Loading
automation-agent
Drives a web browser or a desktop application on the person's behalf - opens pages, logs in, fills forms, clicks through a checkout, downloads statements, moves and renames files, pastes into the field in front - and reports what it did. Acts; does not write essays.
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.
Domains the signal layer detected on requests that ended here.
No routed requests yet. Declared domains: General, Customer Support, Finance, Travel, Hr.
Hard stops enforced before scoring.
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.
curl https://api.opensmartroute.ai/api/v1/route \
-H "Authorization: Bearer $OSR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text": "Open the bank portal, log in and download last month's statement as PDF.", "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.import httpx
r = httpx.post(
"https://api.opensmartroute.ai/api/v1/route",
headers={"Authorization": "Bearer osr_live_..."},
json={"text": "Open the bank portal, log in and download last month's statement as PDF.", "kinds": ["agent"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]]) # e.g. automation-agent first when it fitsExamples the similarity strategy matches against.