supercode168/enterprise-workflow-ai-agent

1---2title: Enterprise Workflow AI Agent3colorFrom: blue4colorTo: indigo5sdk: gradio6app_file: app_hf.py7pinned: false8license: mit9---10 11# Enterprise Workflow AI Agent12 13An AI workflow automation MVP for cross-functional enterprise teams. It demonstrates how one AI platform can support service operations, investment research, and compliance review through structured outputs, retrieval, checklists, drafts, dashboards, and API-ready endpoints.14 15This project is designed for a Forward-Deployed AI / AI Transformation intern profile: it demonstrates business problem framing, data pipeline design, structured AI outputs, retrieval, dashboarding, and API-ready architecture.16 17## Why This Project18 19Nan Fung's internship JD emphasizes building production-grade AI tools across business teams: agents, automated workflows, chatbots, data pipelines, dashboards, APIs, and enterprise system integration.20 21This MVP maps directly to that requirement:22 23- **Business workflow**: service request triage and follow-up24- **AI layer**: structured classification, urgency detection, checklist generation25- **Retrieval layer**: similar historical tickets and prior resolutions26- **Data layer**: SQLite ticket database27- **Interface layer**: browser dashboard and JSON API28- **Upgrade path**: LLM API, RAG vector store, FastAPI, Streamlit/React, MCP tools29 30## Current Features31 32- Load sample maintenance tickets33- Optional NYC 311 data fetch script34- Rule-based structured triage35- Similar case retrieval with lightweight TF-IDF36- Technician checklist generation37- Tenant reply drafting38- Investment document summarization and signal extraction39- Compliance obligation extraction and risk checklist generation40- SQLite persistence41- Browser dashboard42- JSON API endpoints43 44## Demo Screenshots45 46Local verification screenshots are generated under `screenshots/`. They are intentionally not pushed to Hugging Face in the lightweight Space version because the Hub requires Xet/LFS for binary assets.47 48## Architecture49 50```mermaid51flowchart LR52    A["Ticket / document input"] --> B["Structured triage engine"]53    B --> C["Category and urgency"]54    B --> D["Responsible team"]55    B --> E["Missing information"]56    A --> F["Historical case retrieval"]57    F --> G["Similar resolutions"]58    C --> H["Technician checklist"]59    D --> H60    G --> H61    C --> I["Tenant / stakeholder reply"]62    H --> J["Dashboard and API"]63    I --> J64```65 66## Project Scenarios67 681. **Service Operations Copilot**69   - Classify tenant or service requests70   - Retrieve similar historical cases71   - Generate technician checklist and tenant reply72 732. **Investment Research Copilot**74   - Summarize annual reports and company documents75   - Extract risks, revenue signals, and deal memo fields76 773. **Compliance Review Copilot**78   - Extract obligations, dates, clauses, and risk flags79   - Generate review checklist80 81## Run82 83### Hugging Face Spaces84 85The Space runs the Gradio app:86 87```bash88python app_hf.py89```90 91### Local HTML/API version92 93```bash94cd property_maintenance_ai_agent95/Users/yiplimin/.cache/codex-runtimes/codex-primary-runtime/dependencies/python/bin/python3 scripts/load_sample_data.py96/Users/yiplimin/.cache/codex-runtimes/codex-primary-runtime/dependencies/python/bin/python3 app.py97```98 99Then open:100 101```text102http://127.0.0.1:8765103```104 105Pages:106 107```text108http://127.0.0.1:8765/109http://127.0.0.1:8765/investment110http://127.0.0.1:8765/compliance111```112 113Try the JSON API:114 115```text116http://127.0.0.1:8765/api/triage?text=There%20is%20no%20hot%20water%20in%20the%20unit%20and%20the%20tenant%20has%20a%20baby117http://127.0.0.1:8765/api/investment?text=Revenue%20grew%2018%25%20but%20debt%20increased%20to%20USD%20120%20million118http://127.0.0.1:8765/api/compliance?text=The%20supplier%20shall%20maintain%20confidentiality%20and%20approval%20is%20required119```120 121## Resume Bullet Draft122 123Built a multi-scenario enterprise workflow AI agent MVP for service operations, investment research, and compliance review, combining structured ticket triage, urgency detection, historical case retrieval, document signal extraction, risk flagging, checklist generation, stakeholder draft generation, SQLite persistence, browser dashboarding, and JSON API endpoints.124 125## Interview Story126 127I built this project to simulate how an AI transformation intern could work across different business teams rather than being limited to one function. The system starts with service operations because maintenance tickets are concrete, frequent, and workflow-heavy. I then extended the same architecture to investment research and compliance review to show that the core pattern is reusable: take messy business input, convert it into structured output, retrieve relevant context, generate an action checklist, and expose the result through a usable interface.128 129The current version runs without paid LLM APIs so it is easy to demo publicly. The next version would replace deterministic rules with LLM structured outputs, add RAG over real internal documents, and expose MCP-compatible tools for enterprise system integration.130 131## Next Upgrade Steps132 1331. Replace rule-based triage with LLM structured output.1342. Add RAG over NYC 311/HPD historical resolution descriptions.1353. Add real investment reports and compliance policy samples.1364. Add FastAPI once dependencies are available.1375. Add OpenAI/Claude function calling and MCP-style tool wrappers.1386. Add screenshots, evaluation metrics, and a short demo video.139