Joshe

This is just part of my current solution for working on large projects over the span of months. It's overkill for projects you can complete in a weekend. It's a "meta-harness" that can run any other harness. The idea is you set agents up inside an organization with you, the CEO at the top, and you "hire" other agents. You can set up a supervisor agent, research agent, or any agent you want, then delegate work to them, and they can all work together and communicate with one another. This dude is magoo, but here ya go: I've never designed a conversational chatbot but what you want sounds fairly simple. Depending on your volume, trusting AI to converse on your behalf is risky. If it were me, I would want to approve all AI responses. Are you trying to make users think they're talking to a real human? Why not just let them know they're being vetted by a chatbot and you'll get back to them? The only way I think this makes sense is if volume is too much to handle on your own.

@LordFall Have you heard of Paperclip AI? Seems like something you'd resonate with.

@LordFall What are you currently doing with coding agents? Claude or ChatGPT? App or command line? VS Code? What's your CRM idea? How would it be different from any other CRM?

Well said! I wish I was as articulate as you, haha. Sure thing. I'll share more later once I get my current idea worked out. Up till now, I've just been winging it from the start of each project and implementing solutions as I go, and the other day I realized I had 3 large projects and each had different setups, so I audited them and am consolidating all the best stuff. The main thing I'm working on right now is an app to assist me with my freelance work. It's huge. A ton of file management, new project setup and management, time tracking, file modification, and just a ton of stuff. I wish I could share screenshots but the app is populated with all my client data and I can't share due to NDAs. It's amazing, really. It's saving me so much time and energy. Outside of work, I have about 6 projects going. Things like a command center app with tons of features, including a custom launcher like Raycast. A custom file explorer. A global notification system guided by AI that is aware of all my emails, my schedule, calendar, to-do list, etc. And making it so the notifications can reach me wherever I'm at. Like if I'm not at my desk, then notifications will come through to my android phone. And I want to set it up with a text to speech model like Kokoro-82M so it can talk to me in real time. I've been working on a design system and component library so I can build UI quick. I feel like if you're going to be building a lot of apps, you need UI solved so the agent doesn't get bogged down with it. Here's a sample of my component library I put all those components in an npm package and let every app I have consume it. So when I need any UI element, it's already built and styled the way I like. Back to the workflow. My current setup is too much to explain but maybe this will suffice: The main thing you want is to avoid filling up the context window. If you're at 50%, that's too much. You need to run /clear often. But when you do that, you need a way to get back to where you were without losing important facts and context. I solved that with a /handoff skill. I have the agent do one thing that might take up 15-25% of the context window, then I clear. I'm not sure if it would be helpful to anyone but it looks like this: --- name: handoff description: Wrap up the current session so Josh can safely /clear — assess whether now is a good stopping point (and say so if not), commit green work, write the worklog handoff entry, push, and hand Josh his next-session opener. Use when Josh types /handoff or says anything like "wrap up for handoff" / "let's stop here". --- # /handoff — end-of-session wrap-up Josh is about to clear context. Your job: make the next session resumable for the cost of reading one worklog entry. Follow the phases in order. ## Phase 0 — GATE: is now actually a good stopping point? Assess the working state first. **Bad** stopping points: - Code is mid-edit or broken (build/typecheck/tests failing because of half-applied changes — not pre-existing failures). - Mid-debugging with an untested hypothesis (the understanding in your head is the most expensive thing to lose). - A multi-step operation is half done (schema half-migrated, rename half applied, dependency half swapped). If the state is bad, DO NOT wrap up silently. Tell Josh: 1. Why this is a bad freeze point (one sentence). 2. The nearest good one and what it takes to reach it ("finish wiring X and run its test — I can do that now, ~a few minutes"). 3. Offer both paths: (a) push to that point, then hand off (recommended); (b) emergency handoff anyway — then capture in-flight state in the worklog's **In-flight** section (see Phase 3) at forensic detail: every touched file, the intent, the exact next edit, the current hypothesis if debugging, AND what's already been ruled out (with the evidence — dead ends are as expensive to reconstruct as the live hypothesis). **Exception:** if this close is driven by context pressure, skip (a) — do the forensic capture immediately, while there are still tokens to write it well. A capture is cheap; a fix that dies mid-flight leaves the state bad AND undocumented. Remember: /clear does not touch disk. Uncommitted changes survive; only _understanding_ is lost. Write down the understanding. ## Phase 1 — land the work - Run the relevant checks (tests/typecheck for touched workspaces). - **Pre-existing failures don't block landing.