sync local

Use clean generic names instead of repeated redaction placeholders.\n\nCo-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.gitignore

@@ -2,3 +2,5 @@ local/
 case_study.css
 case_study_one_page.html
 case_study_one_page.md
+architecture_dag.md
+architecture_diagram.html

README.md

@@ -1,6 +1,6 @@
 # Talk-to-Data: Semantic Analytics for Enterprise Quotations
 
-**A POC case study in governance-first semantic layer design: SAP → Snowflake → Cortex → Chatbot.**
+**A PoC case study in governance-first semantic layer design: SAP → Snowflake → Cortex Analytics (LLM) → Chatbot.**
 
 ---
 
@@ -76,7 +76,7 @@ Sales and operations teams across multiple regions handle thousands of quote req
 │ - Visual analysis     │      │ - Quote Q&A           │
 │ - Sales reporting     │      │ - Prompt engineering  │
 │ - Ops monitoring      │      │ - Real-time answers   │
-└───────────┬──────────┘      └──────────┬────────────┘
+└───────────┬───── ─────┘      └──────────┬────────────┘
             │                             │
             │                    <1 minute turnaround
             │
@@ -178,7 +178,7 @@ Governance is not a checklist; it's embedded in the data layer.
 
 ---
 
-## Results: From POC to Impact
+## Results: From PoC to Impact
 
 ### Estimated Impact (Based on User Interviews)
 - **Quote turnaround**: 5-30 min (email + manual lookup) → <1 min (chatbot query)
@@ -186,7 +186,7 @@ Governance is not a checklist; it's embedded in the data layer.
   - Pilots with 5 sales reps: ~50+ hours/week freed (estimated)
   - Extrapolation: 30+ sales team × 5 hours/week = 150+ hours recovered org-wide
 - **Error reduction**: Discount exceptions caught by policy guardrails (vs. manually reviewed)
-- **Team velocity**: POC shipped in weeks (not months), governance patterns established for scale
+- **Team velocity**: PoC shipped in weeks (not months), governance patterns established for scale
 
 ### Why This Matters for Delivery Managers
 1. **Governance-first approach**: We didn't build a prototype and hope for policy later. Guardrails were baked in from day one.
@@ -196,29 +196,6 @@ Governance is not a checklist; it's embedded in the data layer.
 
 ---
 
-## How to Use This Repo
-
-### Deliverables
-- **`dbt/`**: Anonymized dbt models (staging, transforms, semantic views)
-  - `models/staging/stg_*.sql` — Raw layer transformations
-  - `models/transform/trf_*.sql` — Business logic
-  - `models/distribute_ddl/sv_*.yml` — Semantic views with synonyms
-- **`cortex/`**: Governance config (information protection, access control, audit rules)
-  - `cortex_governance_config.yaml` — Guardrails, freshness contracts, LLM policies
-- **`docs/`**: Architecture diagrams, decision logs
-  - `architecture_dag.md` — Data flow Mermaid diagram
-  - `decisions.md` — Architecture decision records (ADRs)
-- **`README.md`**: This file (the narrative for interviewers/stakeholders)
-
-### How to Adapt This to Your Domain
-1. **Replace discount logic** with your domain (e.g., pricing tiers, contract terms, approval workflows)
-2. **Adjust freshness** (once-daily to hourly/real-time) based on your use case
-3. **Modify semantic dimensions** to match your business terminology
-4. **Update Cortex policies** for your personal-information and governance rules
-5. **Test with a small pilot** (5-10 users) before org-wide rollout
-
----
-
 ## Lessons Learned
 
 ### What Worked
@@ -231,10 +208,6 @@ Governance is not a checklist; it's embedded in the data layer.
 ✅ **dbt for team alignment**: SQL-first + schema docs meant the data team and business stakeholders spoke the same language. Onboarding new people was fast.
 
