{"id":"45a7754d-c038-4184-9976-519e72fd6711","entityType":"agent","slug":"crewai-advaykankaria-telecom-ai-ops","name":"telecom-ai-ops","canonicalUrl":"https://www.xpersona.co/agent/crewai-advaykankaria-telecom-ai-ops","canonicalPath":"/agent/crewai-advaykankaria-telecom-ai-ops","generatedAt":"2026-10-10T05:39:48.506Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T20:05:57.700Z","emptyReason":null},"description":"A LangGraph-orchestrated AI system combining LlamaIndex, Google ADK, and CrewAI to automate telecom customer support, network diagnostics, and billing resolutions. Telecom AI Operations Center 🛰️ Welcome to the **Telecom AI Operations Center**! This project acts as an intelligent, multi-agent automated front door for Telecom Telecom customer support and NOC teams. By integrating specialized frameworks into a single LangGraph-orchestrated workflow, the system can instantly resolve complex queries spanning policy documents, live operational databases, and billing systems. ✨ Capa","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/AdvayKankaria/telecom-ai-ops","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/AdvayKankaria/telecom-ai-ops","kind":"source"}],"safetyScore":66,"overallRank":18.2,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"A LangGraph-orchestrated AI system combining LlamaIndex, Google ADK, and CrewAI to automate telecom customer support, network diagnostics, and billing resolutio"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:05:57.700Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:05:57.700Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:05:57.693Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T20:05:57.700Z","lastCrawledAt":"2026-10-09T20:05:57.693Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T20:05:57.693Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T05:39:48.505Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-advaykankaria-telecom-ai-ops/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T20:05:57.700Z","emptyReason":null},"readme":"# Telecom AI Operations Center 🛰️\n\n![Telecom Operations Center](https://img.shields.io/badge/Agentic-AI-blue.svg)\n![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-green.svg)\n\nWelcome to the **Telecom AI Operations Center**! This project acts as an intelligent, multi-agent automated front door for Telecom Telecom customer support and NOC teams. By integrating specialized frameworks into a single LangGraph-orchestrated workflow, the system can instantly resolve complex queries spanning policy documents, live operational databases, and billing systems.\n\n## ✨ Capabilities & Architecture\n\nOur system employs a modular, microservice-based architecture that uses the best tool for every specific domain:\n\n1. **Policy & FAQ Knowledge** \n   * **Framework:** `LlamaIndex` Document RAG\n   * **Purpose:** Embeds and searches company policy TXT files (e.g. Roaming, SLAs).\n2. **Network Analytics**\n   * **Framework:** `LlamaIndex` Semantic SQL\n   * **Purpose:** Queries historical outage and performance metrics in natural language.\n3. **Network Diagnostics**\n   * **Framework:** `Google ADK` (Agent Development Kit) A2A Microservice\n   * **Purpose:** Connects via SQL to tower metrics to actively diagnose connection drops.\n4. **Billing Resolution**\n   * **Framework:** `Google ADK` A2A Microservice\n   * **Purpose:** Checks duplicate charges and applies credits directly to the SQL database.\n5. **Customer Communications**\n   * **Framework:** `CrewAI`\n   * **Purpose:** Employs a multi-agent crew to draft and review the final response for empathy and compliance.\n6. **Orchestration & UI**\n   * **Framework:** `LangGraph` & `Streamlit`\n   * **Purpose:** The LangGraph Supervisor dynamically routes the user query to the correct specialists, while Streamlit visualizes the Agent Execution Trace.\n\n## 🚀 Quick Start Guide\n\nFollow these steps to initialize the environment, seed the database, and run the microservices.