AI Ticket Platform
AI-native technical support ticket system for single-enterprise private deployment.
The product centers on support tickets and business knowledge, with configurable Agents, Skills, MCP tools, model gateway, vector retrieval, and enterprise audit controls.
Current Status
Active implementation. The project has a runnable Django + React baseline with enterprise governance, ticket and knowledge workflows, an administrator-facing AI configuration workspace, and the first trusted ticket-intake loop: natural-language drafting, missing-field completion, explicit review, idempotent confirmation, MinIO-backed images, artifacts, and audit history. The real text-model workflow passed locally; real vision-model acceptance remains pending.
Key docs:
- Project blueprint
- Capability status
- Design discussion log
- Local setup
- AI platform demo acceptance
- Trusted ticket intake acceptance
- Frontend design system
Target Stack
- Backend: Django, Django Ninja, PostgreSQL, pgvector, Redis, Celery, MinIO
- Frontend: React, Vite, Tailwind CSS, shadcn/ui, Radix UI, TanStack Table
- AI: OpenAI Python SDK-compatible provider adapter, model gateway, vector retrieval, MCP client
- Deployment: Docker Compose first