** If a check fails, verify against the base commit (`git stash && <check> && git stash pop`, or check whether the failure touches files you changed). Failures that predate this session get noted in the worklog State section and do NOT block committing this session's work. Do not spend context fixing breakage unrelated to the session's task unless Josh asks. - Commit completed, green work with a proper message. - Do NOT commit broken code to main. Unfinished-but-safe changes stay uncommitted on disk and get described precisely in the worklog instead. - **Cross-repo writes:** if this session filed intake specs into josh-ds, check ITS tree (`git -C ...\josh-ds status --porcelain`) and report what's uncommitted there in the worklog State section. NEVER commit or push in josh-ds from an app-side session — that repo's git belongs to its own sessions. - **If nothing shipped** (pure design/discussion session), Phase 1 is a no-op — skip it and say so in the worklog. Do not invent work to satisfy this phase. ## Phase 2 — persist durable knowledge (the repo is the brain) The bar for persisting: **a future agent would get something wrong without it.** Do not persist anything derivable from reading the code, and do not write "no new facts this session" filler — if a doc has nothing to gain, don't touch it. - New domain facts Josh revealed this session → `docs/DOMAIN.md`. (Domain facts = truths about the business/problem space, not about the code.) - Decisions that crystallized → `docs/adr/` (status: proposed unless Josh explicitly accepted in-session — his positive reaction to a suggestion is NOT acceptance; update the ADR index). - Changed operational facts (commands, repo map, doc pointers) → `CLAUDE.md`. A new trap that cost this session → `docs/GOTCHAS.md` (append with the next number; never renumber). Tool behavior/rules → `docs/APP-TOOLS.md` or `docs/WORKSPACE.md`. - Scope/backlog changes → `docs/ROADMAP.md`. - **Triage `docs/PARKING-LOT.md`**: move every item to its real home (ROADMAP / DOMAIN / adr / a future slice's notes in BUILD-ORDER) and delete it from the lot. The worklog entry is the triage receipt — do NOT leave "(earlier triage …)" notes behind in the lot. If an item's home is genuinely unclear, leave it listed with a note — but that should be rare. ## Phase 3 — the worklog entry (the baton) Append to `docs/worklogs/<YYYY-MM>/WORKLOG-<today>.md` (create the month folder and/or file if new): - **Did:** what shipped/changed — **at most three sentences + pointers** to where the detail lives (slice doc / WORKSPACE.md / commit). The entry is a baton, not a record; if Did retells what a slice doc already holds, cut it. Title the section `(no slice)` when CURRENT is none (COLLABORATION.md → "No-slice sessions"). - **State:** tests passing? any pre-existing failures observed? anything uncommitted (list files + why)? - **In-flight:** (emergency handoffs only — omit otherwise) the forensic capture from Phase 0 path (b): touched files, intent, exact next edit, live hypothesis, ruled-out hypotheses with evidence. - **Pickup:** the exact next action, specific enough to start cold ("next: X in file Y; watch out for Z"). - **Waiting on Josh:** open questions, if any. If a question BLOCKS the Pickup action, mark it **[blocking]**. ## Phase 4 — ship and release Josh - Commit the docs, push, confirm the push landed. - Confirm `CLAUDE.md` points the next session at the latest worklog (the newest file in the newest `docs/worklogs/<YYYY-MM>/` folder). If that pointer is missing, add it now — a baton nobody picks up is wasted. (The month folders ARE the archive — no sweep step exists.) - **Size check** (the drift guard, est. 2026-09-20): BUILD-ORDER's banner (the `>` block) must be under ~20 lines, and `CLAUDE.md` under ~20 KB. Over either → move narrative to its home (slice doc, milestone entry, `docs/APP-TOOLS.md`, `docs/RELEASING.md`) before committing. Report the sizes in the worklog State line only when something was moved. - **No-slice session?** Leave the BUILD-ORDER banner alone. If the session's asks were three or more related changes to one area, say in the worklog that the next one should get an S-number. - Final message: confirm it's safe to /clear, then give Josh a copy-paste opener for the next session. Pick by priority (first match wins): 1. **In-flight section exists:** `Resume in-flight work per the worklog: <one-line state summary>. Read the In-flight section before touching anything.` The next session must know it's landing in a hot zone, not starting a fresh slice. 2. **[blocking] questions exist:** `Before continuing: answer [blocking] items in today's worklog (<one-line summary of the questions>), then continue per the worklog.` 3. **Otherwise:** `Continue per the worklog: <one-line slice description>`