 ### What We'd Change at Scale
-⚠️ **Real-time discount updates**: If pilot shows sales need <1hr freshness on policy changes, escalate to hourly ELT.
-
-⚠️ **Multi-region governance**: Current config is single-region (BR). If expanding to US/CA, add region-specific discount tiers and approval workflows.
-
 ⚠️ **Cortex cost**: Monitor Cortex token usage as chatbot volume scales. Current config has cost controls (monthly budget, per-query max tokens); may need aggressive pruning at scale.
 
 ⚠️ **Semantic view complexity**: If adding more dimensions (15→50), consider splitting into focused semantic views (e.g., `sv_quote_discounts`, `sv_quote_compliance`) to keep queries fast.
@@ -263,37 +236,14 @@ A: Yes. Adapt the dbt dialect (BigQuery: `jinja-sql`, Redshift: `redshift` profi
 **Q: Is once-daily refresh really enough?**
 A: For quote research, yes. If you need real-time pricing updates, escalate to hourly ELT. The architecture supports it; just change the schedule in your orchestrator.
 
-**Q: How do I handle discount exceptions?**
-A: Cortex policy flags them and escalates to a human review queue (max 10/hour). Ops team approves or rejects in Snowflake; bot learns the decision for future similar quotes.
-
 **Q: What if I need to scale to 500+ users?**
-A: Semantic layer architecture scales horizontally. Snowflake handles concurrency. Monitor Cortex token usage and partition semantic views if queries slow down. dbt stays the same.
+A: Semantic layer architecture scales horizontally. Snowflake handles concurrency. Monitor Cortex token usage and partition semantic views if queries slow down. dbt stays the same. The real issue comes when you need RLS requirements — this will require additional tools or methods beyond Snowflake RBAC.
 
 **Q: Can I export this as a Snowflake Native App for partners?**
-A: Yes. Package the semantic views + Cortex policies as an app; partners can install it and use the chatbot without seeing raw data.
+A: Yes. Package the semantic views + Cortex policies as an app; partners can install it and use the chatbot without seeing raw data. Cortex Analyst can be seamlessly integrated into any application using REST API.
 
 ---
 
-## Next Steps
+## Context
 
-1. **Expand pilot**: Rollout to 30+ sales team over 4 weeks
-2. **Measure impact**: Track quote turnaround times, bot usage, escalation rates
-3. **Iterate on policies**: Refine discount rules and information-protection controls based on pilot feedback
-4. **Add new domains**: Reuse the semantic layer pattern for contracts, serviceability, pricing
-5. **Scale LLM**: Move from proof-of-concept to production volume (monitor cost, latency)
-
----
-
-## Contact & Questions
-
-This case study demonstrates:
-- Governance-first architecture for enterprise AI
-- Semantic layer design (SAP → dbt → Snowflake → LLM)
-- Operationalizing guardrails and audit trails
-- Shipping production-ready POCs in weeks
-
-For questions about the design decisions, data flow, or how to adapt this to your domain, reach out.
-
----
-
-**Co-authored by Copilot**
+This case study was prepared as a technical exploration demonstrating governance-first semantic layer design for enterprise AI enablement. It reflects delivery patterns developed in a global industrial environment and adapted for privacy-safe public sharing.

