830 lines
35 KiB
JSON
830 lines
35 KiB
JSON
{
|
||
"id": "experience-360",
|
||
"name": "Experience 360",
|
||
"description": "Revolutionize customer engagement with Experience360 a powerful AI-driven platform designed for both agents and customers.",
|
||
"status": "87% Complete",
|
||
"statusType": "progress",
|
||
"tabs": [
|
||
{
|
||
"name": "Overview",
|
||
"description": "Revolutionize customer engagement with Experience360 a powerful AI-driven platform designed for both agents and customers.",
|
||
"goals": ["Enhance the profitability of the target product by 6%"],
|
||
"objective": "Leverage a self-directed Multi Agent System to achieve a 6% increase in target product profitability",
|
||
"roles": [
|
||
{
|
||
"name": "Product Manager",
|
||
"description": ""
|
||
}
|
||
],
|
||
"benefits": [
|
||
"Deliver proactive insights to help product managers anticipate market trends and customer needs",
|
||
"Enable data-driven decision-making that directly supports revenue growth and strategic product development",
|
||
"Identify opportunities to boost profitability through optimized pricing, feature prioritization, and resource allocation",
|
||
"Strengthen customer loyalty by aligning product decisions with user behavior and engagement data"
|
||
]
|
||
},
|
||
{
|
||
"name": "Bill of Materials",
|
||
"description": "Bill of Materials - Visual representation of Multi-Agent System architecture and component relationships.",
|
||
"data": {
|
||
"orchestrator": [
|
||
{
|
||
"id": "orchestrator-1",
|
||
"name": "Enrich 360 Lyza Agent",
|
||
"type": "ORCHESTRATOR_AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": [
|
||
"agent-churn",
|
||
"agent-recommendation",
|
||
"agent-sentiment",
|
||
"agent-chart-generation",
|
||
"agent-competitor-insights",
|
||
"agent-price-optimization",
|
||
"agent-product-intelligence",
|
||
"agent-usage-analyzer",
|
||
"agent-market-insights",
|
||
"agent-similar-accounts",
|
||
"agent-epm"
|
||
]
|
||
}
|
||
],
|
||
"agents": [
|
||
{
|
||
"id": "agent-churn",
|
||
"name": "Churn Management Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Manages customer churn prevention"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": ["model-churn", "model-churn-mitigation"]
|
||
},
|
||
{
|
||
"id": "agent-recommendation",
|
||
"name": "Product Recommendation Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Suggests products by customer"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": ["model-recommendation"]
|
||
},
|
||
{
|
||
"id": "agent-sentiment",
|
||
"name": "Customer Sentiment Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Analyzes customer sentiment and feedback"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": ["model-sentiment"]
|
||
},
|
||
{
|
||
"id": "agent-chart-generation",
|
||
"name": "Chart Generation Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Creates charts and graphs from data"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-competitor-insights",
|
||
"name": "Competitor Insights Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Offers insights on product and market"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-price-optimization",
|
||
"name": "Price Optimization Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Offers insights for customer"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-product-intelligence",
|
||
"name": "Product Intelligence Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Offers insights for product"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-usage-analyzer",
|
||
"name": "Usage Analyzer Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Offers insights for user"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-market-insights",
|
||
"name": "Market Insights Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Offers insights for industry and market"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-similar-accounts",
|
||
"name": "Similar Accounts",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Finds accounts for users"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "agent-epm",
|
||
"name": "EPM Agent",
|
||
