Simpli Triage
AI-powered ticket classification, priority scoring, and intelligent routing.
When a customer submits a support ticket, Triage automatically determines what the ticket is about, how urgent it is, and which team should handle it. Agents spend less time sorting tickets and more time solving problems.
Simpli Triage classifies incoming support tickets by category and urgency, detects sentiment, and routes them to the right team or agent.
Configuration
| Variable | Default | Description |
|---|---|---|
APP_ENV | development | Environment name |
APP_PORT | 8000 | Server port |
APP_LOG_LEVEL | info | Log level |
LITELLM_MODEL | openai/gpt-5-nano | LLM model for classification |
REDIS_URL | — | Redis URL for Celery task queue |
DATABASE_URL | — | Database connection string |
Start the server
simpli-triage serveAPI endpoints
POST /classify
Classify a ticket by category, urgency, and sentiment.
Request:
{
"subject": "Can't process payment",
"body": "I've been trying to pay for 2 hours and keep getting error 500",
"metadata": {"account_type": "premium"}
}Response:
{
"category": "billing",
"urgency": "high",
"sentiment": "negative",
"confidence": 0.87
}POST /route
Route a classified ticket to the appropriate team and agent.
Request:
{
"ticket_id": "T-001",
"category": "billing",
"urgency": "high",
"sentiment": "negative"
}Response:
{
"team": "billing",
"agent": "A-012",
"reason": "High urgency billing issue routed to specialist"
}GET /rules
List all configured routing rules.
GET /health
Health check — returns {"status": "ok"}.
Integration example
Classify and route a ticket in one flow:
import httpx
client = httpx.Client(base_url="http://localhost:8000")
# Step 1: classify
classification = client.post("/classify", json={
"subject": "Account locked out",
"body": "I can't access my account after password reset",
}).json()
# Step 2: route based on classification
routing = client.post("/route", json={
"ticket_id": "T-123",
**classification,
}).json()
print(f"Routed to {routing['team']}: {routing['reason']}")Next steps
- The Ticket Lifecycle — See how Triage fits into the full service pipeline
- Integration Overview — Connect Triage to your helpdesk
- Model Selection — Choose the right model for classification