timing or forgotten messages.

Based on feedback, reminders now track frequency after the initial message per hour, not total per hour.


Lo-Fi Feedback

“My meetings tend to be long, I wouldn’t want to be bothered multiple times per hour on non-work related things.”

3/3 felt summaries were useful but wanted them slightly longer.

SAN FINAL

Design Changes

Homepage Changes

From "OMG what’s this mess" to "a personal digital secretary"

Through 3 rounds of testing, I evolved the interface from a cluttered notification list into a structured 'Content Funnel.' While V1 caused cognitive overload, the final V3 design successfully balanced AI-driven summaries with a 'General-to-Specific' navigation flow—leading one user to describe the experience as having a "personal digital secretary".

* Click on the arrows below to see more details.

V1
‪‪❤︎ 3/3 liked having important notifications in one place.
 
‪‪3/3 were confused when no summaries appeared.
 
Overall Feedback:
All felt overwhelmed by seeing missed messages without context with one person saying "omg what’s this mess”
V2
❤︎‬ 3/3 liked the idea of centralized notifications but rated the current version 2/5.

3/3 said the summaries were “too much, too busy, too messy”
V3
❤︎ 3/3 loved the funnel approach (general → specific). One noted, “This feels like I have a secretary named Jenkins.”
 
3/3 found summaries decent but wanted slightly longer ones.
 
2/3 had 3+ important contacts spread across multiple apps.

Specific App Notification Settings Changes

V2 fixed V1 problems but introduced another problem

Early testing (V1) showed that users wanted more substance from AI summaries to feel truly caught up. While V2 solved the content depth, it introduced a new challenge: notification distraction. I iterated on this by moving from static alerts to 'User-Controlled Settings,' allowing participants to customize summary lengths and reminder intervals to reach their personal "sweet spot".

* Click on the arrows below to see more details.

V1
1/3 participants were satisfied with the current length of the summaries.

2/3 participants thought the summaries were a bit short.
 
  • Can the summaries be more detailed.
  • Summaries tend summarize the key ideas or main points as well.
V2
❤︎ 3/3 liked the idea of centralized notifications but rated the current version 2/5.

❤︎ 3/3 understood and appreciated reminder notifications, but had doubts on the success of it. 
 
  • My meetings tend to be long, I wouldn’t want to be bothered multiple times per hour on non-work related things.
 
  • Getting constant notifications per hour while working would be extremely distracting.
    When asked about a possible fix, they suggested it to be user controlled somehow. 
 
1/3 suggested that the reminder notification tone should be the default application tone
  • People would be are used to it (notification tone) and one more less thing to remember.
 
Controlling Reminder Settings
❤︎ 3/3 mentioned it was more natural and effective
“made more sense” and believed to be “more effective” in returning back sooner.
 
❤︎ 3/3 agreed that having customizable AI summary lengths was the “sweet spot”.

Usability Test

Participants + Usability Test Details + Results

The usabilty test and results have been reflected in the final version of the JENKINS' prototype.

Participants

I tested my design with participants who matched my personas—busy individuals who often overlook notifications do to other responsibilities. 

All participants names have been replaced with a random letter.


Participant D

Occupation: Data Science Manager

Technology Knowledge: High


Participant F

Occupation: Full Time Student

Technology Knowledge: Medium


Participant T

Occupation: Community Center Event Organizer

Technology Knowledge: Low

Usability Test

All usability tests were conducted on Zoom with consent to use cameras, record screens, and sessions for later observation.

Scenario 1

“You just finished a day with back-to-back [meetings, classes, discussions] and want to quickly get caught up on any important messages and message them back.”


Scenario 2

“After a long day, you JUST remembered the notification from an [Apple recruiter, colleague, team member for class]. Find it.”


Scenario 3

“You want to set your close friend Omar as an important sender for Whatsapp in Jenkins. How would you do that?” 


Post Usability Test Questions

1. On a scale of 1 (never use) - 5 (would download it now), what would you rate this design?

  • 3
  • 4
  • 5


2. What do you think this design needs to make it even better?

  • "A way to know when a message has arrived. A way to order messages because it seems like it's missing."
  • "A sort of widget would be nice."
  • "Overall it's really good, but I had trouble adding someone as important. Maybe a way to make that faster."


3. "What do you tend to do to remind yourself to return back to people?"

  • "I don't have a method, I just remember it. All of my devices are connected, when I receive a notification and it's important, I drop everything and deal with it." 
  • "I tend to see messages on my lockscreen at the wrong times, so 1 immediately take a screenshot of it."
  • "I write it in the small notebook that I carry with me."

Results + Updates

Although all tasks were completed, participants faced issues. I prioritized message delivery and “important sender” problems due to time limits.

2/3 wondered about the order of messages
2/3 seemed bothered in going to the chat source. 
2/3 asked "When did this message come?"
2/3 took longer than expected to add an "important sender"


Message Recency

Recent messages appear at the top with timestamps.


Message Time

Each contact shows the last message time.


Quick Add Contact

A bottom-right button lets users mark contacts as important.

Recieved Feedback

Overall Score: 12/15

"Overall it's really good, but I had trouble adding someone as important. Maybe a way to make that faster." ❤︎

Participant D

"A sort of widget would be nice." ❤︎

Participant F

“This feels like I have a secretary named Jenkins.”  ❤︎

Participant T

Looking Back

What I Did Well

Finding a Real Problem

I found a real-world problem with no direct competitor and built a solution for it using the Lean UX framework.

Letting Research Lead

The "recall vs. recognition" framing from prospective memory literature is the reason Jenkins surfaces information the way it does. That came from the research, not a hunch.

De-Risking Early

I used a Hypothesis Prioritization Canvas to test the riskiest assumptions first, like whether iOS and Android could even support the same automation, before sinking more time into a direction that might not have worked.

What I Can Do Later

Expanding Where Jenkins Lives

Turn Jenkins into a home-screen widget so reminders are even more at-a-glance.

Let users mark someone as important right from the source. A Gmail plugin, an incoming call, a new message, instead of doing it inside the app.

Proving It Actually Works

Build a functional version to see if this holds up outside a prototype.

Run a longer field study to see if Jenkins actually cuts down missed replies and relationship strain, not just whether people like the interface.

Cleaning Up Core Usability

Fix message ordering and the friction of jumping to the original chat.

Speed up the "important sender" flow. It took people longer than it should have in testing.

What We Would Do Differently

Talk to More People

Three participants was enough to spot patterns, but not enough to trust them fully. I'd interview more people next time.

Test It in the Wild

Zoom sessions are controlled and calm, the opposite of the distracted, multitasking mess Jenkins is actually built for. I'd want to test it somewhere messier, or across more than one sitting.

Don't Code Feedback Alone

This was a solo project, so I was the only one interpreting what participants said. Bringing in a second person to cross-check that would've caught my own bias.

Selected Works

Sober CuriousProject type
Eastern AccentsProject type
OrontesProject type
Uyku HapProject type
NXT StrainerProject type
View