Starting mid-project with Claude has given me an opportunity to learn something new and startling about LLM (Large Language Model) AI, which both Claude and ChatGPT are. With Claude’s direction, I uploaded all relevant files and information I was bringing from work to date. All of that plus the project chats with Claude are represented in this screenshot. I reported on this format in the previous Field Note, but I understand it more thoroughly now and it’s worth taking another look.
Note: Just a heads up that the first half of this field note borders on the geeky. Well, it’s really pretty geeky. But I’m convinced it explains something that is going to be central to the execution of this project and could be very useful to any amateur user of AI — like me — in coming up with personally tailored strategies for using it. The second half should be more fun, with a couple examples of how it’s working out for me.
When I opened the new chat for this Field Note, I asked a few questions to make sure I understood how Claude’s “memory” works within the project. My understanding had been that when I was engaged in a chat with Claude within, say, The Memoir Project folder, Claude would have access to everything within the folder. That’s true, but very incomplete. Here’s the conversation and the light bulb moment.
ME — As you read this prompt, are you simultaneously “reading” everything else in the project folder, including all the chats and the files and the memory notes? Or is it more nuanced than that?
CLAUDE — Here’s the accurate version of what happens when you open a chat:
If you start a new chat inside the project folder — project files, instructions, and memory digest are all loaded as soon as you start writing the prompt. If you start a new prompt inside an existing chat inside the project folder, the same contents are loaded along with the full history of that chat.
If you start a chat on the Claude.ai Home Screen — not in a project folder — there is nothing to load at first, and then only the history of that chat as you continue the conversation.
ME — When you say everything inside the project is loaded from the first prompt, how should I understand the term "loaded"? I get that it is loaded for you, but loaded where? Into what?
CLAUDE — Good question, and it gets at something genuinely interesting about how I work.
“Loaded” means assembled into my context window — which is essentially the span of text I can “see” and reason about at any given moment. Think of it less like a filing cabinet I can reach into and more like a table I’m working at: everything relevant gets placed on the table at the start of each response, I work with what’s there, and then the table clears. Next prompt, everything goes back on the table again.
The context window has a size limit — a maximum amount of text it can hold at once. For most projects it’s generous enough that the project files, instructions, memory digest, and chat history all fit comfortably. But on a very long chat with very large files, you could theoretically approach that limit.
So “loaded into my context window” is the precise answer. But for the Field Note, “assembled and available for that response” might be the more readable way to put it.
So, when the light bulb came on, my first thought was that now I get the importance and the power of the project folder. Obviously, this isn’t your father’s search engine. This environment isn’t for simple Q&A. In Claude’s words, it’s a “sustained intellectual collaboration, with each exchange building on everything preceding it.” I would add that when research is also involved, as it is with the memoir, the value of the collaboration is magnified.
My second thought was, “Wow, that must take a huge amount of electricity! No wonder the proliferation of data centers is concerning.” This is a topic that deserves a deeper dive, so I’ll stick a pin in it and schedule a response down the road a little.
Read the memoir story titled The Mother Road: Ch. 1 Leaving Home
We’re finally ready to get back to writing, or at least Claude is.
CLAUDE — The agreed method: Question-driven, section by section. We develop Loading Up first, using targeted questions to surface your memories and voice, rather than drafting wholesale from the notes.
Ready to start on Loading Up when you are. First question: When you picture that morning — the DeSoto in the driveway, your dad at the trunk — what’s the first image that comes into focus?
ME — That raises a question that will apply again and again as we proceed, especially from when I’m so young: Do we distinguish between images coming into focus from certain memory, or from how I imagine it was? In fact, I think it would be helpful to come up with a more detailed framework than just “question-driven.”
I’m thinking that what I just learned from Claude provides the means to create a framework that will allow the work to go much faster and stay focused. In fairly short order I wrote out an outline of how my thinking about the memoir has evolved. Claude made a couple of good revisions, then we agreed on a completed description of the approach.
I asked Claude to compose a compressed version just for its use in the Instructions panel. It did, then I pasted it into the panel. Then I pasted what Claude called the “full articulation with nuance and explanations” into the project knowledge document, which we’ve agreed to abbreviate PKD. Here it is:
The Memoir Method for this project (added April 2026)
A memoir based on personal memories alone presents two problems: pre-birth family history and early childhood is largely inaccessible, and memory without context makes for thin reading. This project addresses each through a five-part method.
1. The Bones — what is known Personal memories and family stories; photos with and without contemporaneous captions; memorabilia and physical and digital newspaper clippings; public records and genealogical research.
2. The Dialogue — what the collaboration brings to the surface Questions Claude asks to stimulate Michael’s memories and expand what is known. This is not a research function — it is the primary mechanism by which the collaboration unlocks material that exists but hasn’t yet surfaced.
3. The Flesh — what is inferred and probable Questions Michael asks Claude to research; period detail to answer those questions; logical inferences that connect the dots. Inferences flagged as such — “most likely,” “period-appropriate,” “historically plausible.”
