Simpli Assess

Assess helps support teams build a data-driven automation strategy. Score case complexity, identify repetitive patterns, and rate automation potential — so you know exactly which case types to automate first and which need human expertise.

Simpli Assess provides complexity scoring, automation readiness analysis, and repetitive pattern detection for support operations.

Configuration

Variable	Default	Description
`APP_PORT`	`8013`	Server port
`LITELLM_MODEL`	`openai/gpt-5-mini`	LLM model for analysis
`AUTOMATION_THRESHOLD`	`0.7`	Score above this is considered automatable
`COMPLEXITY_DIMENSIONS`	`technical,procedural,emotional,multi_step`	Dimensions to score
`CORS_ORIGINS`	`*`	Allowed CORS origins (comma-separated)

Start the server

simpli-assess serve

API endpoints

All endpoints are under the /api/v1 prefix.

POST `/api/v1/readiness`

Full automation readiness report — combines complexity, automation, and repetition analysis.

Request:

{
  "cases": [
    {
      "id": "c-1",
      "subject": "Password reset",
      "conversation": [{"role": "customer", "content": "How do I reset my password?"}],
      "resolution": "Sent password reset link",
      "handle_time_minutes": 3.5
    },
    {
      "id": "c-2",
      "subject": "Forgot password",
      "conversation": [{"role": "customer", "content": "I forgot my password"}],
      "resolution": "Sent password reset link",
      "handle_time_minutes": 2.8
    },
    {
      "id": "c-3",
      "subject": "Complex billing dispute",
      "conversation": [
        {"role": "customer", "content": "I was charged for 3 items I returned last month and I want a full refund plus compensation"}
      ],
      "handle_time_minutes": 45.0
    }
  ]
}

The role field accepts values from the AuthorType enum: customer, agent, or system.

Response:

{
  "audit_id": "r-abc123",
  "summary": {
    "total_cases": 3,
    "automatable_count": 2,
    "automatable_rate": 0.67,
    "estimated_time_savings_pct": 0.45,
    "top_automation_candidates": ["password reset"],
    "top_blockers": ["emotional complexity", "multi-step resolution"]
  },
  "complexity": { "..." },
  "automation": { "..." },
  "repetition": { "..." }
}

POST `/api/v1/complexity`

Score case complexity across technical, procedural, emotional, and multi-step dimensions.

POST `/api/v1/automation`

Score automation readiness with reasoning, blockers, and suggested approach.

POST `/api/v1/repetition`

Find repetitive case patterns with frequency and handle time analysis.

GET `/health`

Health check.

Integration example

import httpx

client = httpx.Client(base_url="http://localhost:8013")

# Score complexity for a batch
complexity = client.post("/api/v1/complexity", json={
    "cases": [
        {"id": "c-1", "subject": "Password reset",
         "conversation": [{"role": "customer", "content": "Reset my password"}]},
    ],
}).json()

for result in complexity["results"]:
    print(f"{result['case_id']}: {result['tier']} ({result['overall_score']:.2f})")

# Find automation candidates
automation = client.post("/api/v1/automation", json={
    "cases": cases,
    "automation_threshold": 0.6,
}).json()

print(f"Automatable: {automation['automatable_count']}/{automation['total_cases']}")
for r in automation["results"]:
    if r["automatable"]:
        print(f"  {r['case_id']}: {r['suggested_approach']}")

Next steps

Executive Reporting — Present automation readiness data to leadership
Integration Overview — Connect Assess to your ticketing system
Model Selection — Choose the right model for complexity analysis

On this page