Prompted LinesAI guidance for insurance

Trust · Transparency · August 2026

Agents that build this site

This site is built and maintained by a small set of AI agents working under human direction, using the same harness discipline the site teaches: narrow roles, deterministic checks that run every time, verification loops, and a human at the consequential gates. This page lists them.

The unit of work on this site is the ephemeral agent: spun up with a task, a slice of context, and a set of tools; shut down when the task ends. What keeps the output trustworthy is the harness around them. Two auditors are standing infrastructure, wired in as hooks so they run on every edit; the rest are spun up per job.

Practicing what the site preaches

The practice ladder's harness section describes the pattern: curated context, decomposed work, permissions in code, verification loops. This site runs on exactly that. Below: each one, its role, and what it audits.

Standing agents

The builder

Writes · edits · deploys

The general-purpose coding agent (Devin) that drafts pages, runs research, edits prose, and deploys the site. The agent writing this sentence.

Role
  • Turns human direction into pages, edits, and deployments
  • Verifies its own work: link resolution, citation integrity, served-page checks after every deploy
  • Never merges bulk rewrites of the owner's pre-existing documents without asking
Constrained by
  • Three lightweight audit hooks fire on every edit: prose quality, site structure, and newly added uncited facts
  • Human approval for direction, architecture decisions, and publishing

Prose Auditor

Prose quality · hook

Detects the statistical fingerprints of unedited AI prose and forces a context-aware rewrite before text ships.

What it audits
  • All Markdown and HTML prose in the package; parser strips markup and entities and skips code, CSS/JS, and source quotations
  • Two severity classes: fix-on-sight (em-dashes, spaced en-dashes) and flag-for-judgment (~20 grammar and phrase tells, e.g. moreover, delve, it's worth noting, not just X but Y, intensifiers)
  • Every occurrence gets a line and column; missing files are errors rather than silently ignored; flags may be deliberately kept after review
  • Detection is deterministic and regression-tested; rewrites are done by the agent, in context, never by regex

Lives at .devin/skills/prose-auditor/. First full run: 185 tells found package-wide; everything authored since is clean.

Structural Auditor

Organization · navigation · hook

Keeps the site's structure and navigational flow coherent as pages multiply.

What it audits
  • Nav completeness: every page lists every page, same order; the current page marked exactly once
  • Header hierarchy: compact global masthead first, page-specific title in a separate hero, and chapter navigation only on the field guide after that hero (regression-tested)
  • Link integrity: every internal link and #anchor resolves; no orphan pages
  • Page structure: title, meta description, exactly one h1, footer back-link, heading hierarchy
  • Judgment pass (per skill): purpose separation, next-step affordances, label honesty, placement of new content

Lives at .devin/skills/structural-auditor/. Current audit: masthead/hero separation, primary group labels and active state, chapter placement, shared chrome assets, links/anchors, orphans, metadata, and heading structure across 8 pages; regression suite covers the original header failures and semantic nav drift.

Reference steward

Link rot · quarterly

Guards the citation apparatus against link rot. References are written to survive dead URLs (author, title, publisher, year on each); this agent makes sure they rarely have to.

What it audits
  • Every external link, with one controlled retry: only 404/410 count as dead; network/TLS/5xx remain unreachable and are rechecked
  • Every run writes a timestamped comparison report and identifies status changes from the previous audit
  • Wayback snapshots are age-checked; the resumable manifest is saved after every URL
  • Local PDF copies use collision-resistant names, PDF-signature validation, SHA-256 checksums, byte counts, and atomic writes

Lives at .devin/skills/link-audit/. First run: 100 external links checked; 13 permanently moved links repaired; zero dead. The rot policy: find the new URL, else point to the archived snapshot, else replace the source and re-check the figure.

Evidence Auditor

Fact integrity · tripwire + quarterly

Verifies that every factual claim on the site matches its cited source, and that no number stands without evidence. The audit that protects the site's credibility.

What it audits
  • Quantitative claims plus high-risk qualitative claims (first, only, largest, majority), with stable claim IDs and source line numbers
  • Numbered citations resolve to their reference-list URLs; direct external links count as evidence pointers; quotations, nav, code, and reference entries are excluded
  • A lightweight edit hook flags newly written uncited facts; the full audit fetches sources and compares figure, date, and framing
  • Uncited claims are sourced, labeled as estimates/examples, softened, or removed; vendor-reported numbers keep their "as reported" framing
  • Verdict classes: supported / partially supported / unsupported (fixed immediately) / unreachable (cross-checked against secondary coverage)

Lives at .devin/skills/evidence-auditor/. First manual pass: 117 blocks; the improved parser now indexes quantitative and qualitative claims separately with resolved source URLs. Three partially-supported claims were found and corrected (Zurich rollout figures, AIG's 2030 target framing, CFC's "world first" attribution). Report at research/evidence-report.md; the public receipts live on the evidence page.

Ephemeral agents: the research fleet

The AI roadmap was researched by five parallel research agents, each spun up for one question and shut down when it reported. Their outputs were cross-checked, and every figure that made the page carries a numbered citation in the roadmap's reference list.

Research agentIts questionWhat it fed
Maturity frameworksWhat staged AI-adoption models exist, and where is the industry actually at?The industry-state table; the four-phase shape
Use cases and ROIWhich specialty-insurance AI use cases have measured results?Phase 2–3 use cases; the economics section
Competitive landscapeWhat have named competitors and vendors actually shipped?The competitor table; build-vs-buy guidance
RegulatoryWhat do regulators expect, by when, in which states?The governance gates and the regulatory sequencing section
ImplementationWhy do most AI programs stall, and what do the 7% do differently?The failure-mode table; the 1:1 adoption rule; the exit gates

How the harness maps to this site

Harness layerHow this site uses it
Context engineeringHouse style, tone, and rewrite rules live in the skill files each agent reads before acting; agents see the rules, not vibes
SkillsThe Prose Auditor and Structural Auditor are packaged procedures: versioned, testable, invocable on demand (/prose-auditor, /structural-auditor)
HooksProse, structural, and lightweight evidence tripwires fire after every write/edit; full link archiving and source verification remain scheduled because they require network calls
Verification loopsCitation-integrity checks, link resolution, tag balance, and served-page 200 checks after every deploy
Human gateAaron sets direction, approves architecture and bulk changes, and decides what ships. Consolidations (like the August 2026 harness-into-practice-ladder merge) are owner decisions; the Structural Auditor enforces the rules after them. Slop is cheap; trust is engineered