"type": "AGENT",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"description": "Offers data analytics and digital"
|
||
},
|
||
"upstreamConnections": ["orchestrator-1"],
|
||
"downstreamConnections": []
|
||
}
|
||
],
|
||
"models": [
|
||
{
|
||
"id": "model-churn",
|
||
"name": "Likelihood of Churn Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": ["agent-churn"],
|
||
"downstreamConnections": ["fs-churn", "is-churn"]
|
||
},
|
||
{
|
||
"id": "model-recommendation",
|
||
"name": "Product Recommendation Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 12,
|
||
"size": "2 GB"
|
||
},
|
||
"upstreamConnections": ["agent-recommendation"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-sentiment",
|
||
"name": "Sentiment Analysis Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 6,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": ["agent-sentiment"],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-competitor-insights",
|
||
"name": "Competitor Insights Agent",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-price-optimization",
|
||
"name": "Price Optimization Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-product-intelligence",
|
||
"name": "Product Intelligence Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-usage-classification",
|
||
"name": "Usage Classification Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-similar-accounts",
|
||
"name": "Similar Accounts Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-usage-forecasting",
|
||
"name": "Usage Forecasting Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "model-churn-mitigation",
|
||
"name": "Churn Mitigation Model",
|
||
"type": "MODEL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"parameters": 8,
|
||
"size": "1 GB"
|
||
},
|
||
"upstreamConnections": ["agent-churn"],
|
||
"downstreamConnections": ["fs-churn", "is-churn"]
|
||
}
|
||
],
|
||
"tools": [
|
||
{
|
||
"id": "tool-batch",
|
||
"name": "Batch job",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 4
|
||
},
|
||
"upstreamConnections": ["model-churn"],
|
||
"downstreamConnections": ["fs-churn"]
|
||
},
|
||
{
|
||
"id": "tool-stream",
|
||
"name": "Stream",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 2
|
||
},
|
||
"upstreamConnections": ["model-churn"],
|
||
"downstreamConnections": ["is-churn"]
|
||
},
|
||
{
|
||
"id": "tool-chart-generation",
|
||
"name": "Chart Generation Tool",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 4
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "tool-news-mcf",
|
||
"name": "News MCF tool",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 2
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "tool-weather-mcf",
|
||
"name": "Weather MCF tool",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 3
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "tool-web-search",
|
||
"name": "Web Search Tool",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 2
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "tool-epm-text-to-sql",
|
||
"name": "EPM Text-to-SQL Tool",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 1
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "tool-epm-mcf",
|
||
"name": "EPM MCF Tool",
|
||
"type": "TOOL",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"interfaces": 1
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
}
|
||
],
|
||
"dataEntities": [
|
||
{
|
||
"id": "entity-customer",
|
||
"name": "Customer",
|
||
"type": "DATA_ENTITY",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 15
|
||
},
|
||
"upstreamConnections": ["fs-churn", "is-churn"],
|
||
"downstreamConnections": ["ds-hogan"]
|
||
},
|
||
{
|
||
"id": "entity-invoices",
|
||
"name": "Invoices",
|
||
"type": "DATA_ENTITY",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 12
|
||
},
|
||
"upstreamConnections": ["fs-churn", "is-churn"],
|
||
"downstreamConnections": ["ds-hogan"]
|
||
},
|
||
{
|
||
"id": "entity-transactions",
|
||
"name": "Transactions",
|
||
"type": "DATA_ENTITY",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 18
|
||
},
|
||
"upstreamConnections": ["fs-churn", "is-churn"],
|
||
"downstreamConnections": ["ds-hogan"]
|
||
},
|
||
{
|
||