architecture_dag.md

@@ -1,59 +0,0 @@
-# Quotation Semantic Layer - Data Flow DAG
-# SAP Source -> Snowflake -> dbt Transforms -> Semantic Views -> Cortex -> Chatbot Output
-
-graph LR
-    SAP["🗄️ SAP ERP System<br/>(Sales & Discount Data)"]
-    
-    EXT["📥 Snowflake<br/>External Stage"]
-    
-    RAW["raw.quotations<br/>raw.discount_conditions"]
-    
-    STG["STAGING Layer<br/>stg_quotes<br/>stg_discount_conditions<br/>stg_product_master"]
-    
-    TRF["TRANSFORM Layer<br/>trf_quotation<br/>trf_chatbot_quotation"]
-    
-    DIM["Reference Dimensions<br/>dim_customer_discount_policy<br/>dim_product_portfolio<br/>fct_agreement_discounts"]
-    
-    SEMA["SEMANTIC LAYER<br/>sv_quotation<br/>sv_chatbot_quotation"]
-    
-    CORTEX["Cortex Analytics<br/>Guardrails & Information Protection<br/>Access Control<br/>Freshness Contract"]
-    
-    UI["Snowflake UI<br/>(BI Dashboard)"]
-    CHAT["🤖 Internal Workspace<br/>(Chatbot)"]
-    
-    SAP -->|Daily Batch 05:00 UTC| EXT
-    EXT -->|Load| RAW
-    
-    RAW -->|Column mapping<br/>Type casting| STG
-    
-    STG -->|Join dimensions<br/>Calculate discounts<br/>Apply governance flags| TRF
-    DIM -->|Enrich with policies| TRF
-    
-    TRF -->|Expose semantic<br/>business logic<br/>Hide implementation| SEMA
-    
-    SEMA -->|Apply guardrails<br/>Protect sensitive information<br/>Enforce freshness| CORTEX
-    
-    CORTEX -->|Query & Visualize| UI
-    CORTEX -->|LLM consumption<br/>Prompt engineering layer| CHAT
-    
-    CHAT -->|<1 min<br/>Quote Answers| USER["👤 Sales & Ops<br/>Team"]
-    UI -->|Dashboard<br/>Reporting| OPS["📊 Operations<br/>Team"]
-    
-    SEMA -.->|Data Contract<br/>Lineage| AUDIT["🔒 Audit & Compliance<br/>- Access logs<br/>- Policy changes<br/>- Exception escalations"]
-    
-    style SAP fill:#d4a574
-    style CORTEX fill:#ff9999
-    style SEMA fill:#99ccff
-    style CHAT fill:#99ff99
-    style USER fill:#ffcc99
-    style AUDIT fill:#cc99ff
-
-classDef layer_raw fill:#e1e4e8
-classDef layer_stg fill:#d0d7de
-classDef layer_trf fill:#adb8c1
-classDef layer_sema fill:#6e7681
-
-class RAW layer_raw
-class STG layer_stg
-class TRF layer_trf
-class SEMA layer_sema

