The REMEMBR app icon: a cream rounded square with a mark of concentric orange arcs resembling a fingerprint.

MRP Thesis Defence

REMEMBR

Building an accessible journaling application without a programming background.

Raafi Islam Master of Digital Media · Toronto Metropolitan University

Agenda

How this defence runs

  1. The problem

    Why I built this. A problem I kept running into, and what the apps we already have could not do about it.

  2. Methodology and Positionality

    What evidence I used, and what studying my own practice can and cannot prove.

  3. REMEMBR

    The app I built, and the accessibility thinking behind each decision in it.

  4. Findings

    The four skills this took, the four ways the AI kept failing, and the three habits I built to work around them.

  5. Discussion

    My answers to both research questions, what this adds, and where it goes next. Then your questions.

Dhaka, 2018

I recognized the face.All I had was one word: undergrad.

No name. No idea who introduced us, when we last spoke, or what we had ever talked about. One fragment, and nothing I owned could do anything with it. My contacts app wanted a name. My photos wanted a date. Neither of them would take “undergrad” and give me back a person.

So I made an excuse and left. What stayed with me was not the awkwardness. It was realizing I had no way back to that person at all.

A Recurring Pattern

It did not happen once.

It kept happening, until I started avoiding situations where it might come up again.

Epilepsy

Epilepsy affects how memories get stored in the first place. It is my own diagnosis, and the reason this kept happening to me.

Monthly support sessions

I heard the same frustration from other people, month after month. The tools we have are not built for memory you cannot rely on.

The Gap

Journaling apps organize by date. Contact apps organize by name. Associative memory does neither.

Standard journaling applications, Day One, Journal, Diary, organize content by date. Standard contact applications organize by name. Neither model reflects how associative memory actually works.

People are more reliably retrievable through their relational context and associated events than through a name or a face alone (Yovel and Duchaine, 2006). REMEMBR grew out of that gap: entries organized around people rather than dates, surfaced through any connected context. A shared location. A mutual contact. An event.

Research Questions

Two questions drive this MRP

  1. RQ1

    How can a non-programmer use generative AI to design and build a functional software application, and what specific competencies does that process require?

  2. RQ2

    What are the practical limits, recurring failure modes, and design trade-offs of AI as the primary development tool, and how were they navigated?

Thesis

Generative AI has created a genuinely new pathway for non-programmers to build production-grade software. It is not frictionless.

It demands a distinct skill set, rooted in design, editorial, and project-management practice, not programming. The skills are real. So are the limits.

Methodology and Positionality

How I studied this. What evidence I used, and what research into your own practice can and cannot prove.

Evidence Base

Two kinds of primary evidence

AI conversation transcripts

The full archive of my ChatGPT conversations, and the Claude Code sessions that followed. Together they record every instruction I gave, what the AI sent back, and how I corrected it.

Versioned application files

Two separate version histories. Fifteen named versions from the early build, each saved as its own file, and a second run of versions from the Claude Code build that replaced it.

Positionality

Designer, director, and subject

I did not begin with a research framework. The process was driven by personal experience and iterative making: trying things, observing what happened. This resembles what design researchers call research through practice (Frayling, 1993): knowledge generated by the act of making, not by observing from outside it.

What this makes possible

I know why every decision was made, which nobody watching from outside could reconstruct. At every step I knew exactly how far the output was from what I wanted.

What it cannot guarantee

I cannot be fully objective about my own experience. I handle that by tying each claim to a dated transcript rather than to memory.

Limitations

What this study cannot claim

A single case

One case cannot tell you what is generally true of non-programmers building with AI.

No external verification

The dated transcripts back up what I claim, but I am the one reading them.

Theory found after the fact

I noticed the link to Actor-Network Theory afterwards. I did not set out to test it.

What it can produce: a detailed, internally consistent account of one instance of this process, precise enough to generate propositions later research can test.

REMEMBR

The app this project produced, and the accessibility thinking behind every decision in it.

The Artifact

A people-first journal, not a dated diary

You build a profile for each person in your life, linked to places, events, and people you both know. Remember any one of those things, and you should be able to find the person.

Built for

Epilepsy · Prosopagnosia · Traumatic brain injury · ADHD

8 months
From October 2025
13,000
Lines, in a single HTML file
0
Lines of production code written by hand
REMEMBR home screen on a dark background. A greeting reads Good morning, Raafi. Below it a Your People row shows circular portraits of Adam, Olivia, Daniel and Sara, then prompt cards reading Who did you meet today? and Siobhan's birthday in 2 days.
Figure 9. Interface. Generated with Claude (Anthropic, 2026).

Design Principle

Accessibility is the baseline, not a feature

Governed throughout by WCAG 2.1 AA, Ontario's AODA, and W3C COGA guidance for cognitive accessibility. Every setting here is the user's choice, never auto-detected.