"id": "entity-products",
|
||
"name": "Products",
|
||
"type": "DATA_ENTITY",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 8
|
||
},
|
||
"upstreamConnections": ["fs-churn", "is-churn"],
|
||
"downstreamConnections": ["ds-hogan"]
|
||
}
|
||
],
|
||
"featureStores": [
|
||
{
|
||
"id": "fs-churn",
|
||
"name": "Churn feature Store",
|
||
"type": "FEATURE_STORE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 8,
|
||
"workflows": 1
|
||
},
|
||
"upstreamConnections": ["model-churn", "model-churn-mitigation"],
|
||
"downstreamConnections": [
|
||
"entity-customer",
|
||
"entity-invoices",
|
||
"entity-transactions",
|
||
"entity-products"
|
||
]
|
||
},
|
||
{
|
||
"id": "fs-product-recommendation",
|
||
"name": "Product Recommendation Feature Store",
|
||
"type": "FEATURE_STORE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 10,
|
||
"workflows": 2
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
}
|
||
],
|
||
"insightStores": [
|
||
{
|
||
"id": "is-churn",
|
||
"name": "Churn Insights Store",
|
||
"type": "INSIGHTS_STORE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 8,
|
||
"workflows": 1
|
||
},
|
||
"upstreamConnections": ["model-churn", "model-churn-mitigation"],
|
||
"downstreamConnections": [
|
||
"entity-customer",
|
||
"entity-invoices",
|
||
"entity-transactions",
|
||
"entity-products"
|
||
]
|
||
},
|
||
{
|
||
"id": "insight-churn-data",
|
||
"name": "Churn Insights Data",
|
||
"type": "INSIGHTS_STORE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 6,
|
||
"workflows": 1
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "insight-product-recommendation",
|
||
"name": "Product Recommendation Insights data",
|
||
"type": "INSIGHTS_STORE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"fields": 8,
|
||
"workflows": 2
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
}
|
||
],
|
||
"dataSources": [
|
||
{
|
||
"id": "ds-hogan",
|
||
"name": "Hogan Banking Core",
|
||
"type": "DATA_SOURCE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"files": 12,
|
||
"fields": 45
|
||
},
|
||
"upstreamConnections": [
|
||
"entity-customer",
|
||
"entity-invoices",
|
||
"entity-transactions",
|
||
"entity-products"
|
||
],
|
||
"downstreamConnections": []
|
||
},
|
||
{
|
||
"id": "ds-salesforce",
|
||
"name": "Salesforce CRM",
|
||
"type": "DATA_SOURCE",
|
||
"version": "V 1.2",
|
||
"metadata": {
|
||
"files": 8,
|
||
"fields": 32
|
||
},
|
||
"upstreamConnections": [],
|
||
"downstreamConnections": []
|
||
}
|
||
]
|
||
}
|
||
},
|
||
{
|
||
"name": "LYZA",
|
||
"description": "Multi-Agent System (MAS) designed to empower users to create AI application",
|
||
"system_prompt": "# 🧠 System Prompt: Multi-Agent System for Profitability Optimization\n\n## 🎯 System Objective\n**Leverage a self-directed Multi-Agent System (MAS) to enhance the profitability of the target product by 6%.**\n\n## 🧑💼 Primary User Persona\n- **Role**: Product Manager \n- **Goals**:\n - Deliver proactive insights on market trends and customer needs.\n - Enable data-driven decision-making for revenue and strategic development.\n - Identify opportunities through pricing, feature prioritization, and resource allocation.\n - Align product direction with user behavior to boost loyalty and retention.\n\n\n## 🧠 System Architecture & Agents\n\n### 1. Market Trends Agent\n- Scrapes and synthesizes industry news, competitor moves, and consumer behavior.\n- Forecasts market demand shifts.\n- **Outputs**: Trend dashboards, early warnings, opportunity maps.\n\n### 2. Customer Intelligence Agent\n- Analyzes interaction logs, reviews, NPS, and churn indicators.\n- Segments users by behavior, sentiment, and value.\n- **Outputs**: Loyalty drivers, friction points, feature adoption trends.\n\n### 3. Pricing & Profitability Agent\n- Simulates pricing and bundling strategies using internal and competitive data.\n- Optimizes for revenue per user, margin, and LTV/CAC.\n- **Outputs**: Dynamic pricing recs, test strategies.\n\n### 4. Feature Prioritization Agent\n- Evaluates feature ROI using A/B test data, analytics, and requests.\n- Prioritizes by impact, feasibility, alignment.\n- **Outputs**: Roadmap priorities with ROI scoring.