architecture_diagram.html

@@ -1,275 +0,0 @@
-<!DOCTYPE html>
-<html>
-<head>
-    <meta charset="utf-8">
-    <title>Talk-to-Data: Architecture Animated Diagram</title>
-    <script src="https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.min.js"></script>
-    <style>
-        body {
-            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
-            margin: 0;
-            padding: 20px;
-            background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
-            min-height: 100vh;
-        }
-        .container {
-            max-width: 1200px;
-            margin: 0 auto;
-            background: white;
-            border-radius: 8px;
-            box-shadow: 0 4px 6px rgba(0,0,0,0.1);
-            padding: 30px;
-        }
-        h1 {
-            color: #2c3e50;
-            text-align: center;
-            margin-bottom: 10px;
-            font-size: 28px;
-        }
-        .subtitle {
-            text-align: center;
-            color: #7f8c8d;
-            margin-bottom: 30px;
-            font-size: 14px;
-        }
-        .diagram-wrapper {
-            margin: 30px 0;
-            padding: 28px;
-            background: #f8f9fa;
-            border-radius: 6px;
-            border-left: 4px solid #3498db;
-            overflow-x: auto;
-        }
-        .mermaid {
-            display: flex;
-            justify-content: center;
-            min-width: 760px;
-        }
-        .mermaid svg {
-            width: 100%;
-            max-width: 920px;
-            height: auto;
-            overflow: hidden;
-        }
-        .mermaid .nodeLabel,
-        .mermaid .edgeLabel {
-            font-size: 16px !important;
-        }
-        .mermaid .edgeLabel {
-            background: transparent !important;
-            padding: 2px 4px;
-        }
-        .mermaid .edgeLabel:has(span:empty) {
-            display: none;
-        }
-        .legend {
-            display: grid;
-            grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
-            gap: 15px;
-            margin-top: 30px;
-            padding-top: 20px;
-            border-top: 1px solid #ecf0f1;
-        }
-        .legend-item {
-            display: flex;
-            align-items: center;
-            font-size: 13px;
-        }
-        .legend-color {
-            width: 20px;
-            height: 20px;
-            border-radius: 3px;
-            margin-right: 10px;
-            flex-shrink: 0;
-        }
-        .section {
-            margin-top: 40px;
-            padding: 20px;
-            background: #ecf0f1;
-            border-radius: 6px;
-        }
-        .section h2 {
-            color: #2c3e50;
-            margin-top: 0;
-            font-size: 18px;
-            border-bottom: 2px solid #3498db;
-            padding-bottom: 10px;
-        }
-        .section p {
-            color: #555;
-            line-height: 1.6;
-            margin: 10px 0;
-        }
-        .flow-step {
-            display: flex;
-            align-items: center;
-            margin: 15px 0;
-            padding: 10px;
-            background: white;
-            border-radius: 4px;
-        }
-        .flow-step span {
-            display: inline-block;
-            width: 110px;
-            min-width: 110px;
-            flex-shrink: 0;
-            font-weight: bold;
-            color: #3498db;
-        }
-        .flow-step p {
-            flex: 1;
-            min-width: 0;
-        }
-        code {
-            background: #f4f4f4;
-            padding: 2px 6px;
-            border-radius: 3px;
-            font-size: 12px;
-        }
-        @keyframes flow {
-            0% { opacity: 0.3; }
-            50% { opacity: 1; }
-            100% { opacity: 0.3; }
-        }
-        .animate-flow {
-            animation: flow 2s ease-in-out infinite;
-        }
-    </style>
-</head>
-<body>
-    <div class="container">
-        <h1>Talk-to-Data: Semantic Analytics Architecture</h1>
-        <p class="subtitle">SAP → Snowflake → dbt → Cortex → Chatbot | <1 minute quote answers</p>
-        
-        <div class="diagram-wrapper">
-            <div class="mermaid">
-graph TD
-    SAP["SAP ERP<br/>Quotes and discounts<br/>Daily batch"]
-    RAW["Snowflake raw data"]
-    STG["dbt staging<br/>Clean and standardize"]
-    TRF["dbt transforms<br/>Business rules and flags"]
-    SEMA["Semantic views<br/>Business terms and lineage"]
-    CORTEX["Cortex Analytics<br/>Guardrails and audit"]
-    UI["Snowflake UI<br/>Dashboards"]
-    CHAT["Internal workspace<br/>Chatbot"]
-    USER["Sales and operations<br/>30+ users<br/><1 min estimated answer"]
-    AUDIT["Audit trail<br/>Access and exceptions"]
-
-    SAP --> RAW
-    RAW --> STG
-    STG --> TRF
-    TRF --> SEMA
-    SEMA --> CORTEX
-    CORTEX --> UI
-    CORTEX --> CHAT
-    UI --> USER
-    CHAT --> USER
-    SEMA -.-> AUDIT
-    
-    style SAP fill:#d4a574,stroke:#333,stroke-width:2px,color:#fff
-    style CORTEX fill:#ff9999,stroke:#c0392b,stroke-width:2px,color:#fff
-    style SEMA fill:#99ccff,stroke:#2980b9,stroke-width:2px,color:#fff
-    style CHAT fill:#99ff99,stroke:#27ae60,stroke-width:2px,color:#000
-    style USER fill:#ffcc99,stroke:#e67e22,stroke-width:2px,color:#000
-    style AUDIT fill:#cc99ff,stroke:#8e44ad,stroke-width:2px,color:#fff
-    style RAW fill:#e1e4e8,stroke:#666,stroke-width:1px
-    style STG fill:#d0d7de,stroke:#666,stroke-width:1px
-    style TRF fill:#adb8c1,stroke:#666,stroke-width:1px
-    style RAW fill:#e1e4e8,stroke:#666,stroke-width:1px
-            </div>
-        </div>
-
-        <div class="legend">
-            <div class="legend-item">
-                <div class="legend-color" style="background: #d4a574;"></div>
-                <span><strong>SAP Source:</strong> Daily batch extract</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #e1e4e8;"></div>
