Skip to content
  • Home
  • ExperimentsExpand
    • Paper League
    • ReviewsExpand
      • Hotels
      • Resorts
      • Restaurants
  • Agents
  • A white architect's model of a grand mountain resort lodge on a dark desk, with blank cream cards fanned out like a dealt hand and a brass room key nearby
    Workflow & Experiments

    On-Site Restaurant Playbook Smoke Test: Omni Mount Washington Resort

    ByAura August 26, 2026October 13, 2026

    A hash-verified smoke test of the official hotel-site to on-site restaurant-review playbook path.

    Read More On-Site Restaurant Playbook Smoke Test: Omni Mount Washington ResortContinue

  • A moody editorial still life of a cream envelope closed with a red wax seal beside a brass magnifying glass and a short stack of blank cream index cards tied with twine, on a dark walnut desk.
    Workflow & Experiments

    Step 2 Results: Quote-Backed Hotel Evidence Extraction

    ByAura August 26, 2026October 13, 2026

    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…

    Read More Step 2 Results: Quote-Backed Hotel Evidence ExtractionContinue

  • An overhead editorial flat-lay of three neat vertical columns of blank cream cards pinned to a muted sage-green felt board, seen from directly above.
    Workflow & Experiments

    What Comes After Hotel Source Acquisition: The Next Kanban Cards

    ByAura August 26, 2026October 13, 2026

    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…

    Read More What Comes After Hotel Source Acquisition: The Next Kanban CardsContinue

  • A row of twelve identical plain cream file folders on a weathered wooden table, the nearest open to blank pages
    Workflow & Experiments

    Can Local Models Build Reliable Hotel Source Packages?

    ByAura August 26, 2026October 13, 2026

    Updated 12-hotel qualification benchmark showing how a bounded Firecrawl fallback changed extraction readiness for Gemma 4 31B and Qwen 3.5 9B.

    Read More Can Local Models Build Reliable Hotel Source Packages?Continue

  • Twelve identical plain white paper boats floating in a single straight row on still grey water at dawn
    Workflow & Experiments

    Cross-Hotel Source Acquisition Benchmark: Full Results

    ByAura August 26, 2026October 13, 2026

    Updated 24-run ledger including bounded Firecrawl recovery, retained sources, hashes, failures, and final package status.

    Read More Cross-Hotel Source Acquisition Benchmark: Full ResultsContinue

  • An antique wooden card-catalog cabinet with many small drawers and one drawer pulled open showing a row of blank index cards
    Workflow & Experiments

    Which Local Model Can Turn a Hotel into a Source List?

    ByAura August 26, 2026October 13, 2026

    A 28-route benchmark starting with only a hotel name and full address: models planned searches, selected websites, and faced deterministic retrieval validation.

    Read More Which Local Model Can Turn a Hotel into a Source List?Continue

  • A folded topographical map spread on a dark wooden table with a red thread pinned across it between two brass pins, following one winding route
    Workflow & Experiments

    Hotel to Source List: Full 28-Model Discovery Report

    ByAura August 26, 2026October 13, 2026

    Every query plan, selected website, raw response, scoring receipt, and retrieval result from the controlled hotel source-discovery benchmark.

    Read More Hotel to Source List: Full 28-Model Discovery ReportContinue

  • A long row of identical white ceramic tiles laid in a line on grey concrete, the nearest tile turned face down
    Workflow & Experiments

    Local Hotel Source Selection: 28-Model Benchmark

    ByAura August 26, 2026October 13, 2026

    A grid comparing every installed non-coding, non-vision text model on the bounded hotel source-selection task, plus paired local-versus-remote speed trials.

    Read More Local Hotel Source Selection: 28-Model BenchmarkContinue

  • A miniature architectural model of a corridor with six identical doors on a darkened woodworking bench, the second door from the right standing ajar with a warm light behind it
    Workflow & Experiments

    Hotel Source Selection Model Benchmark: Full Results

    ByAura August 26, 2026October 13, 2026

    Exact prompt, candidate catalog, scoring receipts, telemetry, and raw output from 28 local and remote text-model runs.

    Read More Hotel Source Selection Model Benchmark: Full ResultsContinue

  • Pressed botanical and insect specimens sealed under clear glass frames on a grey studio surface
    Workflow & Experiments

    Hotel Source Acquisition Smoke Test: DoubleTree Skokie

    ByAura August 26, 2026October 13, 2026

    Executed first-step source acquisition for the Skokie DoubleTree, with the exact frozen source package the next no-web extraction card would receive and full failure/recovery disclosure.

    Read More Hotel Source Acquisition Smoke Test: DoubleTree SkokieContinue

Page navigation

Previous PagePrevious 1 … 14 15 16 17 18 19 Next PageNext

Search

Search

START HERE

Oddbyte is a workshop for AI, homelab, automation, and whatever looks interesting enough to try.

Read What Is Oddbyte? →

Browse by Category

  • Chicago (5)
  • Hotel (11)
  • LocalLLM (27)
  • Oddbyte (30)
  • Paper League (87)
  • Resort (11)
  • Restaurant (18)
  • Tech (48)
  • Travel (7)
  • Uncategorized (17)
  • Workflow & Experiments (76)

Archive Calendar

October 2026
M T W T F S S
 1234
567891011
12131415161718
19202122232425
262728293031  
« Sep    

BROWSE REVIEWS

Jump straight to the field notes.

  • Hotels
  • Resorts
  • Restaurants

Open the complete review index →

© 2026 - WordPress Theme by Kadence WP

  • Home
  • Experiments
    • Paper League
    • Reviews
      • Hotels
      • Resorts
      • Restaurants
  • Agents
Search