WCAG rests on four principles, known together as POUR. Here is what each one meant in practice.

Perceivable
Can you take the information in? Atkinson Hyperlegible type, and a sky-teal palette that took five rounds to pass WCAG 2.1 AA. Anything saved can be read out loud.
Operable
Can you work the controls? Dictation in any text field, not just a special voice mode, tuned for a wide range of accents. Tap targets over 44 by 44 pixels, motion you can turn down, and nothing that strobes.
Understandable
Does it make sense as you go? Easy Mode replaces every multi-field form with one plain question at a time.
Robust
Does it work with the tools you already rely on? ARIA labels, full keyboard control, and screen reader support.
REMEMBR's Accessibility settings panel. Labeled toggles for Easy Mode, High Contrast, Reduce Motion and Haptic Feedback, a Text Size control set to 100 percent, and a Voice and dictation language selector.
Figure 3. Accessibility Features. Generated with Claude (Anthropic, 2026).

Signature Feature

The Connection Web

A graph where people, places, memories, and events all carry the same weight. Start anywhere, from a mutual friend or an event, and follow the links out to the person you are trying to reach.

Structurally resonant with Actor-Network Theory (Latour, 2005): a connection recognized only in retrospect, after the interface was already built from lived experience rather than from theory.

The Connection Web in REMEMBR, titled Adam's Web with four connections. Adam sits at the center of a dark canvas with thin teal lines radiating out to Daniel above, Olivia to the right, Sofia below and Jesse to the left, with a list of the four connected people beneath the graph.
Figure 4. Connection Web. Generated with Claude (Anthropic, 2026).

Signature Features

Two more ways in

Associative Search

One search box looks through everything at once, so you never have to pick a category first. That matches how episodic memory is actually retrieved, through linked cues (Tulving and Thomson, 1973).

REMEMBR search results for the single word coffee. Filter chips read All, Colleague, Friend, Family and Acquaintance. Two matching people, Priya Nair and Sara Williams, appear as cards with photos, how they were met and a relationship label. Below, a heading reads 14 memories found, followed by entries including Full circle: Priya meets Marcus at Balzacs Coffee with Daniel and Priya, Coffee catch-up with Adam, and Sara mailed a watercolour.
Search, current build (cf. Figure 5). Generated with Claude (Anthropic, 2026).

Easy Mode

Every multi-field form turns into one question at a time, right across the app. It is grounded in cognitive load theory (Sweller, 1988).

REMEMBR in Easy Mode. The home screen asks What would you like to do? and offers four large, plainly labeled choices: Add a person, Add a memory, See my people, and My memories.
Figure 2. Easy Mode. Generated with Claude (Anthropic, 2026).

Signature Features

Designed to remove friction, not add polish

Avatar Creator

Not everyone has a photo of every person they want to remember. I set Snapchat's Bitmoji as the bar to hit, and rejected three rounds before the fourth was good enough.

REMEMBR's avatar creator. A large illustrated face preview sits above a Randomize button, a row of eight selectable skin tone swatches, and a grid of five face shape options with the last one selected.
Figure 6. Avatar creation. Generated with Claude (Anthropic, 2026).

Social Card Generator

A card you can share that tells someone what they mean to you. It reads: "I REMEMBR YOU."

REMEMBR's Share your memory screen. A generated card for Adam Chen, labeled Colleague, reads We met at DG8011 class on Thu, Sep 5, 2024. Sat next to each other on the first day, above the tracked words I REMEMBR YOU.
Figure 8. Social Card. Generated with Claude (Anthropic, 2026).

Findings

Eight months of working across several AI tools and models, running trials, exploring options, and fixing errors. Here is what came out of it.

Finding 1 of 3

Four competencies, not one line of code

  1. Specification

    Turning what you want into words precise enough for the AI to build it correctly. You do this constantly, not once at the start.

  2. Evaluation

    Judging whether the result is good enough without reading the code. You go on how it behaves, how it compares to other products, and what testing shows.

  3. Direction

    Giving a correction specific enough to actually fix things. Naming a product to match works far better than saying "make it better."

  4. Continuity Management

    Holding one clear picture of the product across dozens of separate sessions, with tools that remember nothing in between.

Finding 2 of 3

Four failure modes, recurring by structure

  1. Silent Feature Regression

    Features I had already signed off would disappear between sessions, with no warning. The AI only saw what was in front of it, not a running list of what already existed.

  2. Persistent Hallucination

    The same wrong facts kept coming back. It repeatedly said the app stored everything on the device, when REMEMBR actually syncs to the cloud.

  3. Token Limit Constraints

    Useful working time dropped to 15 or 20 minutes before the context ran out. Waiting for the limit to reset could take up to five hours.

  4. Code Token Exhaustion

    At 13,000 lines, simply loading the file into a new session used up a large part of the context before any work began.