-                <span><strong>Raw:</strong> Unmodified data</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #d0d7de;"></div>
-                <span><strong>Staging:</strong> Data preparation</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #adb8c1;"></div>
-                <span><strong>Transform:</strong> Business logic</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #99ccff;"></div>
-                <span><strong>Semantic:</strong> Data contract</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #ff9999;"></div>
-                <span><strong>Cortex:</strong> AI guardrails</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #99ff99;"></div>
-                <span><strong>Chatbot:</strong> User interface</span>
-            </div>
-            <div class="legend-item">
-                <div class="legend-color" style="background: #cc99ff;"></div>
-                <span><strong>Audit:</strong> Compliance trail</span>
-            </div>
-        </div>
-
-        <div class="section">
-            <h2>Data Flow Stages</h2>
-            <div class="flow-step">
-                <span>1. Source</span>
-                <p>SAP ERP systems extract quotation, discount, and customer data daily at 05:00 UTC. Data includes quotation identifiers, line items, pricing, and discount conditions.</p>
-            </div>
-            <div class="flow-step">
-                <span>2. Raw</span>
-                <p>Snowflake External Stage ingests CSV/Parquet. Raw schema preserves source structure without modification. Data quality checks validate row counts, null patterns.</p>
-            </div>
-            <div class="flow-step">
-                <span>3. Staging</span>
-                <p><code>stg_*</code> models rename columns, cast data types, and handle nulls. Example: source quotation ID → <code>quote_id</code>, source amount → <code>net_value</code>. No business logic yet.</p>
-            </div>
-            <div class="flow-step">
-                <span>4. Transform</span>
-                <p><code>trf_quotation</code> joins customer policies, product portfolios, and agreement discounts. Calculates discount totals, applies governance flags (e.g., <code>discount_above_ceiling</code>). Two models: <code>trf_quotation</code> (BI) and <code>trf_chatbot_quotation</code> (LLM-optimized).</p>
-            </div>
-            <div class="flow-step">
-                <span>5. Semantic</span>
-                <p>Snowflake DDL semantic views expose curated dimensions and facts. Includes synonyms for natural language (e.g., "desconto cliente" → <code>discount_customer_pct</code>). Single source of truth for BI dashboards and LLM queries.</p>
-            </div>
-            <div class="flow-step">
-                <span>6. Cortex</span>
-                <p><a href="https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-analyst" target="_blank" rel="noopener noreferrer">Cortex Analyst</a> applies guardrails: hides raw discount percentages, protects customer names, checks data freshness, enforces role-based access, and logs all access. LLM queries go through here.</p>
-            </div>
-            <div class="flow-step">
-                <span>7. Consume</span>
-                <p><strong>Snowflake UI:</strong> Dashboards for ops/sales teams (full data visibility). <strong>Internal Workspace:</strong> Chatbot interface (guardrail-filtered data). Both consume the same semantic layer; governance rules ensure consistency.</p>
-            </div>
-        </div>
-
-        <div class="section">
-            <h2>Why This Architecture?</h2>
-            <p><strong>Governance-first:</strong> Guardrails (discount policies, protection of personal and customer information, and audit logs) are embedded in the data layer, not bolted on to the LLM prompt. The bot can't bypass policy; it's enforced by Cortex + dbt.</p>
-            <p><strong>Semantic contract:</strong> The semantic layer (sv_quotation, sv_chatbot_quotation) defines the agreement between data engineers, BI teams, and LLM consumers. Column definitions, synonyms, and access rules are version-controlled.</p>
-            <p><strong>Team efficiency:</strong> dbt lineage shows how every dimension flows from SAP → semantic layer. Data engineers and business analysts can trace a discount calculation back to SAP in seconds. Onboarding takes days, not weeks.</p>
-            <p><strong>Prototyping speed:</strong> Snowflake + Cortex means we didn't build custom infrastructure. POC shipped in weeks. Cortex guardrails were ready on day 1; no custom policy engine to build.</p>
-        </div>
-
-        <div class="section">
-            <h2>Expected Outcomes</h2>
-            <p><strong>Latency:</strong> Quote research from 5-30 minutes (email + manual lookup) → <1 minute (chatbot query)</p>
-            <p><strong>Scalability:</strong> 30+ salespeople can query the chatbot concurrently. Snowflake handles scale; dbt models are stateless (scale linearly).</p>
-            <p><strong>Governance:</strong> All discount exceptions flagged and audited. Policy violations are visible and traceable.</p>
-            <p><strong>Team capability:</strong> Once-daily batch + semantic layer pattern is reusable. Next use cases (contracts, pricing, serviceability) ship faster by leveraging the same playbook.</p>
-        </div>
-
-        <div class="section">
-            <h2>Learn More</h2>
-            <p>
-                See <code>README.md</code> for full narrative, decisions, and lessons learned. 
-                Check <code>dbt/</code> for anonymized SQL models. 
-                Review <code>cortex/cortex_governance_config.yaml</code> for guardrails and access control.
-            </p>
-        </div>
-    </div>
-</body>
-</html>

