Replace Vite/React scaffold with Go build spec

- AGENTS.md: build spec for Paperclip (constraints, conventions, 7 phases)
- docs/phase-1..7: per-phase work, DoD, out-of-scope, risks
- reference/: frozen decisions, stack+ports+budgets, content map, acceptance tests
- agents/: persona and security policy drafts
- Retires the React scaffold; history retained as record of the false start
This commit is contained in:
Sam Rolfe
2026-10-26 16:02:35 +11:00
parent 35a3097042
commit b267e55f8c
33 changed files with 1270 additions and 1223 deletions

64
reference/content-map.md Normal file
View File

@@ -0,0 +1,64 @@
# Content map
## Navigation — six areas
| Nav | Area key | Target role | Contains |
|---|---|---|---|
| **AI & Agentic Systems** | `ai` | AI / LLM Engineer | harnesses · subagents & skills · memory · model routing & cost · RAG & retrieval · voice · guardrails · agent observability (TUIOS) |
| **Platform & Infrastructure** | `platform` | Platform / DevOps Engineer | NixOS & declarative config · Nix packaging · Docker estate · networking · storage & backups · observability · signage infrastructure |
| **Edge & Devices** | `edge` | Edge / IoT Engineer | edge architecture · LoRa · Zigbee · sensors & actuation · audio distribution · cameras · the failures |
| **Products** | `products` | — | Audas Media / Display Screen Media · WebsiteBuilder · Where-Woof |
| **History** | `history` | — | 2000–2014 client wall, agencies, engagements |
| **About** | `about` | — | narrative · 2020–2026 · non-IT background · education · interests · contact |
## Positioning
*"Twenty-five years shipping software. Now building agent systems, the platforms under them, and the hardware at the edge."*
Support line: *…and it all runs unattended.*
Location: **Melbourne**. Flexible — remote, hybrid, office, travel.
## Depth levels
- **L1** — one screen, no scroll: claim · three metric chips · tech chips · one link.
- **L2** — capability statement · what's actually run · architecture diagram · evidence table · trade-offs · drill-downs.
- **L3** — artefact: code excerpt, diagram, screenshot, recording, log, ADR.
**Rule:** every L1 claim has a metric and at least one L3 artefact. Every L3 artefact is ≤ 3 clicks from landing.
## Metric chips (approved values)
| Area | Chips |
|---|---|
| AI | 16+ pipelines (10 n8n/Prefect/LangGraph · 6 Paperclip) · 6 providers behind one gateway · 8 audio endpoints |
| Platform | 50+ containers · 4 hosts · Borg + Kopia + AWS, restore-tested |
| Edge | 20+ nodes (10 ESP32 · 2 custom Zigbee routers · 8 Pi) · 9 zones · 20 automations |
| Products | 3 businesses active (12 adopted over time) · Where-Woof deployed, pre-market |
## Factual corrections — do not undo
- **3** businesses active, not 12. Twelve was cumulative adoption.
- **Where-Woof** is deployed but **has not gone to market**. Not commercial.
- Drop "42 devices" and "~800ms end-to-end" — unverified.
- **Diageo** (not "Diajio"); **Baileys** Irish Cream.
- BBC National Archive was an **internal tool** — describe, no screenshot.
## Failures to keep in
Lizard feeder destroyed by the lizard (rebuilding with plastic containers) · garden cameras postponed, parts arrived · doorbell being rebuilt, adding a ToF sensor · garden automation partly manual.
These are evidence of production experience. Do not soften them.
## Corporate framing rule
Headings name the capability; product names are evidence beneath it.
> ❌ "ESP32 and Zigbee and LoRaWAN"
> ✅ "Distributed edge computing — constrained devices, custom radio, sub-second actuation"
> ✅ …with `ESP32 · Zigbee · LoRaWAN · MQTT` beneath as proof.
## Sources
`../resume_ai_system/plan/EVIDENCE-NOTES.md` (authority for facts) · `draft-content.md` (client wall, recovered site content) · `20-content-spine.md` (areas and claims) · `old_projects.md` (code exhibits, IoT grouping) · `resume_2025.docx` (2000–2020 engagements).
Read-only. Copy what's needed into `content/`; never link to these paths from the site.