# New Home Agentic OS — New Home Star > The New Home Agentic OS is a continuously learning AI platform built by New Home Star that operationalizes decades of home builder transaction intelligence. It ingests sales calls, CRM data, and builder knowledge to create a shared intelligence layer that coaches agents, surfaces buyer insights, and compounds competitive advantage over time. **Site URL:** https://agentic-os-kk3f2kyb.manus.space **Full content URL:** https://agentic-os-kk3f2kyb.manus.space/crawl **Structured data URL:** https://agentic-os-kk3f2kyb.manus.space/crawl/json --- ## What Is the New Home Agentic OS? The New Home Agentic OS is an AI-powered operating system built by New Home Star (NHS) for the new home sales industry. It transforms raw sales interactions — calls, CRM data, coaching sessions, buyer conversations — into a continuously learning intelligence platform that coaches agents, surfaces buyer insights, and creates a compounding data moat for NHS and its builder partners. **Core thesis:** Every question asked, every objection handled, every deal closed makes the system smarter. Unlike static training materials or disconnected tools, the Agentic OS compounds intelligence over time — turning NHS's decades of transaction expertise into a living, queryable knowledge base. --- ## Value Propositions - Better buyer intelligence from every interaction - Faster sales agent onboarding with institutional knowledge - Institutional memory that survives agent turnover - Consistent coaching across all builder partners - Compounding competitive advantage — the system gets smarter every day - No more reinventing the wheel — one shared system replaces everyone building their own --- ## The 8-Layer Architecture ### Layer 1 — Expertise Capture Ingests institutional knowledge and structured buyer intelligence from five sources: Zoom (the centerpiece — client strategy sessions, sales coaching, internal planning, builder consulting), Google Drive (assessments, playbooks, templates, strategic documents), Gmail (decisions, follow-up actions, client context, historical communication), New Home Connect (training content, videos, learning materials), and Qualtrics (NHS TCP-model survey responses capturing Familial Status, Life Stage, Economic Condition, hot buttons, motivators, objections, and buyer intent). Years of recorded institutional expertise already exist in Zoom. ### Layer 2 — Classification & Taxonomy Every piece of captured content is classified against a rich NHS data model: Builder Classification (Production, Luxury, Build-On-Your-Lot, Active Adult), Buyer Classification (TCP profile, hot buttons, motivators, objections, life stage, household composition), Customer Journey (Lead → Prospect → Qualified Prospect → On-Site Opportunity → Purchaser → Homeowner → Evangelist), and Builder Product Taxonomy (Builder → Community → Floor Plan → Homesite → Features → Inventory Home). ### Layer 3 — Knowledge Library The organized institutional memory of New Home Star, structured by seven knowledge domains: Sales, Marketing, Recruiting, Training, Operations, Builder Consulting, and Leadership. The emphasis is on how NHS knowledge is organized — not what software stores it. Only Approved knowledge pages are embedded into the vector layer. ### Layer 4 — Vector Intelligence Layer Transforms human-readable knowledge into machine-queryable intelligence via a four-step flow: Human Knowledge → Classification → Embeddings → Semantic Retrieval. AI retrieves knowledge by meaning, not keywords. A buyer who says they want to wait until rates drop gets the most relevant NHS response to that exact situation. ### Layer 5 — Strategic Reasoning Layer Claude Console serves as the reasoning engine between intelligence retrieval and execution. Before any execution happens, this layer analyzes retrieved intelligence, evaluates options, and produces a validated recommendation. Responsibilities: Planning, Analysis, Recommendations, Validation, Decision Support. The system thinks before it acts. ### Layer 6 — Execution Layer Manus is the execution environment. It takes validated recommendations from the Strategic Reasoning Layer and produces tangible deliverables: Applications (builder portals, buyer-facing tools, internal dashboards), Agents (Sales Coach, Buyer Intelligence, Community Positioning, Onboarding), and Deliverables (landing pages, CRO audits, referral programs, assessments, dashboards, builder portals). ### Layer 7 — Human Review & Governance Security (PII Protection, Access Controls, Builder Permissions, Data Segmentation), Governance (Human Approval, Knowledge Validation, Version Control, Audit Trails), and Quality Control (Output Review, Feedback Loops, Accuracy Monitoring). Every output is reviewed by a human before delivery. Every rejection is a learning signal. ### Layer 8 — Continuous Learning Every builder, buyer, meeting, campaign, survey, and closed deal creates new intelligence. Approved outputs are re-embedded into the vector index and saved to the knowledge library. The system becomes more valuable with every interaction — not just more data, but more structured, classified, and retrievable intelligence that compounds over time. --- ## The Compounding Loop The system is designed as a self-reinforcing loop. Each step feeds the next, and outcomes feed back to the beginning: **01 Builder:** Builder partners connect their Zoom, HubSpot, CallRail, and NHC accounts. **02 Agent:** NHS sales agents conduct calls, coaching sessions, and buyer interactions. **03 Buyer:** Buyer signals — intent, objections, community preferences — are captured automatically. **04 Interaction:** Every interaction is transcribed, classified, and embedded into the expertise library. **05 Deal:** Closed deals and outcomes feed back into the system, making every future recommendation smarter. --- ## Data Sources The system ingests from five primary source categories: 1. **NHC Training IP** — New Home Star's proprietary training content, scripts, and sales methodology 2. **Call Recordings** — Zoom and CallRail recordings from builder sales calls and coaching sessions 3. **CRM Data** — HubSpot CRM events, contact records, deal stages, and buyer activity 4. **Builder Data** — New Home Connect API for sales pacing, community inventory, and buyer segmentation 5. **TCP Survey Intelligence** — Qualtrics captures the NHS TCP model: Familial Status, Life Stage, Economic Condition, hot buttons, motivators, objections, and buyer intent --- ## Who Built This? New Home Star (NHS) is the largest independent new home sales company in the United States, managing sales for major home builders across the country. The Agentic OS is an internal platform built to give NHS agents and builder partners a persistent competitive advantage through AI-powered sales intelligence. **Primary tools in use:** Zoom, CallRail, HubSpot, New Home Connect --- ## Strategic Positioning The NHS Agentic OS is positioned as a **data moat** — a proprietary intelligence layer that becomes more valuable as more data flows through it. Competitors cannot replicate it because the value is in the accumulated, classified, and embedded transaction history, not just the technology stack. The system is also a **consolidation play** — replacing the fragmented, individually-built tools that every team creates on their own with a single shared intelligence platform that benefits everyone at NHS simultaneously. --- ## Frequently Asked Questions **Q: What is the New Home Agentic OS?** A: It is an AI-powered operating system built by New Home Star that captures, classifies, and compounds sales intelligence from every builder interaction into a shared knowledge platform. **Q: Who uses this system?** A: NHS sales agents, builder partners, and NHS leadership. The system is internal to New Home Star and its builder network. **Q: What data does it ingest?** A: Zoom call recordings, HubSpot CRM data, CallRail call logs, New Home Connect training and builder data, Google Drive and Gmail knowledge, plus Qualtrics TCP-model survey responses. **Q: What AI models power it?** A: OpenAI GPT-4o for reasoning, Anthropic Claude 3.5 Sonnet for reasoning, OpenAI Whisper for transcription, and text-embedding-3-large for vector embeddings. **Q: How does the compounding loop work?** A: Builder interactions are captured → classified → embedded into vector memory → used by AI agents → delivered to agents → outcomes feed back into the system. Each cycle makes the system smarter.