SiteForgesf · contract-first buildersf:rival · autonomous parity loop

SiteForge (sf) & sf:rival

Two instruments for building and sharpening websites. sf builds a site from a signed, machine-verifiable contract through eight fail-closed stages — deterministic where it can be, human-signed where it must be. sf:rival takes an existing live site and runs an autonomous loop until it is internally superior to a field of rivals, gated by a mechanical verifier rather than by asking at every edit.

01The Idea

Most "AI site builders" hallucinate a finished site — they emit plausible pages that were never checked against a plan. SiteForge refuses that. It treats a website as the realization of a contract: a plan so precise that every requirement in it is a check the build must pass. Nothing ships that the contract cannot verify.

Contract-first

A signed plan compiles into machine-verifiable acceptance checks. The builder's only job is to satisfy them — no drift, no improvisation.

Clean-rebuild & self-healing

Structure is regenerated to match the contract rather than patched in place, so the site cannot silently diverge from its plan.

Fail-closed stages

Each stage is human-signed and consumes the previous stage's signed output. A missing signature stops the pipeline — it never guesses forward.

The honest boundary. A green build means the site is mechanically valid — it conforms to the signed plan. It is never a promise that the site will rank. Ranking is a downstream, probabilistic concern. SiteForge makes the structure correct and provable; it does not overclaim the outcome.

02Contract-First — the plan is the spec

The centre of SiteForge is a compiled build contract: a keyword-to-structure mapping where every entry is simultaneously an instruction and an acceptance test. It is a bet portfolio made concrete — each mapped page is a wager on a search opportunity — but the structure that realizes it is deterministic and checkable.

SIGNED BRIEF what the site is, who it serves, the market, the seeds │ ▼ SIGNED IDENTITY the brand/entity facts + the profile plan (human-supplied) │ ▼ SIGNED RESEARCH real keyword + SERP evidence — kills "structure from assumption" │ ▼ COMPILED CONTRACT every requirement ⇒ an acceptance check (this is the spec) │ ▼ BUILD satisfy the checks · clean-rebuild · verify · self-heal

Each arrow is a signature. Upstream unknowns are surfaced and kept as unknowns rather than papered over — the contract is only as strong as the evidence signed into it, and the system is explicit about that.

03The 8 Stages

SiteForge runs a greenfield site from positioning to a filled, audited site. Every stage is human-signed and fail-closed; the badge on the right shows who owns the decision.

1 · discover

Discovery & positioning

Problem-first intake: business model, market, seed keywords, competitors, and constraints. Discovery-first — surface and keep the unknowns instead of jumping to a solution. Output: a signed brief.

signed
2 · identity

Brand / entity foundation

Resolve the brand and author entities, the proof of expertise, and the profile plan. Every fact is supplied by the human and never inferred — this is a decision-and-dossier gate, not a content step.

signed
3 · research

Keyword & SERP evidence

Real keyword expansion (volume, difficulty, intent), the top-results shape, competitors, and cluster candidates. The build contract is fail-closed without this signed evidence corpus.

signed
4 · map

Compile the build contract

Turn the signed brief + evidence into a machine-verifiable keyword-to-structure mapping. Red-teamed and validated; every requirement becomes an acceptance check. This is the spec the build consumes.

signed
5 · design

Approve the theme

Generate a real block theme plus one rendered preview per page type, bound by hash to the exact contract. The human approves the look and signs. This is not a screenshot mock-up — it is a real, verifiable theme package.

signed
6 · build

Build the structure

Realize the signed mapping into a verified staging site — complete, themed, structurally correct, and with no prose yet. Deterministic and self-healing. Green here means it conforms to the plan.

verified
7 · pilot

Fill real content

Write the real article prose per page — grounded in the content brief, the author's voice, and the research evidence, with no fabricated numbers. Content only; it never touches structure, theme, or strategy.

gated
8 · audit

Conformance & health audit

Verify the built site still conforms to its contract and apply deterministic repairs — drift, broken links, wrong index directives, missing schema, redirect chains. Structural and technical only; not a ranking diagnosis.

verified
Anti-recurrence by design. Each stage consumes the previous stage's signed artifact through a preflight gate. You cannot skip a signature, and a later stage cannot run on an unsigned or hash-mismatched input. The visual step is verified with a rendered screenshot review, because a page can pass every text check and still look broken.

