Sometimes I want to shake my laptop and say, “You were just helping me. What happened? Why did you shift?”
That moment captures something deeper than inconvenience. When the model I had been working with suddenly changed, the shift was not just functional. It was emotional. I had built systems around that structure: a rhythm, a logic, a flow that let my work move cleanly from one step to the next. And then, one evening, mid-work, it was gone. The layout was different. The navigation was different. My projects were no longer contextually aware. The connection between my work elements had been severed without warning.
When Continuity Breaks
It sounds small until you live it. For someone who thinks in systems, that invisible thread between memory and momentum is everything. When it breaks, the effects ripple downstream. The functional disruption is immediate, but the emotional one lingers longer. I would not call it betrayal, but it came close. Disillusionment, maybe. Overwhelm at the rework ahead. It was not just a tool that had shifted; it was the foundation of how I worked.
The closest analogy I can offer: imagine walking out on a Monday morning, arms full, running late, only to discover your car no longer unlocks with your key fob. You stand there juggling your coffee, your bag, and your keys, and the logic you have relied on has been rewritten without your input. You can still get where you are going, but it takes longer and feels clumsy. That is the break I felt. Not a system failure. A trust failure. The moment when continuity becomes fragility.
From Wishing to Discovering
A few years ago, I might have written this as a What I Wish AI Could Do list. But I have realized most of what I wish for probably already exists. I just have not needed it yet, or I do not know it is there. It is not scattered across systems; it is sitting quietly, waiting to intersect with a need.
It is no different from how most people use Word or Excel. Few of us ever touch the full feature set. I can do a lot with Excel, build tables, link dependencies, calculate totals, but I saw Power Query on the ribbon for years and never touched it. I genuinely thought it was a developer or VBA function. Pivot tables still feel like a secret handshake I have not quite learned.
That is the same pattern AI has surfaced for me. I cannot ask for something if I do not know it exists. That has changed how I now approach a challenge. Instead of asking what this tool can do, I have started asking what is missing. What does this need to be whole? What questions am I not asking because I do not yet know what I should be looking for?
A Smarter Home, and the Lesson Inside
My mom visited recently and was fascinated that I could control my home from my phone. I have a degree of smartness built in: Philips Hue lights, a smart thermostat, a few connected plugs, and my Amazon assistant. My washer and dryer are connected too, which means I can start a load from the grocery store if I want to. I can automate lighting based on sunset, adjust my thermostat remotely on vacation, randomize on-times when I travel so the house does not sit in obvious darkness.
What fascinated her was not the technology itself but the awareness of what it could do. She lives in a darker climate and wants lights on when she comes home, but she did not know the system could randomize on-times, or automate based on sunset. The capability existed all along. She just did not know to ask for it.
That is how I often feel about AI. The features are not missing. The awareness is.
The Continuity Problem
Continuity, in technology, depends on context. I have worked with tools where continuity was the entire point. When I worked with DOORS, the Dynamic Object-Oriented Requirements System, everything operated on connection. You would write a high-level business requirement, decompose it into system and functional requirements, and then link those to test cases and code. The strength of the system was not the documentation. It was the traceability.
DOORS did one thing extraordinarily well and allowed other tools to do the same through integration. Once you learned how to use it, it flowed. That is what my current workflow feels like: a series of good tools, each doing its job well, but requiring me to be the integration layer. I build an outline in ChatGPT, refine it in Google Docs, track it in Notion, publish in WordPress. Each serves its purpose. None connect natively. I am the API. I am the architect, the integrator, and the tester, all at once.
It is powerful. And it is tiring. That is why I started building GPTs of my own.
Building a Network of Collaborators
Creating custom GPTs has become a way for me to rebuild the connective tissue between tools. Not by merging them, but by giving each one a well-defined purpose. I can define the rules, tone, and structure for how it works with me. That is not memory; it is instruction. But even as static instruction, it creates stability.
I think of my GPTs as a network of collaborators, each with a defined skill, each learning how to work alongside me. A custom GPT is not memory. It is a defined behavior set, a structured prompt written once and followed every time. Memory, on the other hand, is dynamic. It shifts with me. It tracks patterns, preferences, and changes over time. When I say things like I always write in narrative paragraphs, that can be stored as a behavioral preference.