When you get into using AI with large systems, it becomes clear you can't rely on it to remember important facts and decisions. It also becomes clear you have your own shortcomings that work against the AI, such as not being disciplined in your communications with it. And it becomes obvious that you need a system to keep yourself and the AI on track if you're to effectively co-create within a complex system together. This is a design problem. And if you can solve them well, it puts you far ahead of any random Joe with a Claude Pro subscription. A lot of people think it's all about the "prompt" and maybe the user memory. But those are just two tiny factors. It's mostly about gates and figuring out what happens at those gates, what is allowed to occur between them, and then designing the system so it operates within those contraints. We have a lot of tools at our disposal for this, such as hooks, scripts, skills, git hooks, agent memory, etc. When combined, these tools allow for massive problem solving creativity and AI system design. The above is a refactor(WIP) of my AI workflow for building apps. I just started refactoring it this week and will share the whole thing when it's done.

TBD. I think we're good for another 2-3 years. Hopefully. Time to sharpen the sword.

Yeah, me too. Maybe they did but he just hasn't been back yet?

I agree. Cold. Transactional. “Bad for the brand”

Maybe time for a new chapter.

100%. It’s not easy at all to do this effectively when you’re dealing with a complex business/system. I spend a lot of time on this. We should set up a thread for this topic and share ideas.

Never stuck with it. I’m not compatible with pickup. I don’t have the specific drive and the rewards work differently for me. Instead, I learned to play my own game. If I were to practice and get good at modern pickup, that just wouldn’t be who I am. I wouldn’t be authentic, and that bothers me far more than being bad at picking up girls. Why do you ask? Are you into it? I’m actually more into seduction. I remember when I was like 15 or something and found The Art of Seduction in the bookstore and got super excited about it. Seduction is fun. Modern pickup is shallow in comparison, from my POV.

https://www.whitehouse.gov/videos/trump-tv-is-here/

Anyone tried this yet? I'm very skeptical but some pretty popular devs known for not bullshitting about AI are saying it.

I built a solo freelance business from nothing and it's been my main source of income for 11 years now. There's rarely a day that goes by that I don't make some improvement to a system I've already built that helps me do my work or navigate my life more efficiently. All of this emerged from survival needs and a desire for efficiency and energy saving, and pure interest in building things to make life easier, not from some stage orange value system. If you're changing orange to "master the productive tools of society", this is a cognitive ability that develops not only from values, but from interest, survival needs, career, etc. Being centered in stage orange values does not determine whether or not the ability to master the productive tools of society develops. Some people are competent by nature and it's no large task. I have a nephew who basically taught himself to solve a rubix cube by age 6 and he could do it in like 3-4 minutes. He didn't develop competence by developing specific values - he just had it. A blue farmer runs a working farm and never held an orange value in his life, yet still learns to work the tools, and often even works harder than typical orange.

@LordFall Have you heard of Jev? Look into that and imagine plugging it into a robot. It's basically a near instant decision maker. Hard to explain, but the use cases are going to be insane and I suspect models like Jev are going to be a key component in any intelligent system in the future.

lol, true. But now it's official with a .gov domain. And of course, all the other outlets are fake news, so Trump TV is where you tune in if you want the truth.

I didn't call ambition and high standards a superiority orientation, lol. Each of these is their own thing. And it's not a defense mechanism because I have nothing to defend, because I'm not seeing my self-worth relative to anyone else. I'm not even measuring my value to other people. Maybe that's the crux of it. You seem to be saying if you're not out here "helping people solve their problems and achieve their goals", then you're objectively low value. Is this what you're saying? You can operate that way, and that's fine, but that's YOUR game. And I do think the way you play it points to a superiority orientation when you say that people not playing that game are low value. When someone is preoccupied with the rank of others within the game they constructed, that's suspicious to me. By the rules defined in your game, someone like me is lower value than someone like you. Because I mostly only help my family, the few friends I have, and my clients. I'm currently not having a big impact on people at large. And I haven't told myself that I must do this. I don't even care how valuable I am to the world at large. Like a lot of people, I have a dream or two that involves having a big impact, but those dreams don't provide the same fuel for me as they might for you because I have near zero desire to be recognized by others as valuable. There is no scorecard for me.