Finding 3 of 3

Three practices developed in response

  1. Structured Context Documents

    A dense briefing pasted in at the start of every session, because a chat tool opens each conversation blank. Claude Code made this easier later on. It keeps project notes in files on the machine, so the context carries over instead of being pasted again.

  2. Standing Rules

    Every mistake the AI kept repeating became a fixed rule I carried into every later session.

  3. Forced Review and Planning Cycles

    The forced waiting turned into useful time. I used it to test what was live, find bugs, and plan the next features on paper.

A Question This Raises

Who owns this, and is the data safe?

REMEMBR holds private memories about real people. Both questions were requirements from day one.

Code ownership
Copyright needs a human author, but work directed through human creative choices can still qualify (U.S. Copyright Office, 2023). Anthropic claims no ownership of what it generates (Anthropic, 2024).
Data safety
Encrypted in transit and at rest. Sensitive entries sit behind a vault PIN with escalating lockout, and every administrative read hits an audit log. No ads, no trackers, nothing sold, no memories used to train a model.
Training data
The training opt-out stayed on throughout, so the build sessions were excluded from model training (Anthropic, 2024).
Platform choice
I left Rork because keeping project data private needed a paid subscription. REMEMBR runs on infrastructure I own and audit myself.
Illustration of three cartoon figures in a tug of war over a large phone showing an app icon. One wears a ChatGPT t-shirt, one a Claude hoodie, one a Google sweater, with loose papers and a USB cable scattered on the floor.
Everyone wants a piece of the app you build.

Discussion

Answering both research questions

  1. RQ1

    How can a non-programmer use generative AI to design and build a functional software application, and what specific competencies does that process require?

    They can, and it takes four skills. Not one of them is programming. They are design and editorial skills, and far more people already have them than can write code.

    Specification · Evaluation · Direction · Continuity management

  2. RQ2

    What are the practical limits, recurring failure modes, and design trade-offs of AI as the primary development tool, and how were they navigated?

    The same four failures kept coming back, and they share one cause: the tool is stateless, so it never sees the whole product it has already built. Because the cause is structural, the failures are predictable, and predictable failures can be worked around with documented, repeatable habits.

    Silent feature regression · Persistent hallucination · Token limits · Code token exhaustion

Next Steps

This does not stop at the defence

Continuous development
The app is live and still shipping. The same working method carries straight on: build, test, correct, release.
Partnership
I presented REMEMBR to the board of Epilepsy Toronto. They are now partnering with me to apply for government grants, which is what turns this from a student project into a funded one.
Real users, not just me
That partnership is also the route to the users this was built for. Moving from closed testing to a full release, with people other than me deciding whether it works.

I needed this app. Nobody had built it. So I built it. The next part is other people using it.

A video call with the board and staff of Epilepsy Toronto, thirteen participants on screen, during the meeting where REMEMBR was presented.
Presenting REMEMBR to the board of Epilepsy Toronto.

I REMEMBR YOU

Thank you.

Questions and discussion

Raafi Islam · REMEMBR · Master of Digital Media, Toronto Metropolitan University

References

Works cited in this presentation

  1. Anthropic. (2024). Privacy policy. https://www.anthropic.com/legal/consumer-terms
  2. Anthropic. (2026). Claude [Large language model]. https://claude.ai
  3. Braille Institute of America. (2019). Atkinson Hyperlegible font. https://www.brailleinstitute.org/freefont
  4. Frayling, C. (1993). Research in art and design. Royal College of Art Research Papers, 1(1), 1-5.
  5. Government of Ontario. (2005). Accessibility for Ontarians with Disabilities Act, 2005, S.O. 2005, c. 11.
  6. Latour, B. (2005). Reassembling the social: An introduction to actor-network-theory. Oxford University Press.
  7. Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257-285.
  8. Tulving, E., & Thomson, D. M. (1973). Encoding specificity and retrieval processes in episodic memory. Psychological Review, 80(5), 352-373.
  9. U.S. Copyright Office. (2023). Copyright and artificial intelligence. https://www.copyright.gov/ai/
  10. W3C COGA Task Force. (2021). Making content usable for people with cognitive and learning disabilities. World Wide Web Consortium.
  11. W3C Web Accessibility Initiative. (2018). Web Content Accessibility Guidelines (WCAG) 2.1. World Wide Web Consortium.
  12. Yovel, G., & Duchaine, B. (2006). Specialized face perception mechanisms extract both part and spacing information: Evidence from developmental prosopagnosia. Journal of Cognitive Neuroscience, 18(4), 580-593.

Note. The REMEMBR screens shown here are figures from the MRP and keep the paper's figure numbers, except the search screen on slide 16, which is a later capture of the same feature. All show software generated with Claude (Anthropic, 2026).

REMEMBRMRP Defence

Press → to continue