All models
workflow
Customer notification workflow
workflow-notify-customer
Sends order, shipping and delivery status updates to the customer over email and SMS.
Decision and plan target (no provider attached) PII allowed Tool calling
- Price per 1M tokens
- free
- $0 per 1k
- Requests · 30d
- 0
- no traffic
- Latency
- 2000 ms
- declared
- Success rate
- n/a
- quality prior 0.90
Traffic over 30 days
Requests per day this target answered on this deployment, with the cost line.
No requests yet. Route something from the playground to see usage here.
- Tokens
- 0
- Spend
- $0
- Previous window
- 0 req
Routed for
Domains the signal layer detected on requests that ended here.
No routed requests yet. Declared domains: Customer Support.
Capabilities
DomainsCustomer Support
ActionsAction
Complexity band0.00 - 0.50
Languages*
Context windowundeclared
Streamingyes
Policy constraints
Hard stops enforced before scoring.
Data boundaryPublic
Regionsanywhere
PIIallowed
Max input tokensunlimited
Tenantsall
Representative prompts
Examples the similarity strategy matches against.
- Notify the customer that order #4521 has shipped.
- Send a delivery update for the delayed order.
- Run the customer notification workflow.
Route to it
This workflow is not executed by the platform. Ask the router for a decision restricted to kinds=["workflow"] 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": "Notify the customer that order #4521 has shipped.", "kinds": ["workflow"], "top_k": 3}'
# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of workflow 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": "Notify the customer that order #4521 has shipped.", "kinds": ["workflow"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]]) # e.g. workflow-notify-customer first when it fits