My File System Was a Disaster. Here's the One I'm Building to Replace It. I want to be upfront about something before I get into this: what follows is not a finished system I've been running for years and am now generously revealing to you. It's the system I'm actively building right now, because the old one finally broke under its own weight. Here's what broke it. I went looking for a cover concept file from an earlier book. It wasn't in the book folder. It was in a "Graphics" folder from eight months ago that also had three other books' covers in it, none labeled clearly enough to tell them apart at a glance. The marketing copy for that same book was in a completely different folder tree, because I'd started using a new tool partway through and never went back to reconcile the old stuff. Fifteen minutes of searching for one file I knew existed. That's the tax you pay for not deciding on a structure up front, and I'd been paying it quietly for a long time. So I sat down and asked the obvious question: what's actually going in these folders, and what's the smallest set of rules that keeps it findable six months from now when I've forgotten the details? The core idea: Projects is the top, then everything nests by type Books aren't the only thing I'm keeping track of. There are coding projects, there's a growing pile of AI prompts and skill files, there are short stories that don't need the full novel treatment, and there's a permanent junk drawer of half-formed ideas that aren't committed to anything yet. Trying to organize all of that around "books" was the first mistake, because a lot of my actual work isn't a book. So the true top level is just **Projects**, full stop. Not around the tool that made something, not around the date, not around whether it's "writing stuff" or "marketing stuff." Whatever kind of thing it is, fiction or code or a stray idea, it lives inside its own project folder, not scattered across whatever pile happened to be open when I made it.

Do we need to have a class on book covers in WCP? There are a couple ways to do it and I'm sure I'm not doing it the best way yet, but I'm glad to share what i know in a Q&A format. I just need to know a good day/time for the most folks to participate and we'll record it for the rest. I'm getting pretty good results from the ones I show you all with very little effort. I'm working on a way to give more/easier control over type by using layers, and image under the type. These are really low effort below. They all could use some touchups.

Stop Guessing at Your Comps — Reverse-Engineer Them Instead Topic: Using Book Reporter (CONAN) and Series Reporter (SONJA) to forensically analyze comp titles before you write a word of your own story The problem this solves Most of us pick comp titles the same way: we read a book we loved, we feel something, and we say "I want to write something like that." Then we sit down to plan our own story and realize "like that" was never actually specific. Was it the pacing? The trope execution? The voice? The way the series built across four books instead of one? Vibes aren't a blueprint. If you can't name exactly what a comp title is doing — structurally, at the sentence level, across its beats — you can't reliably reproduce what made it work, and you definitely can't improve on it. That's what Book Reporter and Series Reporter are for. They're the forensic layer of the Professional Writing System — the tools you run before Phase 1 (Story Development Room) to turn "I want something like this" into an actual architecture you can build from. The two tools, and how they're different Book Reporter (CONAN) analyzes one book. He reads it the way a mechanic pulls an engine — not to admire it, but to understand exactly what's load-bearing and what's cosmetic. He produces a Forensic Morphology Report: 15 layers covering structure, character architecture, prose voice, world-building, tropes, emotional design, and hooks, plus: A Beat Rhythm Map — a chapter-by-chapter tension chart that shows you exactly where the book accelerates, where it breathes, and where it stalls (dead zones, flagged by name) Genre Beat Benchmarks — where this book's inciting incident, midpoint, dark night, and climax land as percentages of total length, compared against genre norms A Prose Quality Score Card — eight dimensions scored 1–10, so "the writing is good" becomes "voice distinctiveness is an 8, but foreshadowing/payoff execution is a 4, and here's why" A Reconstruction Brief — the condensed DNA of the book (genre, structure, archetypes, thematic argument, world type, tropes) formatted to drop directly into Story Development Room, plus 2–3 original seed concepts that share the book's structural DNA without copying it

Because time alone and quiet is hard to come by. I am about to start going to my car to do this. But I can ideate, write, read.... and code no matter what. So I did a thing.... Trainings, Onboarding, better documentation are all priorities and being added to daily. But in the background my buddy Claude is churning along on a few things... Next Priorities are marketing, LayoutCrafter (the Vellum/Atticus tool) which I had some layout issues with to get all the extras that Romantasy and modern books now have, images in the backgrounds, fancy chapter headings, sprayed edges, forced edges (neat trick that one), etc. In doing more research on this I came across a few things that tied into some future roadmap items. I've mentioned this before that I started writing again a few years ago with a fascination of Visual novels created in Ren'Py and then came Ai. About six months ago I started noodling on how to do this easier and write better and WordCrafter.Pro was born and continues to evolve. I am trying NOT to change much in its base functionality to keep the learning curve light on the basic writing side but instead use the plugins to do the "optional" additions AudioCrafter for audiobooks, BookCrafter as an automated writing tool, the unfinished tools, Layout Crafter for book finishing, ImageCrafter for higher end covers, graphics, and POD or DIY merchandise, MarketCrafter for the full marketing plan and social media mastery, PathCrafter for Interactive/Branching Fiction and the three just research projects so far GameCrafter, VideoCrafter, BookWorlds, and a couple others that are notes on a napkin. The goal is a one stop shop. We may not do everything here but having to learn one tool that does most helps us all be more productive So a teaser of my last few days is below. And yes I have been editing furiously two books as well PathCrafter for interactive and branching fiction. At it's simplest it is a Choose Your Own Adventure book engine. But I'ma glutton for punishment and can't leave it at just that. So you can also create game books with encounters, combat, dice rolls, NPC's with timelines and agendas they follow. Both of these formats can be read/played online or exported as an epub, pdf or html file with the choices on each page and "If you have the lantern go to page 12, Otherwise got ot page 23". The gaming version has extra pages to cover those needs, including a way to generate a random number if you do not have dice. Cool eh?

I was looking at the Error logs for WordCrafter.Pro this morning and I'm seeing some trends in the last several days. If you are having issues with errors let me know. I built this back side log so I can be a little proactive when folks are having issues but not saying anything. Sometimes it's the program, sometimes it's the ai model and the provider. And yes sometimes it's the guy sitting behind the coding console listening to his buddies Claude or Gemini gas lighting him. "I can't fix it if I don't know it's broke" was a sign in an early shop I worked in and I've never forgotten it. I don't have an easy way to pull how much $$ you have left on an api key but I can try to make the error messages you see make more sense. Something like "Hey add more $$ to your openai key" I renew the list of models about once a week to cover anything new from our providers and I have a couple of tests I run to see if they work in WCP before you see them. The failures get deactivated but some of them slip through (sigh..more work developing better testing). NONE of the gpt5 models passed this morning. Not sure what has changed on their side or this one so I will do more testing. Most notably I'm seeing failures in the reasoning and higher end models mostly. Fable, gpt 5.6 dol, luna and weirdly gpt-4o-mini. They are blowing the context window for the OUTPUT call. So the reasoning it is doing is taking a huge amount of tokens and not giving a full answer which makes me wonder if this is by design to make openai more money costing us for the reasoning to get better answers but not really. I'm thinking also that the increased guard rails on the system prompts that these models use before we send our prompts through are stealing some of our context windows. The system prompt for Anthropic's Claude Fable 5 is approximately 120,000 characters long (roughly 30,000 tokens consumed before the user types a single word). This is why they have started caching repeated prompts not to save us money, but to save face when they have to put stronger rules in place that takes up what we have to use.