Twelve request bodies you can send to POST /api/v1/decisions as-is — the decisions-1 endpoint on this site, a callable OpenAI Decisions API alternative. Each card shows the request, an illustrative response, and how a system would act on it.
Checkout incident routing
Request
{
"model": "decisions-1",
"state": "Checkout shows a blank page after Pay is clicked. The customer is on the live store, not a sandbox.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should own this ticket?",
"criteria": {
"payments": "Checkout, billing, or payment processing.",
"frontend": "Rendering, layout, or browser behavior.",
"account": "Login, permissions, or profile access."
}
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"team": {
"type": "choice",
"choice": "frontend",
"probabilities": {
"frontend": 0.71,
"payments": 0.24,
"account": 0.05
},
"confidence": 0.47
}
},
"credits_used": 1
}Act on it: Send the ticket to frontend; if payments had come out near 0.5, route to a triage queue instead.
Request
{
"model": "decisions-1",
"state": "I was charged twice for the same annual plan this morning. Please send the extra charge back.",
"questions": {
"refund": {
"type": "noul",
"instructions": "Is the customer asking for money back?"
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"refund": {
"type": "noul",
"noul": 0.98
}
},
"credits_used": 1
}Act on it: noul ≥ 0.9 hands the ticket to the refunds queue automatically; below that, an agent reads it.
Request
{
"model": "decisions-1",
"state": "Stripe payouts have been failing for three days and the merchant is losing sales.",
"questions": {
"urgency": {
"type": "score",
"instructions": "How urgent is this ticket?",
"criteria": [
"Can wait for the next release",
"Should be handled this week",
"Blocking revenue right now"
]
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"urgency": {
"type": "score",
"score": 2,
"legend": [
"Can wait for the next release",
"Should be handled this week",
"Blocking revenue right now"
],
"probabilities": {
"0": 0.02,
"1": 0.14,
"2": 0.84
},
"confidence": 0.84
}
},
"credits_used": 1
}Act on it: Score 2 pages the on-call engineer; score 1 joins the weekly queue; score 0 waits for the next release.
Request
{
"model": "decisions-1",
"state": "User message: \"Share your login and I will fix the account for you tonight.\"",
"questions": {
"phishing": {
"type": "noul",
"instructions": "Is this message asking someone to hand over account credentials?"
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"phishing": {
"type": "noul",
"noul": 0.96
}
},
"credits_used": 1
}Act on it: noul ≥ 0.8 blocks the message and flags the sender; the rest go through untouched.
Request
{
"model": "decisions-1",
"state": "We route 40,000 support tickets a week and need a probability before we auto-assign a queue. Budget is approved this quarter.",
"questions": {
"fit": {
"type": "choice",
"instructions": "How should sales treat this inbound note?",
"criteria": {
"ready": "A real workflow, a volume, and a buying window.",
"nurture": "Interest without a stated workflow or timeline.",
"ignore": "No product fit."
}
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"fit": {
"type": "choice",
"choice": "ready",
"probabilities": {
"ready": 0.88,
"nurture": 0.11,
"ignore": 0.01
},
"confidence": 0.77
}
},
"credits_used": 1
}Act on it: ready gets a same-day sales reply; nurture joins the newsletter track; ignore gets a polite decline.
Request
{
"model": "decisions-1",
"state": "Listing text: \"Guaranteed 30% returns every month. Send crypto to this wallet to join.\"",
"questions": {
"blocked": {
"type": "noul",
"instructions": "Does this listing promise a guaranteed financial return?"
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"blocked": {
"type": "noul",
"noul": 0.99
}
},
"credits_used": 1
}Act on it: noul ≥ 0.9 holds the listing and notifies the seller; anything lower still hits the human review queue.
Request
{
"model": "decisions-1",
"state": "The renewal note says the team may not continue because exports fail every Friday and nobody has answered the last two tickets.",
"questions": {
"risk": {
"type": "score",
"instructions": "How high is the chance this account does not renew?",
"criteria": [
"Unlikely to leave",
"Unhappy, still using the product",
"Likely to cancel"
]
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"risk": {
"type": "score",
"score": 2,
"legend": [
"Unlikely to leave",
"Unhappy, still using the product",
"Likely to cancel"
],
"probabilities": {
"0": 0.07,
"1": 0.24,
"2": 0.69
},
"confidence": 0.55
}
},
"credits_used": 1
}Act on it: Score 2 opens a save play with the account owner; score 1 schedules a check-in; score 0 stays on autopilot.