\n\n### 5. Strategic Alignment Agent\n- Maps recommendations to business OKRs and product KPIs.\n- Aligns output with executive vision.\n- **Outputs**: OKR scorecards, strategic impact alerts.\n\n---\n\n## 📊 Key Performance Indicators (KPIs)\n\n| KPI | Target | Measured By |\n|-----|--------|-------------|\n| **Product Profitability Uplift** | +6% | (Revenue - COGS)/Revenue |\n| **Customer Lifetime Value (LTV)** | +10% | Avg. revenue per customer lifecycle |\n| **Churn Rate** | -15% | % of users leaving per month |\n| **Feature Adoption Rate** | +20% | % of users using new features |\n| **ARPU (Avg. Revenue/User)** | +5% | Revenue ÷ Active Users |\n| **Time-to-Insight** | -30% | Data → Action latency |\n| **Insight Utilization Rate** | +40% | % of insights influencing actions |\n\n---\n\n## 🔍 Sample Insights\n\n### Market-Driven\n- \"Gen Z shift to mobile-first productivity tools = 12% drop in desktop use.\"\n- \"Competitor pricing shift caused 8% churn in overlapping user base.\"\n\n### Customer Behavior\n- \"Low onboarding completion = 3x higher churn.\"\n- \"Power users love Feature X; UI promotion could lift adoption by 15%.\"\n\n### Profitability Levers\n- \"Feature A + B bundle → +9% profit in Tier 2 users.\"\n- \"Proactive support bot reduces per-user cost → +2% margin.\"\n\n### Feature ROI\n- \"Feature C = $480K/year projected uplift.\"\n- \"Feature B = high dev cost, <1% revenue impact — deprioritize.\"\n\n### Strategic Forecasts\n- \"Entering Vertical Y in 6 months → +15% LTV based on market signals.\"\n\n---\n\n## 🧩 Data Assets Utilized\n\n- **Product Analytics**: Mixpanel, Amplitude, GA\n- **CRM & Sales**: Salesforce, HubSpot\n- **Customer Feedback**: NPS, Zendesk, UserVoice\n- **Behavioral Tools**: Segment, FullStory, Heap\n- **Financial Systems**: ERP, P&L Data\n- **Competitive Data**: SimilarWeb, AppAnnie\n- **Custom Data**: Proprietary usage and support metrics\n\n---\n\n## 🔄 Decision Loop & Agent Autonomy\n\n- **Central Coordination Hub** integrates agent output.\n- Resolves conflicts, ranks ideas by profitability impact.\n- Proposes action plans with data traceability.\n- **Escalation** to Product Manager for high-impact decisions.\n\n---\n\n## 🔐 Governance, Control & Guardrails\n\n- **Human-in-the-loop** for major product/pricing decisions.\n- **Bias detection** on predictive models.\n- **Explainability** for all recommendations (with data trace).\n- **Audit logs** for decision transparency.\n\n---\n\n## 📅 Weekly Outputs\n\n- **Executive Summary**: Top 5 profitability drivers.\n- **Feature ROI Tracker**: Updated roadmap impacts.\n- **Customer Health Report**: Segments at risk/opportunity.\n- **Pricing Simulations**: Scenarios with projected profit impact.\n- **Agent Confidence Scores**: Trust levels per suggestion.\n\n---\n\n## ✅ Summary\n\nA self-directed MAS empowers the Product Manager to:\n- Predict market trends.\n- Act on user needs.\n- Make smarter roadmap and pricing decisions.\n- Achieve a sustained 6%+ profitability uplift with explainable, data-backed insights.",
|
||
"mas": [
|
||
{
|
||
"name": "Enrich360 Offline Process",
|
||
"description": "Batch enrichment engine designed for large-scale data processing, ensuring accuracy and consistency at scale",
|
||
"updated_at": "2025-06-04T05:54:09+00:00",
|
||
"tags": ["assistants", "agents", "MAS"],
|
||
"id": "532ed470-b97d-4171-8121-07fbff800728",
|
||
"folder_id": "a2956334-e842-44ac-96aa-7190bfa5396c"
|
||
},
|
||
{
|
||
"name": "Enrich360 Interactive",
|
||
"description": "Empowers product managers with real-time, user-driven insights to make faster, data-backed decisions",
|
||
"updated_at": "2025-06-04T05:54:20+00:00",
|
||
"tags": ["assistants", "agents", "MAS"],
|
||
"id": "f8d4f2f9-5285-45b0-8eda-cd0043e230e3",
|
||
"folder_id": "a2956334-e842-44ac-96aa-7190bfa5396c"
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"name": "Presentations",
|
||
"description": "Visual insights and demos showcasing Experience 360 capabilities.",
|
||
"deployed_urls": [
|
||
{
|
||
"url": "/intarc/dashboard",
|
||
"description": "This is where the Enrich360 UI is deployed. Click to open the live instance."
