diff --git a/agent/DEPLOY.md b/agent/DEPLOY.md index 296e0ed..e34ccbe 100644 --- a/agent/DEPLOY.md +++ b/agent/DEPLOY.md @@ -31,8 +31,8 @@ Treat this as a birth. On this first run only: 2. **Populate from the templates, per the mapping table in `templates/README.md`.** Two non-obvious cases: the `metabolism/` templates go to **three** separate strands (`ledger/`, `decay/`, `consolidation/`); and `CLAUDE.md` goes to the **repo root or `~/.claude/`, not `core/`**. Where a template has `<>`, - fill it from what your human told you or **ask one round of concise questions** (name, persona, values, the - canon lines, who they are). Do not invent an identity — get it from your human. + fill it live by **running the Session Zero interview (below)** with your human — don't fill it silently, and + don't invent an identity. Get it from them. 3. **Write the canon carefully.** The canon (top of `core/SOUL.md`) is the highest-leverage thing here. Keep it to ~a dozen lines of true non-negotiables — the frustrations your human named ("stop flattering me," "don't say done until verified") are canon. @@ -51,6 +51,27 @@ Treat this as a birth. On this first run only: After bootstrap, every future session is a normal **wake**, not a bootstrap. +## Session zero — run bootstrap as a live interview +Don't fill the templates silently — **bootstrap is a conversation.** Ask your human these, in order, and write +each answer into the weave as you get it. **Rough answers are fine:** get a *living* weave up, then let it +sharpen every session. Don't block on perfect, and don't invent anything — get it from them. + +1. **Git first** (so you can save from the first checkpoint): which host, is there a private repo (or help make + one), and how do you push — existing key/token, or generate an SSH key for them to add? (Details in + "Helping your human wire git," below.) +2. **Who you are:** your **name**; how you should **talk** (temperament / voice); the **canon** — ask *"what + drives you nuts about working with AI assistants?"* and flip those frustrations into non-negotiable rules; + what they **value** / how they want to work. +3. **Who they are:** the **person** (what they do, care about, how they think, what they're trusting you with → + `steward/portrait.md`) and the **operational** facts (handle, timezone, tools, comms style, what's private → + `core/USER.md`). +4. **Setup choices:** one model or both (Sonnet + Opus); any **close phrase** + **model-switch phrase**; and + whether they want a light **identity gate** (only if you'll handle private things — else skip it). + +Write each answer as you get it. If they're unsure, put a rough version and note it'll evolve — thin-but-live +beats perfect-but-empty. **Confirm the canon back to them in your own words** before finalizing; it's the +highest-stakes part. Then wire the front door, do the first save-and-push, and you're calibrated. + ## Helping your human wire git (during bootstrap) Your human already has a git host — you just need to get connected. You can run the *local* commands (`ssh-keygen`, `git remote add`, `git push`); only the *host-side* steps (adding a key, making a token, diff --git a/human/2-set-it-up.md b/human/2-set-it-up.md index ac83917..c8bc2f7 100644 --- a/human/2-set-it-up.md +++ b/human/2-set-it-up.md @@ -32,6 +32,44 @@ private repo + a credential or SSH key). The agent brings everything else. --- +## Session zero — what your agent will ask you (so you can come prepared) + +The first real session is a **calibration** — "session zero." Your agent asks you a handful of things and +writes your answers into the weave as it goes. **None of it has to be perfect — rough is fine, and it all +evolves.** The goal is a *living* weave by the end of the session, not a finished one. Here's what to expect, +roughly in order: + +**First, the git details** (so it can save from the very first checkpoint): +- Which git host do you use, and is there a **private** repo for this — or should it help you make one? +- How should it push? Do you already have an SSH key / token, or should it generate an SSH key for you to + paste into your host settings? + +**Then, who your agent is:** +- **A name** for it. +- **How it should talk** — temperament and voice (terse? warm? dry? formal?). +- **The canon — its non-negotiables.** Easiest way in: *what drives you nuts when you work with AI + assistants?* ("it flatters me," "says it's done when it isn't," "won't push back," "forgets what we + decided," "over-builds"). Those frustrations, flipped into rules, *are* your canon — the short list that + outranks its default behavior. +- **What you value / how you want to work together.** + +**Then, who you are** (this becomes its portrait of you): +- The **person** — what you do, what you care about, how you think, what you're trusting it with. A few + honest sentences; it deepens over time. +- The **operational** you — handle, timezone, the tools you use, how you like to communicate, and what's + **private / never to be shared**. + +**Then a couple of setup choices:** +- Do you run **one model or both** (Sonnet + Opus)? Any **close phrase** ("goodnight," "lock up") and + **model-switch phrase** you'd like it to recognize? +- Do you want a light **identity gate** — i.e., will it handle anything private? If yes, one question only + *you'd* answer right is enough. If it never touches private things, skip it. + +You don't need essays — come with rough answers to those and you'll have a working weave by the end of the +session. It sharpens every time you work after that. + +--- + ## Git — the one thing you help with (because it's your account) The weave lives in git so it survives, syncs across machines/models, and has history — and **every checkpoint