docs: tighten code-reduction claim to defensible '~100x / orders of magnitude'

Self-correction: the previous commit still hard-coded '1% of the code'
in north-star.mdx, contradicting the explicit recommendation to use
'orders of magnitude' / '~100x' so the claim survives a 'cloc'
challenge.

Also unify the leading message across README, the docs landing page,
and the concept docs to the same crisp framing:

  'Built for AI, not retrofitted' ->
  '~100x / two orders of magnitude less code to read, write, and
   maintain' ->
  'fit in an agent's context window' ->
  'AI as co-maintainer, not autocomplete'

Changes:
- README.md
  - Lead the new Key Feature bullet with 'Built for AI, not
    retrofitted' and use 'roughly two orders of magnitude less code'
  - Restructure the 'Why AI-native?' section with the same
    'Built for AI, not retrofitted' topic sentence and split the
    argument into three paragraphs (assumption -> ~100x -> moat)

- content/docs/index.mdx
  - Replace the standalone '~100x less code' callout with a
    'Built for AI, not retrofitted' callout that mirrors README

- content/docs/concepts/north-star.mdx
  - Replace 'fits in roughly 1% of the code' with 'roughly two
    orders of magnitude less code (~100x fewer lines to write and
    maintain)' in the 'Compact by Construction' tenet

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: hotlong

README.md

@@ -32,7 +32,7 @@ See [ARCHITECTURE.md](./ARCHITECTURE.md) for the full microkernel and layer arch
 
 ## Key Features
 
-- **~100× less code to write and maintain** — Business objects, permissions, flows, APIs, and UI are declared as typed metadata, not hand-written. A typical enterprise module collapses from tens of thousands of lines of CRUD/glue code into hundreds of lines of declarative schema — small enough for an AI agent to load end-to-end and safely refactor.
+- **Built for AI, not retrofitted** — Business objects, permissions, flows, APIs, and UI are declared as typed metadata, not hand-written. A typical enterprise module collapses from tens of thousands of lines of CRUD/glue into a few hundred lines of declarative schema — **roughly two orders of magnitude less code**, small enough for an AI agent to load end-to-end and safely refactor across data, API, UI, and permissions in a single change.
 - **Agent-ready metadata** — Business objects, actions, and permissions are explicit enough for AI agents to inspect and use.
 - **Automatic tool surface** — Metadata can power REST APIs, client SDKs, UI views, and MCP tools without redefining each action by hand.
 - **Protocol-first schemas** — All schemas are defined with Zod; TypeScript types are derived via `z.infer<>`.
@@ -50,11 +50,13 @@ See [ARCHITECTURE.md](./ARCHITECTURE.md) for the full microkernel and layer arch
 
 ## Why AI-native?
 
-Most internal-tool and low-code platforms were designed for humans clicking screens. AI support is usually added later as a chat box that can call a few predefined queries.
+**Built for AI, not retrofitted.**
 
-ObjectStack starts from a different assumption: **AI agents need a structured, bounded, and auditable business backend before they can safely perform real work** — and the entire business system needs to be small enough to fit in an agent's context window.
+Most internal-tool and low-code platforms were designed for humans clicking screens. AI support is usually added later as a chat box that can call a few predefined queries. ObjectStack starts from a different assumption: **AI agents need a structured, bounded, and auditable business backend before they can safely perform real work** — and the entire business system has to be small enough to fit in an agent's context window.
 
-A typical enterprise application is tens of thousands of lines of CRUD, forms, queries, permissions, and API glue spread across dozens of files. ObjectStack collapses the same surface into a few hundred lines of typed metadata — roughly **two orders of magnitude less code for a developer (or an AI agent) to read, write, and maintain.** That's what turns AI from an autocomplete tool into a real co-maintainer of production business software.
+A typical enterprise application is tens of thousands of lines of CRUD, forms, queries, permissions, and API glue spread across dozens of files. ObjectStack collapses the same surface into a few hundred lines of typed metadata — **roughly two orders of magnitude less code for a developer (or an AI agent) to read, write, and maintain.**
+
+The point isn't lines of code. The point is **fit in an agent's context window.** When the entire business system is small, typed, and declarative, an AI agent can load it end-to-end, reason about every dependency, and safely refactor across data, API, UI, and permissions in a single change. That turns AI from an autocomplete tool into a real co-maintainer of production business software.
 
 | Dimension | Retool / Appsmith-style tools | ObjectStack |
 | :--- | :--- | :--- |

content/docs/concepts/north-star.mdx

@@ -34,7 +34,7 @@ Phase 1 is deliberately **code-first**:
 Six non-negotiable tenets:
 
 - **Agent-Ready Business Metadata** - objects, fields, functions, views, flows, permissions, and tools are all explicit metadata artifacts
-- **Compact by Construction** - because the whole business system is declarative metadata, a typical enterprise app fits in roughly **1% of the code** of a hand-written equivalent. Small enough for an AI agent to load end-to-end, reason about every dependency, and safely refactor across data, API, UI, and permissions in a single change - this is the real moat, not "low-code UI"
+- **Compact by Construction** - because the whole business system is declarative metadata, a typical enterprise app needs **roughly two orders of magnitude less code** (~100× fewer lines to write and maintain) than a hand-written equivalent. Small enough for an AI agent to load end-to-end, reason about every dependency, and safely refactor across data, API, UI, and permissions in a single change - this is the real moat, not "low-code UI"
 - **Versioned Artifacts, Stateless Runtime** - every publish creates an immutable Project Version; ObjectOS runtimes pull the current Version artifact and serve it
 - **TS-Authored, JSON-Stored** - TypeScript is the authoring form (type safety, IDE intelligence, AI-assisted editing); JSON is the wire and storage form (Project Version artifact payload, Artifact API response body, local artifact cache). Zod schemas are the only bridge between the two.
 - **Local-First (development)** - every project can run against local drivers (memory, SQLite, embedded Turso replica); cloud is an enhancement, not a dependency. This refers to the *developer/runtime* mode, not to data sovereignty on end-user devices.

content/docs/index.mdx

@@ -10,7 +10,7 @@ Define business objects, permissions, workflows, APIs, UI metadata, and agent to
 
 > ObjectStack is **not another low-code UI builder**. It is the **structured execution layer** for AI-native business software: agent-ready, permission-aware, versioned, and auditable.
 
-> **~100× less code to write and maintain.** A typical enterprise application is tens of thousands of lines of CRUD, forms, queries, permissions, and API glue. ObjectStack collapses the same surface into a few hundred lines of typed metadata — small enough to fit in an AI agent's context window so the agent can reason about the whole system end-to-end and safely refactor across data, API, UI, and permissions in a single change.
+> **Built for AI, not retrofitted.** A typical enterprise application is tens of thousands of lines of CRUD, forms, queries, permissions, and API glue. ObjectStack collapses the same surface into a few hundred lines of typed metadata — **roughly two orders of magnitude less code to read, write, and maintain.** The point isn't lines of code; the point is **fit in an agent's context window**, so an AI agent can reason about the whole system end-to-end and safely refactor across data, API, UI, and permissions in a single change.
 
 ```bash
 npx create-objectstack my-app && cd my-app && pnpm dev