cortex_governance_config.yaml

@@ -22,20 +22,20 @@ cortex_policies:
   
   # Access control: Who can query this semantic model
   access_control:
-    default_role: "[REDACTED: SNOWFLAKE_ROLE]"
+    default_role: "quotation_analytics_user"
     authorized_teams:
       - name: "sales_team"
-        snowflake_role: "[REDACTED: SALES_ROLE]"
+        snowflake_role: "quotation_sales_user"
         tables: ["sv_quotation", "sv_chatbot_quotation"]
         max_rows_returned: 100000
       
       - name: "operations_team"
-        snowflake_role: "[REDACTED: OPS_ROLE]"
+        snowflake_role: "quotation_operations_user"
         tables: ["sv_quotation", "sv_chatbot_quotation"]
         max_rows_returned: 500000
       
       - name: "cortex_agent"
-        snowflake_role: "[REDACTED: CORTEX_AGENT_ROLE]"
+        snowflake_role: "quotation_cortex_agent"
         tables: ["sv_chatbot_quotation"]
         max_rows_returned: 1000
         allowed_functions: ["semantic_search", "similarity_score"]
@@ -59,7 +59,7 @@ cortex_policies:
       description: "Mask actual customer names in chatbot responses"
       pattern: "customer_name|cliente_nome"
       action: "mask_value"
-      replacement: "[REDACTED: Customer Information]"
+      replacement: "[Customer information protected]"
       exception: "Sales team in authorized_teams can see unmasked values"
     
     - rule: "pii_scrubbing"
@@ -97,7 +97,7 @@ cortex_policies:
   
   # Cost controls: Prevent runaway LLM usage
   cost_controls:
-    monthly_budget_usd: "[REDACTED: BUDGET]"
+    monthly_budget_usd: "configured in the deployment environment"
     alert_threshold_pct: 80
     per_query_max_tokens: 2000
     max_concurrent_queries: 10
@@ -121,9 +121,9 @@ semantic_model_lineage:
   description: "How quotation data flows through transformations"
   stages:
     1_source:
-      system: "[REDACTED: SAP_SYSTEM]"
+      system: "enterprise_erp_source"
       frequency: "Daily batch 05:00 UTC"
-      tables: ["[REDACTED: SOURCE_QUOTE_TABLE]", "[REDACTED: SOURCE_DISCOUNT_TABLE]"]
+      tables: ["source_quotes", "source_discount_conditions"]
     
     2_staging:
       schema: "STAGING"
@@ -142,8 +142,8 @@ semantic_model_lineage:
     