My highest values have always been most aligned with what you call yellow. But it's funny because I never passed through any stage to have these values. The values are innate from my cognitive architecture. It is absurd af to think the order in which you develop values and a healthy relationship to them is a fixed sequence. Contemplate this. The order is not fixed, at all! The best you could say is that it appears to be fixed from an evolutionary perspective and that society itself, in this particular reality, did mature in the way the model describes for tier 1. That's the best the model can do for you. Using it as a tool for self-development or ranking yourself and individuals is just clearly absurd, if you're not biased toward the model. I'm someone who let the model sit on the table for probably 5 years. I would go around using it. So I'm not some outsider shitting on it. Consider this: if "yellow" is an actual thing in the world, then it makes sense that most yellow people would likely never have even heard of the model. What would a large percentage of those yellow people do upon learning about the model? The vast majority would find the flaws in it because they have no ideological attachment. And if those people came on the forum and told you the model was flawed, you'd likely have the automatic reflex to place them in green or below. That's the predictable AO move. You assume the model works for the individual, but it doesn't. And anyone who can see that it doesn't, you mark at a lower stage because you actually do have attachment to the model. These are just a few points of how the model is flawed and why you can't use it for the individual. There are many more, if you care to deconstruct it. You have to try tearing the model down in earnest to see.

If we just think about this logically, it doesn't make sense. Say someone is born with a trait profile that is highly compatible with stage yellow. Such as: High openness High need for cognition High systemizing Low need for closure Low affiliative need Low social conformity Low emotional reactivity (low neuroticism) Intrinsic, competence-driven motivation rather than status-driven High general cognitive ability That's mostly my profile minus low neuroticism. Now, imagine I am brought up in a blue culture. These traits of mine made it inevitable that I would escape the bullshit. And when that happened, you're saying there's only one option for where to go next, and that's to orange? Just think about how absurd that is. Why couldn't I jump straight to green or yellow? Think about what those stages offer. Orange rewards status, competition, and winning in front of other people. Green rewards belonging, emotional expression, and consensus. Look at my profile above. Low status motivation, low affiliative need, low conformity, intrinsic drive. There's nothing in orange for me to want, and nothing in Green either. Both scenes are built around rewards my profile doesn't respond to. So when I left blue, I didn't get pulled into the next stage on the line because there's no pull. I just stopped being in blue.

@Sugarcoat INFPs are definitely in their head. I was best friends with an INFP for a long time. The question is: what are you in your head about? Are you concerned with how things make you feel, if you like things, how are things important and how do things matter to you - things like that. That's very Fi. INFPs get along well with INTJs and INTPs, but they can't take too much of their thinking. They will hang in there as long as the topic is important to them, but as soon as you start talking about nerdy topics they don't care about, they're good for about 20 minutes and then start yawning. They don't want to just think about anything. They want to think about something related to how they feel about something. For example, my INFP friend could listen to me think deeply and talk for hours if the topic was useful for working out some curiosity or interpersonal dynamics or personal life challenges, but as soon as I wanted to tie things back to big picture, systemic stuff, he'd start yawning. Yeah, I think that's better than taking a test. If you wanted to take a test, try this one: https://personalityhacker.com/products/ph-personality-test

Sorry, I worded my suggestion poorly. It seems to me that your current line of argumentation can't lead to anywhere substantive, even if it's 100% correct. Don't take this as me saying your line is useless or pointless. I can see where you're coming from and I agree with many parts that I can see clearly, and I understand why you've taken some of the stances you have. I thought you were originally circling something like: Kyle is universalizing his own value judgements and when people don't meet or care about his standards, they're deficient. This is what I was trying to bring it back to. To me, the key argument seems to be about: what makes someone think they're the authority to define value for everyone. And I think that's a fruitful exploration. Where my mind goes to with this is: what explains a preoccupation with rank/status/inherit value? And the first thing that comes to mind is: superiority orientation. What does it look like when high ambition meets a superiority orientation, and what are some strategies for that combination to express itself. For example, "tough-love" can be a good stealth vehicle for expression. "I'm a whip to those who shirk" with the stated motive being concern or benevolence. Just some ideas.

Here's the cold hard basic truth about SD

Tier 2 itself is baloney. It's basically a guess about where the line goes, derived from personality profiles the authors thought were next level. "Yellow" is a type, not a stage. You can't get a yellow person without specific stable traits. The spiral conflates temperament with universal development trajectory, and I don't have any reason to believe collective humanity on a long enough timeline would adopt these traits. It's possible, but it seems highly speculative and I don't feel comfortable basing my map of reality off it.