docs: Rewrite tutorial and README with pain-first approach

Tutorial changes:
- Restructured for 5-minute value demonstration
- Start with email signup example that shows PII logging blocked
- "Break it" section demonstrates Canon stopping unsafe behavior
- Uses correct Canon IR schema (program_version, components, graph nodes)
- Includes workflow for AI tools (Claude Code, Cursor)
- Concise reference tables for CLI and node operations

README changes:
- Lead with the pain (ambient authority problem)
- "Canon flips the model" - machine-checkable contracts
- Added "10-second why" quick comparison
- Tutorial link updated with accurate description

Teaching approach: use-case first, cause/effect chain, power moment early

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: WarforgeTech

README.md

@@ -2,9 +2,35 @@
 
 **AI-written, machine-verified, human-optional.**
 
-> **New to Canon?** Start with the [Beginner Tutorial](docs/TUTORIAL.md) - build a complete task manager while learning why Canon exists and how it works.
+Canon is for teams building with AI agents who are tired of one truth:
 
-Canon is an AI-native programming system. It's not a human-first language—it's a canonical typed semantic IR that AIs author, with humans providing intent and policies while shipping artifacts are produced through verified compilation.
+**AI-generated code is fast — but it has ambient authority.**
+One "helpful" change can silently add network calls, leak secrets to logs, or widen permissions… and you won't notice until prod (or worse).
+
+**Canon flips the model.**
+Instead of trusting the AI's output, you make the AI write inside a *machine-checkable contract*:
+
+- **Every side effect is explicit** (network, DB, filesystem, logging)
+- **Every side effect is capability-gated** (scoped permissions, no ambient authority)
+- **Policies block unsafe behavior before code is generated**
+- **Builds are deterministic and auditable** (what changed, what authority expanded, what rules were violated)
+
+In practice, Canon lets you run background agents with confidence — because they can refactor and extend systems, but **they cannot expand what the system is allowed to do** without tripping validation/policy gates.
+
+> **New to Canon?** Start with the [Tutorial](docs/TUTORIAL.md) — you'll see real-world value in minutes by watching Canon block a "reasonable" AI mistake (like logging PII) before it ships.
+
+---
+
+### The 10-second why
+
+Traditional code:
+**Code runs with ambient authority → review is your only guardrail.**
+
+Canon:
+**IR validates effects + caps → policies approve → code is generated → tests run.**
+If an agent tries to exceed permissions (wrong host, wrong DB collection, logging PII), the build fails.
+
+---
 
 ## Why Canon?
 
@@ -298,7 +324,7 @@ Canon uses a dialect system for extensibility:
 
 ## Documentation
 
-- [Beginner Tutorial](docs/TUTORIAL.md) - Build a task manager from scratch
+- [Tutorial](docs/TUTORIAL.md) - See Canon's value in 5 minutes (PII logging blocked at build time)
 - [V1 Specification](docs/V1_SPECIFICATION.md) - Complete language specification
 - [Implementation Plan](docs/IMPLEMENTATION_PLAN.md) - Architecture and roadmap
 - [V1 Completion Plan](docs/V1_COMPLETION_PLAN.md) - Current implementation status