DoD satisfied (evidence in AUD-142): A1 with no AI services, one binary, deterministic templ generate, 6 L1 + 6 L2 + artefact pages, FTS5 search, Lighthouse 100/100 mobile and desktop, <100ms first byte, stage panel driven by route or stream, print legible.
Ai Resume — Paperclip build directory
This is the working directory for the Paperclip project Resume Ai. Paperclip builds here. Everything needed to build is in this folder; nothing outside it is required.
Relationship to the planning folder
| Folder | Holds | Status |
|---|---|---|
/home/sam/paseo/projects/resume_ai_system/ |
The why — research, cull decisions, stack rationale, evidence notes, content drafts | Planning. Not the build. Sam works here |
/home/sam/paseo/projects/resume_ai_system_paperclip_build/ |
The what — build spec, phase documents, reference material, and the site itself | This folder. Paperclip works here |
The planning folder is read-only reference. Do not edit it from here, and do not make the build depend on it — anything needed must be copied in.
Start here
AGENTS.md— the build spec. Constraints, conventions, and the phase list. Read it before anything else.docs/phase-N-*.md— one document per phase: work, Definition of Done, out of scope, risks.reference/— frozen decisions, stack and budgets, content map, acceptance tests.
Phases
| # | Phase | Ships |
|---|---|---|
| 1 | Content source of truth | content/ + validator |
| 2 | Mode A static site | Browsable pre-rendered site, no AI |
| 3 | Public deployment | Live URL behind Caddy |
| 4 | Corpus and retrieval | content/ → Qdrant |
| 5 | Mode B console | Streaming, cited answers |
| 6 | Guardrails, cost, kill switch | Safe to leave public |
| 7 | Polish | Logos, diagrams, code exhibits |
Order is deliberate. Content first (both renderers need it). Deploy at Phase 3, not last — a live half-built URL is worth more than a perfect site that never ships. AI after deployment so it can never block launch.
Repository
This folder is the git working copy of sam/ai-resume. One repo, one product.
Previously held an abandoned Vite/React scaffold. It was replaced by this build spec; the history is retained because it honestly records the false start, and it is referenced in the site's "alternatives considered" content.
Build and run
The site is one Go binary serving pre-rendered HTML. There is no Node, no bundler and no
node_modules; go.sum is the only dependency lock.
nix develop # go, templ, sqlite3, make, curl
make validate # content gate: front-matter against the frozen schema
make test # go test ./... plus the validator self-test
make dist # templ generate → bin/ → pre-rendered dist/
make dev # build, then serve on http://127.0.0.1:8096
bin/resume-build reads content/ and writes dist/ (pages, stage fragments, the fragment
manifest, the SQLite FTS5 index, assets). bin/resume-server serves dist/ and never reads
content/, never calls a model, and never opens a socket to another service — that is what
keeps acceptance test A1 true.
The two things that are not files are /search (FTS5 over page titles and body text) and
/api/stage/stream (the presentation panel driven by an event stream instead of a route).
Ground rules
- Do not touch other systems. No stopping containers, no editing other projects, no
nixos-rebuild, no Caddy changes except the single block specified in Phase 3 — and that one Sam applies. - Mode A must work with every AI service stopped. Hard gate.
- Never invent facts about Sam's career. If it is not in
reference/orcontent/, ask. - Secrets live in
~/.config/environment.d/only. - All models go through OmniRoute.
Current state
- Repo prepared, scaffold retired, build spec written
- Phase 1 — content source of truth (40 documents across six areas,
make validate) - Phase 2 — static site (
make dist, 45 pages, 86 stage fragments, FTS5 search) - Phase 3 — public deployment
- Phase 4 — corpus
- Phase 5 — AI overlay
- Phase 6 — guardrails
- Phase 7 — polish