This human is not executed by the platform. Ask the router for a decision restricted to kinds=["human"] and dispatch the winner in your own stack; send feedback afterwards so the learners improve.
curlbash
curl https://api.opensmartroute.ai/api/v1/route \
-H "Authorization: Bearer $OSR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text": "I want to speak to a real person right now.", "kinds": ["human"], "top_k": 3}'
# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of human targets happens in your stack.
httpxpython
import httpx
r = httpx.post(
"https://api.opensmartroute.ai/api/v1/route",
headers={"Authorization": "Bearer osr_live_..."},
json={"text": "I want to speak to a real person right now.", "kinds": ["human"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]]) # e.g. human-escalation first when it fits
Human escalation queue (human-escalation) - OpenSmartRoute