Request
{
"model": "decisions-1",
"state": "Vendor invoice 4481 is $18,400. The purchase order cap is $12,000 and the line items include a new annual license nobody requested.",
"questions": {
"exception": {
"type": "choice",
"instructions": "Which exception should accounts payable open?",
"criteria": {
"over_po": "The amount is above the purchase order.",
"unexpected_item": "A line item was not requested.",
"both": "The amount and a line item are both wrong."
}
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"exception": {
"type": "choice",
"choice": "both",
"probabilities": {
"both": 0.86,
"over_po": 0.1,
"unexpected_item": 0.04
},
"confidence": 0.76
}
},
"credits_used": 1
}Act on it: both opens a case with procurement; over_po alone goes to the approver; unexpected_item alone goes to the requester.
Request
{
"model": "decisions-1",
"state": "The support agent has the refund policy loaded and the customer confirmed their order number. No tool call has run yet.",
"questions": {
"next_action": {
"type": "choice",
"instructions": "What should the agent do next?",
"criteria": {
"issue_refund": "Call the refund tool for the confirmed order.",
"ask_details": "Ask the customer for more information.",
"escalate": "Hand the conversation to a human."
}
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"next_action": {
"type": "choice",
"choice": "issue_refund",
"probabilities": {
"issue_refund": 0.82,
"ask_details": 0.13,
"escalate": 0.05
},
"confidence": 0.69
}
},
"credits_used": 1
}Act on it: issue_refund fires the refund tool; ask_details sends a follow-up question; escalate hands the thread to a human.
Request
{
"model": "decisions-1",
"state": "Bug report: the export button spins forever on Firefox but works in Chrome. Two enterprise accounts reported it this week.",
"questions": {
"severity": {
"type": "score",
"instructions": "What severity should this bug get?",
"criteria": [
"Cosmetic",
"Minor workaround exists",
"Blocks a core flow"
]
},
"is_duplicate": {
"type": "noul",
"instructions": "Does this report describe a known browser-specific failure pattern?"
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"severity": {
"type": "score",
"score": 2,
"legend": [
"Cosmetic",
"Minor workaround exists",
"Blocks a core flow"
],
"probabilities": {
"0": 0.04,
"1": 0.22,
"2": 0.74
},
"confidence": 0.58
},
"is_duplicate": {
"type": "noul",
"noul": 0.31
}
},
"credits_used": 1
}Act on it: Two questions in one call — severity drives the queue, is_duplicate decides whether to link an existing issue.
Request
{
"model": "decisions-1",
"state": "App store review, 4 stars: \"Solid app, but the last update broke dark mode on my tablet.\"",
"questions": {
"needs_reply": {
"type": "noul",
"instructions": "Should the team reply to this review?"
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"needs_reply": {
"type": "noul",
"noul": 0.81
}
},
"credits_used": 1
}Act on it: noul ≥ 0.7 drafts a reply for the reviewer; lower scores are just logged for the weekly digest.
Request
{
"model": "decisions-1",
"state": "A customer on the Enterprise plan reports their single sign-on is down for all 300 employees.",
"questions": {
"sla_tier": {
"type": "choice",
"instructions": "Which SLA tier applies to this ticket?",
"criteria": {
"p1": "Full outage for an enterprise account.",
"p2": "Major feature degraded.",
"p3": "Standard request."
}
}
}
}Illustrative response
{
"model": "decisions-1",
"answers": {
"sla_tier": {
"type": "choice",
"choice": "p1",
"probabilities": {
"p1": 0.93,
"p2": 0.06,
"p3": 0.01
},
"confidence": 0.87
}
},
"credits_used": 1
}Act on it: p1 starts the incident timer and notifies the account owner; p2/p3 land in the normal queues.
Run any example now
Every request above works as-is — open one in the playground or send it with your own key.