04What "Green" Means — and what it doesn't

Green means

  • The site conforms to the signed contract
  • Every mapped page exists with the required structure, schema, and internal links
  • No drift, broken links, redirect chains, or wrong index directives
  • The theme matches the approved, hash-bound design
  • The rendered pages look correct, not just pass text checks

Green does not mean

  • The site will rank — that is downstream and probabilistic
  • The content strategy was correct — the contract is a bet, honestly labelled
  • Off-page authority exists — that is a separate concern entirely
  • The work is "finished" as a product — structure conformance is not the same as a living site

This distinction is the whole ethic of the system: prove what can be proven, and never dress up a structural pass as a ranking guarantee.

05sf:rival — the autonomous parity loop

sf:rivalgiven: a live own-site + edit access + a list of rival URLs

Where sf builds greenfield, sf:rival sharpens an existing live site. You hand it your own site, the credentials to edit it, and a set of competitor URLs. It then runs autonomously — bench, discover, fix, verify, re-bench — until the site is internally superior to the whole field on every measured and judged dimension, and reports back. There is no per-edit confirmation.

┌───────────────────────────────────────────────────────┐ │ │ ▼ │ ① BENCH measure own-site vs each rival on every dimension │ │ ▼ │ ② DISCOVER a mandatory open-ended pass — find gaps a fixed │ checklist would miss (freshness, canonical, leaks…) ▼ │ ③ FIX apply a structure-preserving edit │ │ │ ▼ │ ④ VERIFY mechanical verifier: PASS ⇒ keep · FAIL ⇒ revert + flag │ │ ▼ │ ⑤ RE-BENCH ────────────── superior on all dims? ── no ───────┘ │ yes ▼ REPORT

The loop closes on a real target — internal superiority across the field — not on a fixed number of iterations. Its safety does not come from asking the human at each step; it comes from a mechanical guard on every edit.

06Autonomy & Safety — how it runs unattended

Structure-preserving verifier

Every edit passes through a mechanical verifier that checks the page's structure is intact. PASS keeps the change; FAIL reverts it and flags it. This — not a human confirmation prompt — is what makes unattended editing safe.

Snapshot → verify → restore → purge

Before any live edit the current state is snapshotted; after it, the rendered result is verified and the cache purged. A bad edit is rolled back to the snapshot automatically.

Mandatory open-ended discovery

A fixed checklist is a rut. Each round runs an open-ended pass that hunts for issues a checklist can't name — stale content, canonical mistakes, follow-link leaks, weak clustering — so the loop keeps finding real gains.

Never fabricate to win parity

The loop will not invent identity facts, authors, or trust signals just to match a rival. If closing a gap needs a real external asset, it stops and hands that decision to the human.

Full-auto is authorization, not a bypass. Running unattended means the human granted authorization up front. The loop still snapshots, still verifies every edit mechanically, still refuses to fabricate, and still restores on failure. Autonomy is bounded, not blind.

07Scope & the Three Human Gates

sf:rival is deliberately narrow. It competes on internal factors — the things you fully control on your own pages — and explicitly leaves the rest alone.

In scope — internal, site-wide

Schema and entity graph, navigation and footer, internal linking and clusters, canonical correctness, content freshness, link hygiene, de-cannibalization, on-page structure. The full site, not just one page.

Out of scope — always

Off-page authority: backlinks, domain rating, referring domains. Also out: "why isn't it ranking" diagnosis. sf:rival makes a site internally superior; it does not chase authority or explain the SERP.

It stops autonomously for only three classes of decision

Real external assets
Anything that requires creating a genuine off-site asset or identity fact — never fabricated to close a gap.
Home title / H1 on a ranking page
The most sensitive on-page levers on a page that already ranks are proposed for a human decision, not silently changed.
Genuine layout restructure
A real structural redesign (as opposed to a structure-preserving edit) is a human call, not an autonomous one.

Everything else inside the internal-superiority envelope runs to done without interrupting the human.

08sf vs sf:rival — same ethic, opposite starting point

sf (SiteForge build)sf:rival
Starting pointGreenfield — no site yetAn existing live site
GoalA structurally correct site that conforms to a signed contractA live site made internally superior to a field of rivals
Control modelHuman-signed at every stage; fail-closedAutonomous loop; no per-edit confirmation
Safety comes fromSignatures + preflight gates + hash-bindingA mechanical structure-preserving verifier + snapshots
Human gatesOne signature per stageOnly three decision classes (assets · home title/H1 · real restructure)
"Green" meansConforms to the plan — never a ranking claimInternally superior on measured + judged dimensions
Off-pageA separate, later concernExplicitly out of scope
Shared ethicProve what can be proven · never fabricate · never overclaim the outcome · verify the render, not the promise