Skip to content
OpenSmartRoute
All models
agent

Customer support agent

support-agent

Handles orders, refunds, subscriptions and account issues via internal tools.

Decision and plan target (no provider attached) PII allowed Tool calling
Price per 1M tokens
$2.00
$0.0020 per 1k
Requests · 30d
0
no traffic
Latency
1500 ms
declared
Success rate
n/a
quality prior 0.80

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, Qa, Extract, Escalate
Complexity band0.00 - 0.70
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.

  • I want a refund for order #12345, it arrived damaged.
  • Cancel my subscription and confirm by email.
  • My account is locked, help me reset my password.

Route to it

This agent is not executed by the platform. Ask the router for a decision restricted to kinds=["agent"] 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 a refund for order #12345, it arrived damaged.", "kinds": ["agent"], "top_k": 3}'

# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of agent 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 a refund for order #12345, it arrived damaged.", "kinds": ["agent"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]])  # e.g. support-agent first when it fits
Customer support agent (support-agent) - OpenSmartRoute