\n\n### 1. Prerequisites\n- **Python 3.11+**\n- A valid **OpenAI API Key** (for LlamaIndex, LangGraph, and CrewAI)\n- A valid **Google Gemini API Key** (for Google ADK agents)\n\n### 2. Environment Setup\nCreate a virtual environment and install dependencies:\n```bash\npython3 -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt\n```\n\nSet up your environment variables:\n```bash\ncp .env.example .env\n# Open .env and add your OPENAI_API_KEY and GOOGLE_API_KEY\n```\n\n### 3. Initialize the Database\nThis will create `data/telecom_ops.db` and insert seed data representing customers, towers, outages, and billing charges:\n```bash\npython init_db.py\n```\n\n### 4. Start the Microservices\nYou must run the Google ADK Agents as standalone A2A microservices alongside the Streamlit app. Open three separate terminal windows and run:\n\n**Terminal 1:** Network Diagnostics Agent (Port 8001)\n```bash\nPYTHONPATH=. python adk_services/network_diagnostics/agent.py\n```\n\n**Terminal 2:** Billing Resolution Agent (Port 8002)\n```bash\nPYTHONPATH=. python adk_services/billing_resolution/agent.py\n```\n\n**Terminal 3:** Streamlit User Interface\n```bash\nPYTHONPATH=. python -m streamlit run ui/app.py\n```\n\n## 🎯 Demo Scenarios\n\nOnce the Streamlit UI is running at `http://localhost:8501`, try pasting these real-world scenarios into the chat:\n\n1. **Policy Query:** `\"What is Telecom's roaming policy for Western Europe?\"`\n2. **Network Analytics:** `\"Which region had the most CRITICAL network outages recently?\"`\n3. **Diagnostics:** `\"My 5G keeps dropping in Austin near tower TX-512. Please diagnose.\"`\n4. **Billing Action:** `\"Customer CUST-10002 was charged twice for Unlimited Plus. Investigate and apply credit.\"`\n5. **Complex Multi-Agent Flow:** `\"We had a 6-hour outage in the Midwest. Am I eligible for SLA credit and what does policy say?\"`\n\n## 🧪 Automated Testing (Promptfoo)\n\nThis project integrates **promptfoo** to automate the testing of the agentic system.\n\nTo evaluate all of the demo scenarios against expected logic assertions automatically:\n1. Ensure Node.js is installed (`npx` must be available).\n2. Open a new terminal.\n3. Run the evaluation:\n```bash\nsource ../.venv/bin/activate\nPYTHONPATH=. npx promptfoo@latest eval\n```\n\n## 🛠️ Troubleshooting\n\n| Issue | Resolution |\n|---|---|\n| **ADK unavailable** | Ensure both ADK agent services are running on ports 8001 and 8002. |\n| **Empty SQL answers** | Verify `init_db.py` ran successfully and `data/telecom_ops.db` exists. |\n| **Hugging Face Errors** | The app handles local cache automatically, but ensure write permissions to `.hf_cache`. |\n| **Model Errors** | We strictly use `gpt-4.1-mini` as configured. |\n","readmeExcerpt":"Telecom AI Operations Center 🛰️ Welcome to the **Telecom AI Operations Center**! This project acts as an intelligent, multi-agent automated front door for Telecom Telecom customer support and NOC teams. By integrating specialized frameworks into a single LangGraph-orchestrated workflow, the system can instantly resolve complex queries spanning policy documents, live operational databases, and billing systems. ✨ Capa","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python3 -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt"},{"language":"bash","snippet":"cp .env.example .env\n# Open .env and add your OPENAI_API_KEY and GOOGLE_API_KEY"},{"language":"bash","snippet":"python init_db.py"},{"language":"bash","snippet":"PYTHONPATH=. python adk_services/network_diagnostics/agent.py"},{"language":"bash","snippet":"PYTHONPATH=. python adk_services/billing_resolution/agent.py"},{"language":"bash","snippet":"PYTHONPATH=. python -m streamlit run ui/app.py"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"A LangGraph-orchestrated AI system combining LlamaIndex, Google ADK, and CrewAI to automate telecom customer support, network diagnostics, and billing resolutions. Telecom AI Operations Center 🛰️ Welcome to the **Telecom AI Operations Center**! This project acts as an intelligent, multi-agent automated front door for Telecom Telecom customer support and NOC teams. By integrating specialized frameworks into a single LangGraph-orchestrated workflow, the system can instantly resolve complex queries spanning policy documents, live operational databases, and billing systems. ✨ Capa","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":390,"uniquenessScore":65,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:05:57.700Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:05:57.700Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:39:48.506Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}