mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-18 15:29:36 +00:00
Phase 1 - Repo Hardening: - README.md, LICENSE, SECURITY.md, CONTRIBUTING.md - GitHub Actions repo-hygiene workflow - docs/: ARCHITECTURE, DATA-MODEL, API-MAP, AGENT-MAP, DEPLOYMENT-NOTES Phase 2 - Database Models (7 new): - Company, Contact, Call, Commission, Payout, Dispute, GuaranteeClaim - Consent, Complaint, Policy, KnowledgeArticle, SectorAsset - Updated models/__init__.py with all 32+ models Phase 3 - API Surfaces (16 new route files): - companies, contacts, calls, meetings, commissions, payouts - disputes, guarantees, consents, complaints, knowledge - sectors, presentations, supervisor, admin, health - Updated router.py with all 24 route groups Phase 4 - AI Prompt Registry (18 agent contracts): - Lead Qualification, Affiliate Recruitment Evaluator, Onboarding Coach - Outreach Writer, Arabic WhatsApp, English Conversation, Voice Call - Meeting Booking, Sector Strategist, Objection Handler - Proposal Drafter, QA Reviewer, Compliance Reviewer - Knowledge Retrieval, Revenue Attribution, Fraud Reviewer - Guarantee Claim Reviewer, Management Summary Phase 5 - Communication Templates: - 15 production templates (WhatsApp, email, voice, internal) - Arabic + English variants with variable interpolation Phase 6 - Compliance Center (7 legal docs): - Privacy policy, Terms of service, Refund policy - Commission policy, Affiliate rules, Consent policy, Data protection - All PDPL-compliant, Arabic Phase 7 - Celery Workers (fully implemented): - follow_up_tasks: automated lead follow-ups with workflow execution - message_tasks: WhatsApp/email/SMS with retry logic - notification_tasks: daily reports, meeting reminders, in-app notifications - affiliate_tasks: target checking, commission calculation, weekly reports, AI outreach Phase 8 - Knowledge Base OS (8 files): - Services overview, Pricing policy, Channel policy, Meeting policy - Identity rules, Escalation rules, Hiring path, Internal SOPs https://claude.ai/code/session_01KnJgK7RwyeCvRZTRThHtfU
124 lines
4.8 KiB
Markdown
124 lines
4.8 KiB
Markdown
# Architecture Overview
|
|
|
|
## System Diagram
|
|
|
|
```
|
|
+------------------+
|
|
| Client / App |
|
|
| (Browser/Mobile) |
|
|
+--------+---------+
|
|
|
|
|
HTTPS (443)
|
|
|
|
|
+--------+---------+
|
|
| Nginx |
|
|
| (Reverse Proxy) |
|
|
+---+---------+----+
|
|
| |
|
|
/api/* | | /*
|
|
| |
|
|
+-------------+ +----+-----------+
|
|
| FastAPI | | Next.js |
|
|
| Backend | | Frontend |
|
|
| :8000 | | :3000 |
|
|
+--+-----+----+ +----------------+
|
|
| |
|
|
+--------+ +--------+
|
|
| |
|
|
+-------+--------+ +--------+-------+
|
|
| PostgreSQL 15 | | Redis 7 |
|
|
| (Primary DB) | | (Cache/Broker) |
|
|
+----------------+ +-------+--------+
|
|
|
|
|
+-------+--------+
|
|
| Celery Workers |
|
|
| + Celery Beat |
|
|
+----------------+
|
|
```
|
|
|
|
## Multi-Tenant Model
|
|
|
|
```
|
|
Request --> Auth Middleware --> Extract tenant_id from JWT
|
|
|
|
|
v
|
|
Query scoping: WHERE tenant_id = :tid
|
|
|
|
|
v
|
|
All reads/writes isolated per tenant
|
|
```
|
|
|
|
- Every database table with tenant-scoped data includes a `tenant_id` foreign key.
|
|
- Middleware extracts `tenant_id` from the authenticated JWT on every request.
|
|
- Database queries are automatically scoped. Cross-tenant access is blocked at the ORM layer.
|
|
- Superadmin role can query across tenants for platform-level reporting.
|
|
|
|
## AI Agent Layer
|
|
|
|
```
|
|
Incoming Event (lead, message, call, meeting request)
|
|
|
|
|
v
|
|
+------------------+
|
|
| Agent Router | --> selects agent(s) based on event type
|
|
+------------------+
|
|
|
|
|
v
|
|
+------------------+ +------------------+
|
|
| Agent Executor | --> | LLM Provider |
|
|
| (Celery Task) | | (OpenAI / etc) |
|
|
+------------------+ +------------------+
|
|
|
|
|
v
|
|
+------------------+
|
|
| Action Handler | --> update DB, send message, book meeting, escalate
|
|
+------------------+
|
|
```
|
|
|
|
- 18 specialized agents (see `docs/AGENT-MAP.md`)
|
|
- Each agent has a defined role, input schema, output schema, and escalation rules
|
|
- Agents execute as Celery tasks for async processing
|
|
- Outputs are logged to `ai_conversations` for audit
|
|
|
|
## Integration Layer
|
|
|
|
```
|
|
+------------------+ +------------------+ +------------------+
|
|
| WhatsApp | | Email | | SMS |
|
|
| Business API | | (SMTP/Provider) | | (Gateway) |
|
|
+--------+---------+ +--------+---------+ +--------+---------+
|
|
| | |
|
|
+------------------------+------------------------+
|
|
|
|
|
+-------+--------+
|
|
| Message Bus |
|
|
| (Redis Queue) |
|
|
+-------+--------+
|
|
|
|
|
+-------+--------+
|
|
| Celery Worker |
|
|
+----------------+
|
|
```
|
|
|
|
- WhatsApp Business API for Arabic-first automated conversations
|
|
- Email for proposals, notifications, and follow-ups
|
|
- SMS for OTP and urgent alerts
|
|
- All outbound messages queued through Redis for rate limiting and retry
|
|
|
|
## Major Modules
|
|
|
|
| Module | Location | Purpose |
|
|
|--------|----------|---------|
|
|
| Auth & Tenancy | `backend/auth/` | JWT, RBAC, tenant isolation |
|
|
| Lead Management | `backend/leads/` | Capture, scoring, qualification, assignment |
|
|
| Deal Pipeline | `backend/deals/` | Stage tracking, revenue forecasting |
|
|
| Affiliate System | `affiliate-system/` | Recruitment, onboarding, performance, commissions |
|
|
| AI Agents | `ai-agents/` | 18 specialized agents with prompt definitions |
|
|
| Knowledge Base | `knowledge-base/` | RAG articles, sector data, FAQ |
|
|
| Guarantee | `guarantee/` | Gold guarantee claims, disputes, refunds |
|
|
| Presentations | `presentations/` | Proposal and pitch deck generation |
|
|
| Meetings | `backend/meetings/` | AI-driven booking, calendar sync |
|
|
| Commissions | `backend/commissions/` | Calculation, payouts, dispute resolution |
|
|
| Notifications | `backend/notifications/` | Multi-channel delivery (WhatsApp, email, SMS, in-app) |
|
|
| Dashboard | `frontend/` | Analytics, pipeline views, admin panels |
|