     5_cortex_consumption:
       interface_1: "Snowflake Native App (BI)"
-      interface_2: "[REDACTED: SIEMENS_WORKSPACE]"
-      llm_model: "[REDACTED: LLM_VERSION]"
+      interface_2: "internal_chatbot_workspace"
+      llm_model: "managed_cortex_model"
       prompt_template: |
         You are a sales support assistant. Answer quote questions using only
         the data provided. If discount exceeds policy, flag for human review.

linkedin_post.md

@@ -1,43 +0,0 @@
-# LinkedIn post draft
-
-Sales teams should not need an email chain to answer a routine quotation question.
-
-In a proof of concept, I designed a governance-first semantic analytics flow for quotation data:
-
-**SAP → Snowflake → dbt → Semantic Views → Cortex → Chatbot**
-
-The business problem was simple: more than 30 salespeople could need help validating a quote, discount, or product classification. A question that looked small could take 5–30 minutes because the answer depended on manual lookup and internal communication.
-
-The solution was not “put an LLM on top of raw tables.”
-
-I first created a semantic contract:
-
-- curated quotation dimensions and facts;
-- business-friendly synonyms for natural-language questions;
-- centralized discount calculations;
-- explicit policy-exception flags;
-- lineage from source data to the consumer-facing model.
-
-Then Cortex applied the controls around that contract:
-
-- data freshness warning for the daily batch;
-- role-based access;
-- protection of sensitive information;
-- escalation when a discount exceeded policy;
-- audit logging for queries and decisions.
-
-The semantic model was consumed in two ways:
-
-1. Snowflake's interface for analytical exploration.
-2. An internal chatbot workspace for direct questions, with prompt engineering to refine the response experience.
-
-The estimated user outcome was reducing routine quote research from 5–30 minutes to less than one minute. That is an estimate based on the existing human workflow, not a production benchmark—and that distinction matters.
-
-The main lesson: **governance belongs in the data and semantic layers, not only in the prompt.**
-
-The POC also created a reusable delivery pattern for future use cases: define the business contract, expose only the right data, add guardrails, then choose the lightest useful interface.
-
-I documented the anonymized architecture, decisions, and lessons learned here:  
-[GitHub repository link]
-
-#DataArchitecture #Snowflake #dbt #DataGovernance #EnterpriseAI #TechnicalDelivery

marts_quotes.sql

@@ -9,17 +9,17 @@
 
 with source_quotes as (
     select
-        [REDACTED: quote_id column],
-        [REDACTED: line_item column],
-        [REDACTED: customer_id column],
-        [REDACTED: material_id column],
-        [REDACTED: quantity column],
-        [REDACTED: net_value column],
-        [REDACTED: quote_date column],
-        [REDACTED: sales_person_id column],
-        [REDACTED: source_timestamp column]
-    from [REDACTED: SOURCE_SCHEMA].[REDACTED: QUOTE_TABLE]
-    where [REDACTED: date_partition] >= dateadd(day, -1, current_date())
+        quote_id,
+        line_item,
+        customer_id,
+        material_id,
+        quantity,
+        net_value,
+        quote_date,
+        sales_person_id,
+        source_timestamp
+    from source_quotes
+    where quote_date >= dateadd(day, -1, current_date())
 ),
 
 enrich_product_portfolio as (
@@ -34,9 +34,9 @@ enrich_product_portfolio as (
         sq.sales_person_id,
         /* Product portfolio classification */
         case
-            when sq.material_id like '[REDACTED: pattern 1]%' then 'data-integration'
-            when sq.material_id like '[REDACTED: pattern 2]%' then 'automation'
-            when sq.material_id like '[REDACTED: pattern 3]%' then 'connectivity'
+            when sq.material_id like 'DI-%' then 'data-integration'
+            when sq.material_id like 'AU-%' then 'automation'
+            when sq.material_id like 'CO-%' then 'connectivity'
             else 'other'
         end as portfolio_code,
         pm.portfolio_name,
@@ -109,5 +109,3 @@ select
     sales_person_id,
     current_timestamp() as dbt_loaded_at
 from governance_flags
-
--- ponytail: materialized as table for chatbot + BI queries (not incremental yet; append-only refresh if needed later)