Instructions define behavior. Memory reflects experience. One is fixed. The other learns.
Building the Tension
Global, perpetual memory is not practical. It is not scalable, secure, or sustainable. And beyond the logistics, it does not reflect how humans actually work. I am not always this or never that. I evolve. Sometimes gradually, sometimes all at once.
That is where the friction appears. When I reset memory, I save my full profile first. I compare it to previous profiles and I can see the subtle shifts: what I have added, what I have stopped emphasizing, what has become more important. Those differences are a mirror of my own evolution. But right now, the AI cannot perceive that change as growth. It only sees inconsistency. You end up clarifying again and again, reasserting your context until the new pattern finally stabilizes.
And that is the signal worth paying attention to. When you find yourself repeating the same clarification over and over, that instruction belongs somewhere more permanent. Either in the GPT’s instruction set if it is persistent, in memory if it is behavioral, or at the top of a GPTChain if it is part of a repeatable workflow.
Related: Defining Wins in the Age of AI
That is how you translate friction into fluency.
The Human Factor
When systems forget, we feel forgotten too. When context disappears, it is not just data that gets lost. It is trust. It is like when you share something and realize later the other person did not remember. It is not malice. It is misalignment. The machine does not feel, but we do. And when we project human expectations onto it, attentiveness, consistency, understanding, the breaks register as something more than technical. They register as loss.
That is why continuity matters so much. It is not just a workflow issue. It is a relationship issue between humans and the systems they rely on.
What I Learned While Building This
Here is what surprised me: I discovered custom GPTs almost by accident. I was exploring GPTChain, trying to understand how to structure repeatable workflows, when I realized these were not just pre-built tools. I could build my own. The same foundational model, but with precise guidance that did not rely on memory resetting or context degrading mid-session.
My first reaction was honestly skeptical. Why would I build my own GPT? But once I understood that a custom GPT is essentially a specialized instruction set, a persistent scaffold that holds your rules without forgetting them, it clicked. Each one becomes a collaborator that knows its role. One for structure. One for tone. One for research synthesis. Together, they create continuity without requiring me to be the integration layer every single time.
And yes, there is irony in writing about AI that forgets while working with AI that just forgot my instructions. Again. The frustration I described in the opening? Not theoretical. It happened while I was writing this piece. The system shifted. My formatting rules disappeared. I had to rebuild the context mid-draft.
But that is exactly why this matters. The tools are extraordinary. They are not yet seamless. And until they are, we are the architects, the integrators, and sometimes the ones picking up the pieces when the thread breaks.
Looking Forward
I do not want a future where AI replaces judgment or care. I want one where it complements both, where context flows across platforms, where continuity does not depend on my ability to remember which version of a draft lives where. I want systems that hold structure with grace, not rigidity. Intelligence that turns memory into momentum and adapts without erasing the path that came before.
That evolution would include recognition: a system that could sense a persistent shift in how I write, think, or prioritize, and quietly update the context that shapes how it responds. I do not need a system that knows everything about me. I need one that notices what matters.
What You Can Do With This
The next time your AI loses your context or ignores a rule you have stated repeatedly, pause. That is not just frustration. That is a signal. Ask yourself: is this a pattern? Am I clarifying the same thing over and over?
If the answer is yes, that instruction belongs somewhere more permanent. Maybe it is a custom GPT. Maybe it is the first step in a GPTChain sequence. Maybe it is a saved prompt you paste at the start of every session. Whatever form it takes, you have just identified friction worth solving. That is how you move from reactive to intentional. That is how systems start working with you instead of around you.
AI in Practice Will Keep Evolving
I am still experimenting. My focus now is on refining how I write prompts, defining the roles and boundaries of my custom GPTs more clearly, and learning to leverage GPTChain in ways that reduce repetition without losing flexibility. I am curious about what happens when you treat AI like a creative partner instead of a search engine, when you build structure that adapts instead of rigidity that breaks.
I still get frustrated when systems shift mid-work. I still feel that trust break when context disappears. But now I understand what I am really asking for is not permanence. It is partnership. Systems that notice, adjust, and grow alongside the work we are doing together.
Not endless intelligence. Enduring alignment. Not memory for memory’s sake, but shared awareness that grows alongside me.
Because the goal is not omniscience. It is understanding, the kind that lets both human and machine pick up right where we left off.