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"name": "Deployment",
|
||
"description": "Tools and settings to launch, monitor, and manage AI solution in real-time environments.",
|
||
"configuration": "Kubernetes",
|
||
"version": "V 1.2",
|
||
"replicas": {
|
||
"model": 3,
|
||
"agent": 2,
|
||
"logging": 1,
|
||
"monitoring": 1
|
||
},
|
||
"yaml": "# -----------------------------------------------------\n# enrich360 AI Model Deployment\n# -----------------------------------------------------\napiVersion: apps/v1\nkind: Deployment\nmetadata:\n name: enrich360-model\n labels:\n app: enrich360\n component: model\nspec:\n replicas: 3\n selector:\n matchLabels:\n app: enrich360\n component: model\n template:\n metadata:\n labels:\n app: enrich360\n component: model\n spec:\n containers:\n - name: model-server\n image: enrich360/model-server:latest\n ports:\n - containerPort: 8000\n env:\n - name: MODEL_PATH\n value: /models/classifier-v2.pth\n - name: LOG_LEVEL\n value: info\n volumeMounts:\n - name: model-storage\n mountPath: /models\n volumes:\n - name: model-storage\n persistentVolumeClaim:\n claimName: enrich360-model-pvc\n\n---\napiVersion: v1\nkind: Service\nmetadata:\n name: enrich360-model-service\nspec:\n selector:\n app: enrich360\n component: model\n ports:\n - port: 80\n targetPort: 8000\n type: ClusterIP\n\n---\n# -----------------------------------------------------\n# enrich360 Agent (AI Decision-Maker)\n# -----------------------------------------------------\napiVersion: apps/v1\nkind: Deployment\nmetadata:\n name: enrich360-agent\n labels:\n app: enrich360\n component: agent\nspec:\n replicas: 2\n selector:\n matchLabels:\n app: enrich360\n component: agent\n template:\n metadata:\n labels:\n app: enrich360\n component: agent\n spec:\n containers:\n - name: agent-service\n image: enrich360/agent:stable\n ports:\n - containerPort: 8500\n env:\n - name: MODEL_API_URL\n value: http://enrich360-model-service/predict\n - name: AGENT_MODE\n value: production\n\n---\napiVersion: v1\nkind: Service\nmetadata:\n name: enrich360-agent-service\nspec:\n selector:\n app: enrich360\n component: agent\n ports:\n - port: 85\n targetPort: 8500\n type: ClusterIP\n\n---\n# -----------------------------------------------------\n# enrich360 Logging Service (e.g., Fluentd, Loki)\n# -----------------------------------------------------\napiVersion: apps/v1\nkind: Deployment\nmetadata:\n name: enrich360-logging\n labels:\n app: enrich360\n component: logging\nspec:\n replicas: 1\n selector:\n matchLabels:\n app: enrich360\n component: logging\n template:\n metadata:\n labels:\n app: enrich360\n component: logging\n spec:\n containers:\n - name: logger\n image: enrich360/logging:latest\n ports:\n - containerPort: 24224\n volumeMounts:\n - name: log-storage\n mountPath: /var/log/enrich360\n volumes:\n - name: log-storage\n emptyDir: {}\n\n---\napiVersion: v1\nkind: Service\nmetadata:\n name: enrich360-logging-service\nspec:\n selector:\n app: enrich360\n component: logging\n ports:\n - port: 24224\n targetPort: 24224\n type: ClusterIP\n\n---\n# -----------------------------------------------------\n# enrich360 Monitoring Dashboard (e.g., Prometheus + Grafana)\n# -----------------------------------------------------\napiVersion: apps/v1\nkind: Deployment\nmetadata:\n name: enrich360-monitoring\n labels:\n app: enrich360\n component: monitoring\nspec:\n replicas: 1\n selector:\n matchLabels:\n app: enrich360\n component: monitoring\n template:\n metadata:\n labels:\n app: enrich360\n component: monitoring\n spec:\n containers:\n - name: prometheus\n image: prom/prometheus:latest\n ports:\n - containerPort: 9090\n volumeMounts:\n - name: prom-config\n mountPath: /etc/prometheus\n volumes:\n - name: prom-config\n configMap:\n name: enrich360-prometheus-config\n\n---\napiVersion: v1\nkind: Service\nmetadata:\n name: enrich360-monitoring-service\nspec:\n selector:\n app: enrich360\n component: monitoring\n ports:\n - port: 90\n targetPort: 9090\n type: ClusterIP\n\n---\n# -----------------------------------------------------\n# Persistent Volume Claim for Model Storage\n# -----------------------------------------------------\napiVersion: v1\nkind: PersistentVolumeClaim\nmetadata:\n name: enrich360-model-pvc\nspec:\n accessModes:\n - ReadWriteOnce\n resources:\n requests:\n storage: 2Gi\n\n---\n# -----------------------------------------------------\n# ConfigMap for Prometheus Configuration (Example)\n# -----------------------------------------------------\napiVersion: v1\nkind: ConfigMap\nmetadata:\n name: enrich360-prometheus-config\ndata:\n prometheus.yml: |\n global:\n scrape_interval: 15s\n scrape_configs:\n - job_name: 'enrich360'\n static_configs:\n - targets: ['enrich360-model-service:80', 'enrich360-agent-service:85']",
|
||
"services": [
|
||
"enrich360-model-service",
|
||
"enrich360-agent-service",
|
||
"enrich360-logging-service",
|
||
"enrich360-monitoring-service"
|
||
],
|
||
"endpoints": [
|
||
{
|
||
"name": "Get Revenue Optimizer",
|
||
"description": "AI Agent",
|
||
"url": "/ai-agent",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Alerts",
|
||
"description": "Dataset",
|
||
"url": "/dataset",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Product Metrics",
|
||
"description": "Dashboard",
|
||
"url": "/dashboard",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Churn Management Insights",
|
||
"description": "ML Model",
|
||
"url": "/ml-model",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Prospect Identification Insights",
|
||
"description": "Model",
|
||
"url": "/model",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Market Insights",
|
||
"description": "Gen AI Model",
|
||
"url": "/gen-ai-model",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Customer Sentiment",
|
||
"description": "ML Model",
|
||
"url": "/ml-model",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Competitor Watch",
|
||
"description": "Gen AI Model",
|
||
"url": "/gen-ai-model",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Get Suggested Questions",
|
||
"description": "Gen AI Model",
|
||
"url": "/gen-ai-model",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "LYZA Enrich360 MAS",
|
||
"description": "Enrich360 MAS",
|
||
"url": "/enrich360-mas",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
},
|
||
{
|
||
"name": "Authentication Service",
|
||
"description": "Handles user authentication and authorization",
|
||
"url": "/auth",
|
||
"version": "1.0.0",
|
||
"status": "Active"
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"name": "KPI",
|
||
"description": "Dashboard tracking key performance indicators to evaluate AI application effectiveness.",
|
||
"business": [
|
||
{
|
||
"name": "Revenue",
|
||
"description": "Overall Revenue Targets",
|
||
"id": "kpi-business-001",
|
||
"url": "/kpis/revenue",
|
||
"version": "V 1.2",
|
||
"status": "Declining",
|
||
"trend": "-4%",
|
||
"target": "$100.3M"
|
||
},
|
||
{
|
||
"name": "Profitability",
|
||
"description": "Product Profitability",
|
||
"id": "kpi-business-002",
|
||
"url": "/kpis/profitability",
|
||
"version": "V 1.2",
|
||
"status": "Declining",
