Quickstart
Two steps to your first call: send a decision request to the public endpoint, then route on calibrated confidence.
1. CURL — Call the Public Endpoint (SYSTEMONE CHOICE primitive)
bashcurl -X POST https://api.unfork.ai/v1/systemone \
-H "Content-Type: application/json" \
-d '{
"task": "choice",
"text": "Refund request is 3 days overdue, but credit history is excellent. Approve automatically?",
"candidates": ["approve", "reject", "escalate_to_human"]
}'
2. PYTHON Client Example (with confidence & escalation)
pythonimport requests
ENDPOINT = "https://api.unfork.ai/v1/systemone"
payload = {
"task": "choice",
"text": "Large withdrawal request from an unusual location",
"candidates": ["allow", "challenge_otp", "block_and_alert"]
}
res = requests.post(ENDPOINT, json=payload).json()
decision = res["decision"]
confidence = res["calibrated_confidence"]
# Route automatically based on calibrated confidence
if confidence < 0.85:
route_to_human_triage(payload["text"], reason="low_calibrated_conf")
else:
execute_action(decision)
Built on official Qwen3-8B weights plus a QLoRA adapter; a single 24GB GPU (bf16) handles loading and inference. Full specs on the Models page.