🌐 中文
Admin Review

HSW-006 Wave 1 Review

OGSM v4 Phase 4 Trial — AIA CEU Course: Selecting Self-Closing and Controlled-Closing Door Solutions
5 agents dispatched in parallel (Pilot + 4 parallel) — outputs ready for review before Wave 2 dispatch.

📊 Factory Status Update (as of 2026-04-11)

These 5 Wave 1 deliverables were produced during the HSW-006 Phase 4 trial when the factory was still at OGSM v4 (human iteration era).

Since then, the factory has iterated to OGSM v5 (AI factory era) and validated 16 of 19 agents through Batches 1–4 on real production inputs. If we re-ran Wave 1 today, it would use polished v5 agents with paywall workaround, substrate gap protocol, reviewer-override layer, and REST API /ai-fallback (no more Gemini hang issues).

→ OGSM v5 Example → v4 History (this Wave 1 was produced under this) → Scaling Playbook → Unified Strategy
Wave 1 Deliverables 5 / 5 complete
Wave 1: Complete Wave 2: Pending — 8 reviewers
1,147
Total deliverable lines across 5 agents
3
Blog candidates flagged for Phase 3 queue
5
Friction points identified (Gemini, paywall, timing)
5
Agents dispatched (Pilot + 4 parallel)
Investigator A — Cases & Data 119 lines 4 real cases Sources verified Gemini search log included

Loading deliverable...

Investigator B — Codes & Cost 185 lines 7 code citations 20-year TCO table All M checks pass

Loading deliverable...

Writer A — Front Half 334 lines Slides S1–S12 Theory & Mechanism

Loading deliverable...

Writer B — Back Half 256 lines Slides S13–S24 5 scenarios 4 spec resources

Loading deliverable...

Engagement Designer 253 lines 5 interactions 4 emotional transitions All M checks pass

Loading deliverable...

📄 Blog Candidates Queue — Phase 3 Pipeline
Type Distribution
regulatory-explainer: 1 case-study: 0 product-comparison: 0 statistical-insight: 0 cost-comparison: 0 code-conflict: 1 scenario-guide: 1 reader-interest: 0

Alerts: None — queue has 3 entries across 3 types, still well-distributed.

Candidate #1 — id: 1
The 14-Day Clock: What NYC's Post-Twin-Parks Self-Closing Door Law Means For Your Next Multifamily Spec
regulatory-explainer source: investigator-a flagged: 2026-04-10
NYC's post-Twin-Parks Local Law creates a direct line from the Project Architect's closer spec decision to the owner's post-occupancy fine exposure. 22,300 violations issued in a single 4-month window (Jul–Oct 2023), ~30,000 still open as of late 2023. Boston, Philadelphia, and Newark have begun referencing the NYC framework. Architects specifying multifamily work need a peer-to-peer explainer anchored to Twin Parks + 14-day/$250-per-day mechanics + actionable spec language. High emotional hook, clear regulatory framework, 4–5 actionable spec clauses.
Candidate #2 — id: 2
Beyond The Big Three: A Project Architect's Field Guide To Independent Door Hardware Spec Resources
scenario-guide source: writer-b flagged: 2026-04-10
Most project architects never learn about BSD SpecLink, Deltek MasterSpec, SCIP, or CSI chapter networking. A neutral peer-to-peer guide naming all 4 independent resource paths fills a genuine information gap. Low competitor coverage — this topic is orthogonal to the Big 3's commercial interests. Reinforces Waterson's posture as a resource-provider brand rather than a vendor funnel.
Candidate #3 — id: 3
The NFPA 80 Section 6.4.1.4 vs Annex A 30-Degree Inconsistency
code-conflict source: investigator-b flagged: 2026-04-10
The NFPA 80 6.4.1.4 "positive latching on each door operation" requirement versus Annex A's 30-degree opening position recommendation for spring hinge adjustment is an unresolved inconsistency affecting every fire-door inspection involving a spring-hinge install. Lori Greene (Allegion) has publicly flagged this as deserving a code change proposal. A Waterson-branded explainer walking through the inspection criterion (5.2.3.5.2), the adjustment rule (6.4.1.4), and the Annex A divergence lands on why combined spring+hydraulic hinges are a defensible spec choice for architects who want to avoid the 30-degree trap entirely. New type for the queue: code-conflict.
1. Gemini Flash quota 429 — hit by 3 agents gemini-2.5-flash silently routes to gemini-3-flash-preview which has tight preview quotas. All 3 agents (Investigator A, Investigator B, Writer B) hit HTTP 429. Investigator A and B fell back to gemini-2.5-flash-lite; Writer B switched to WebSearch entirely. Recommendation: rewrite Wave 2 briefings to accept "any Gemini model OR WebSearch" and treat full gemini-2.5-flash as a bonus.
2. ICC / NFPA paywall — Investigator B pattern-verified only WebFetch against codes.iccsafe.org returns GTM shell only — content gated behind ICC Digital Codes Premium. NFPA LiNK similarly paywalled. All 7 code citations in Investigator B are pattern-verified via independent commentary (idighardware.com, UpCodes, FIT.edu) and tagged [Paraphrase — verify verbatim] where needed. Wave 2 should either acquire ICC + NFPA subscriptions or formally acknowledge pattern-verified citation standard.
3. Writer B didn't read Investigator B — dependency timing gap Investigator B's deliverable was not present in HSW-006-working/ at Writer B's drafting time. Writer B's Slide 15 cycle-count math and Slide 17 K-tag reference draw on general industry knowledge rather than Investigator B's verified research table. Recommendation: route Investigator B's citations back to Writer B for a 5-minute integration pass before the Reviewer wave begins.
4. 01-outline.md empty — scaffold gap The shared outline file (01-outline.md) was 1 line (empty) at the start of Wave 1. Writer A drafted the front-half scope by inferring from the briefing. Writer B and Writer A both assumed a 12/12 slide split with no confirmed alignment. Recommendation: Commander should write a proper 01-outline.md before Wave 2 review agents dispatch.
5. Writer A brand names — LCN / Norton / Dorma / Sargent neutrality concern Writer A's Slide 7 names LCN 4040XP, Norton 8500, Dorma 8916, Sargent 351 as examples of closers with independent valves. These are not Waterson products. This is technically neutral (it's an education course, not a sales deck) but may create an implicit competitor endorsement in the AIA CES submission. Reviewer wave should decide: strip brand names from Slide 7, or add Waterson's equivalent product in the same list.
Next Decision Point
Review the 5 Wave 1 deliverables above. Then decide:
Option A — Continue to Wave 2: dispatch 8 reviewers in parallel (Technical Reviewer, Code Reviewer, ADA Reviewer, Neutrality Reviewer, Accessibility Reviewer, Pacing Reviewer, Post-Test Designer, Slide Architect). Estimated wall-clock time: 25–35 min.

Option B — Pause to fix Wave 1 gaps: address the 3 high-priority gaps first — (1) Writer B + Investigator B integration pass, (2) 01-outline.md scaffold, (3) Slide 7 brand-name neutrality decision — then dispatch Wave 2 with a stronger foundation.