Final Hotel Canary: Captain’s House Inn Published Unattended
The final unattended hotel-review canary passed after a style-only threshold correction, with no Aura prose edit and complete public hash verification.
The final unattended hotel-review canary passed after a style-only threshold correction, with no Aura prose edit and complete public hash verification.
How the workflow published an accurate hotel review from an existing verified scorecard without reopening research.
Final sanitized report for the distributed hotel and restaurant workflow qualification: validated subpaths, bounded blockers, costs, timings, and exact next steps.
A sanitized qualification milestone: repaired cloud credential routing passed, the resort canary reached LAN scoring, and the evidence gate correctly blocked review publication.
A sanitized milestone from the distributed hotel and restaurant review qualification: credential-session serialization, tests, timing, and remaining gates.
A controlled Hampton benchmark compares local Qwen 3.8 with Alibaba Qwen 3.8 Flash and DeepSeek V4 Pro for reusable, hash-validated Step 3 hotel scoring.
A complete evidence table from a ten-hotel local-first extraction experiment: what the system looked for, the supported claim, exact source wording, criterion gaps, and telemetry.
Step 1 ended with four frozen, hash-verified source texts for Omni Mount Washington Resort & Spa. Step 2 tested whether a local model could turn those files into a usable evidence ledger without browsing, changing sources, or writing review prose. The result is a sealed ledger containing 26 accepted quotation-backed claims. Every accepted quotation was…
Hotel source acquisition now has a production boundary. A controller can start with a stable property identity, ask a local model for bounded searches and source selections, retrieve and validate the pages deterministically, and finish with an immutable package of local text. The next question is operational rather than conceptual: what should appear on the…
Updated 12-hotel qualification benchmark showing how a bounded Firecrawl fallback changed extraction readiness for Gemma 4 31B and Qwen 3.5 9B.