4. The Context Research into local, regional, and national events and conditions that illuminate the world the personal history moved through. Selected with the project’s larger purpose in mind: to preserve an authentic record of the America that strived, however imperfectly, to live up to its founding documents.
5. Storytelling Tell the most interesting story possible while staying faithful to what is known, what is inferred, and what the context reveals. The bones and flesh together; the personal and the national braided.
I’m finding one of the most fruitful avenues in communicating with Claude is to occasionally ask how it works and its perspective on our process. I did that here and got a great answer that validated the decision to include it.
ME — Do you feel this is a helpful addition? And if so, how?
CLAUDE — Yes, genuinely useful — and in a specific way.
Most of what’s in the Instructions panel and the PKD tells me how to behave and what’s been decided. This framework does something different: it tells me how to think about the work itself. That’s a different kind of orientation.
Without it, I come to each session knowing the facts of the project and the behavioral rules, but the underlying method has to be inferred from examples — from “An Ordinary Day,” from the cloakroom, from decisions made in past chats. This makes it explicit. It tells me what we’re actually doing and why, not just what’s been done.
Practically, it will help most at the start of new vignettes, when we’re furthest from established examples and closest to blank-page decisions. A new topic, a new set of memories, a new historical context — and the method is right there as a shared reference point rather than something we have to re-establish through conversation.
It feels good to get that established. It feels even better to get this vignette finished. Here are a couple examples of how Claude and I worked together to get there.
Thanks to a suggestion from my sister, Pam, I’d started a subscription to Newspapers.com. This site touts 35,000+ digitized, searchable newspapers from 1690 (I know!) to 2025. I’d been spending enough time already searching just the Monroe local newspaper to realize how rich a source this was going to be — and how much time could be spent in countless rabbit holes. Seems the kind of thing Claude could help speed things along. So, I asked:
ME — I’ve been going through Newspapers.com and finding lots of tidbits in the Monroe Evening News 1952-1953. Since it requires a subscription, I assume you can’t access that site?
CLAUDE — Correct — I can’t access Newspapers.com even with a subscription. It’s behind a login wall, so it’s not fetchable the way an open web page would be.
Hmm, well, no harm in asking.
CLAUDE — But what you’re finding there sounds potentially valuable. A few thoughts on how to use it:
The Monroe Evening News clippings could serve exactly the role that period detail plays in your best writing — not as historical lecture, but as a quick grounding note that puts the reader there. A headline glimpsed, a price from an ad, a weather report. The kind of thing that costs one sentence but earns a lot of authenticity.
The most useful thing you could do is paste the relevant tidbits directly into our chat as you find them. I can help you evaluate which ones earn a place in the vignette and where they might land — and which ones are interesting but belong in your research file rather than the prose.
What have you found so far that feels promising?
ME — My mother was a county block worker for the 1952 March of Dimes, one of about 400 women whose names are all listed by area under the photo. My father’s school (principal of Custer Junior High) student council also sold ice cream bars to raise $200 for the “polio fund” at the same time. I’m going to attach clippings to see if they are visible to you and might be useful.
CLAUDE — Both images are clear and readable. And what a find — especially the second one.
The Mothers’ March photo is evocative period texture — 400 women going door to door in Monroe on a winter evening, your mother among them. That’s a vivid detail about who your parents were in this community just before they left it.
These photos may resurface when I get back to vignettes from 1948-1953. A small town newspaper in that era published a remarkable amount about community life and it’s members that would be unthinkable in a newspaper of today. Come to think of it, the Monroe Evening News was the social media of the ‘50s. In a short time I found numerous mentions of both parents that establish a profile of their life in Monroe. None of these details appear in this current memoir vignette. However, they were the justification for this paragraph:
At some point before my parents locked the door and got in the car, a couple of the neighbor women appeared on the sidewalk in their wool coats to say goodbye. Most farewells had taken place over the previous couple weeks — it was remarkable how many connections had been made in just over four years of living in Monroe. They chatted briefly and hugged each other. These were neighbors who knew and cared about each other.
CLAUDE — Ready to start on the Loading Up scene when you are.
ME — I’d like to find images of a ‘49 DeSoto. Interior in particular seems hard to find. Any chance that’s something you can do?
CLAUDE — Let me look.
Claude took a good 30-40 seconds to come back with 11 photos. I used 3 in the vignette, including this one — which was important for showing the space on the floor of the back seat that would be layered with sleeping bags and serve as separate, cozy space for my sister and me on the long trip.
I entered into this project with AI fully expecting that I would be asking a lot of questions. I also learned quickly that giving good prompts involves more than that: giving the chatbot plenty of context and parameters along with the questions improves the quality of response. But I’m surprised to find that collaboration with AI depends upon the chatbot asking me questions, not only to stimulate my own thinking and memory — but because two-way questioning is as basic to AI collaboration as it is to human collaboration.
Read the memoir vignette titled The Mother Road: Ch. 1 Leaving Home