Runnable demo · no sign-in
Run a harness, read the decision
- 01 pick
- 02 edit & run
- 03 read the answer
- 04 take the code
02Edit the state, then run
148/2000fixed questions
- choicedepartment
- scoreseverity
- noulescalate
03The decision
—
awaiting run
—
awaiting run
—
awaiting run
Verdict pending — department ≥ 0.8, otherwise send to a human triage queue instead of routing.
» waiting for a run04How this works
Three closed questions about one piece of text: which team, how bad, escalate or not. None of them produces language a person reads, so none of them needs a generative call.
Then, in code: The chosen team receives the ticket; severity sets the queue; a high escalation probability pages a human.
05Your code
// Route a support ticket — the call this page runs
const response = await fetch('https://ai.gateway.lovable.dev/v1/systemone', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.LOVABLE_API_KEY}`, // server side only
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'typesafe/jev-latest',
state, // the context your code already has, unchanged
questions: {
"department": {
"type": "choice",
"instructions": "Which team should handle this ticket?",
"criteria": {
"billing": "charges, invoices and refunds",
"technical": "bugs, outages and integration failures",
"account": "login, permissions and profile changes",
"other": "anything that does not fit the other teams"
}
},
"severity": {
"type": "score",
"instructions": "How severe is this for the customer?",
"criteria": [
"cosmetic or informational",
"degraded, a workaround exists",
"blocking, no workaround",
"blocking with financial or data loss"
]
},
"escalate": {
"type": "noul",
"instructions": "Should this go to a human immediately?"
}
},
}),
});
const { answers, usage } = await response.json();
// act on it, in code
const gate = answers.department;
if ((gate.confidence ?? gate.noul) < 0.8) {
// send to a human triage queue instead of routing
}Keep the key server-side. The question set is data — keep it next to the code that acts on the answer.
Now find these call-sites in your own project
The console reads a public repository or pasted files and names every AI call-site it can see, with the evidence behind each classification and the coverage it managed to read.