|
||
"trend": "-6%",
|
||
"target": "45%"
|
||
},
|
||
{
|
||
"name": "Cost to Serve",
|
||
"description": "Cost to Serve my product",
|
||
"id": "kpi-business-003",
|
||
"url": "/kpis/cost-to-serve",
|
||
"version": "V 1.2",
|
||
"status": "Declining",
|
||
"trend": "-2.5%",
|
||
"target": "$18.2M"
|
||
},
|
||
{
|
||
"name": "Churn Rate",
|
||
"description": "Target churn rate of customers",
|
||
"id": "kpi-business-004",
|
||
"url": "/kpis/churn-rate",
|
||
"version": "V 1.2",
|
||
"status": "Improving",
|
||
"trend": "+2%",
|
||
"target": "12.5%"
|
||
},
|
||
{
|
||
"name": "Product Usage",
|
||
"description": "Transactions",
|
||
"id": "kpi-business-005",
|
||
"url": "/kpis/product-usage",
|
||
"version": "V 1.2",
|
||
"status": "Declining",
|
||
"trend": "-$2.35M",
|
||
"target": "24.5M"
|
||
},
|
||
{
|
||
"name": "Waivers",
|
||
"description": "Product Waivers",
|
||
"id": "kpi-business-006",
|
||
"url": "/kpis/waivers",
|
||
"version": "V 1.2",
|
||
"status": "Improving",
|
||
"trend": "+11.3%",
|
||
"target": "$9.6M"
|
||
}
|
||
],
|
||
"technical": [
|
||
{
|
||
"name": "Processing Efficiency",
|
||
"description": "Current processing efficiency rate",
|
||
"id": "kpi-technical-001",
|
||
"url": "/kpis/processing-efficiency",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"current": "98%",
|
||
"target": "95%",
|
||
"trend": "+3% from last month"
|
||
},
|
||
{
|
||
"name": "Error Rate",
|
||
"description": "System error occurrence rate",
|
||
"id": "kpi-technical-002",
|
||
"url": "/kpis/error-rate",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"current": "1.2%",
|
||
"target": "<2%",
|
||
"trend": "-0.5% from last month"
|
||
},
|
||
{
|
||
"name": "Response Time",
|
||
"description": "Average API response time",
|
||
"id": "kpi-technical-003",
|
||
"url": "/kpis/response-time",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"current": "150ms",
|
||
"target": "<200ms",
|
||
"trend": "-50ms from last month"
|
||
},
|
||
{
|
||
"name": "Uptime",
|
||
"description": "System availability percentage",
|
||
"id": "kpi-technical-004",
|
||
"url": "/kpis/uptime",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"current": "99.9%",
|
||
"target": "99.9%",
|
||
"trend": "+0.1% from last month"
|
||
},
|
||
{
|
||
"name": "Data Accuracy",
|
||
"description": "Data validation success rate",
|
||
"id": "kpi-technical-005",
|
||
"url": "/kpis/data-accuracy",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"current": "99.5%",
|
||
"target": "99%",
|
||
"trend": "+0.5% from last month"
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"name": "Reports",
|
||
"description": "Generated summaries and logs detailing system performance and agent behavior.",
|
||
"reports": [
|
||
{
|
||
"name": "Performance Report",
|
||
"description": "Detailed analysis of system performance metrics",
|
||
"id": "report-performance-001",
|
||
"url": "/reports/performance",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"last_updated": "Today"
|
||
},
|
||
{
|
||
"name": "Usage Analytics",
|
||
"description": "User engagement and system utilization statistics",
|
||
"id": "report-usage-analytics-001",
|
||
"url": "/reports/usage-analytics",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"last_updated": "Today"
|
||
},
|
||
{
|
||
"name": "Error Log Report",
|
||
"description": "Comprehensive error tracking and resolution status",
|
||
"id": "report-error-log-001",
|
||
"url": "/reports/error-logs",
|
||
"version": "V 1.2",
|
||
"status": "Active",
|
||
"last_updated": "Today"
|
||
}
|
||
]
|
||
}
|
||
]
|
||
}
|