api all systems normal
Get API keyEleven requests, ready to run. Every type names its answer: choice (one of your labels), score (a level on your scale), truth (a probability), number (a value on your grid). Every card holds the exact body sent to /v1/decide and the answer it gets back, ready to open in the playground.
One lesson per question type, each a decision developers automate every day. Each asks one question and shows exactly what comes back: the fields, the numbers and how your code reads them.
Give it your options. It picks exactly one and returns a probability for every option.
Stop skipping the last page when the cursor lands on an exact multiple of the page size. Adds a regression test for 100 items at 25 per page.
criteria
fixpicked at 0.86confidence 0.83
then your code
confidence 0.83 clears a 0.7 threshold, so the commit is labeled fix and the changelog updates on its own.
Give it an ordered scale. It returns the expected level and how the probability spreads over every level.
Checkout fails for every customer paying with Apple Pay since this morning's release. The button spins and then shows 'payment declined'. Card payments still work.
criteria
2.60nearest level: blockerconfidence 0.60
then your code
confidence 0.60 is under 0.7, so the code takes the cautious level, blocker, and rolls the release back on its own.
Is this statement true? One calibrated probability from 0.00 to 1.00 that the statement is true. 0.80 means true about 8 times in 10. Your code picks the cut-off: 0.50 for a plain yes or no, higher when acting on a false yes is costly.
Hi, I see two identical charges of $49.00 for order #4471 on the same day. I only placed the order once.
criteria
0.97trueprobability it is truerefunds at 0.80
then your code
0.97 clears the 0.80 threshold, so the duplicate charge is refunded and the reply goes out on its own.
One value on a grid you set (min, max and an optional step), with a calibrated probability for every value: the most probable value, the expected value and the confidence.
Drone frame over row B4 of the north car park, camera pointing straight down.
grid
7most probable valueconfidence 0.77expected 6.97
then your code
confidence 0.77 clears 0.7, so row B4 is logged at 7 cars and the car park's free-space sign updates on its own.
Seven jobs teams still hand-code with brittle rules or hand to a slow chat model, each answered in one call, and one control loop that streams its decisions. The code acts on every answer the moment it lands.
3 questions, one call
Route every ticket, rank how urgent it is and pay back double charges before anyone opens the inbox.
0.94truerefund, clears 0.80
input: webhook: new ticket
Customer: I was charged twice and nobody has replied for 3 days.
answers, one call
routeChoice, billingurgencyScore, urgentrefundTruth, refunds at 0.80then your code
if route.choice == "billing"if urgency.score >= 2if refund.truth >= 0.803 questions, one call
Before an agent runs a tool call, check it is needed and how hard it would be to undo.
block0.83verdict, risk destructive
answers, one call
verdictChoice, blockriskScore, destructivein_scopeTruth, runs at 0.80then your code
block 0.83, risk 2.83 (destructive), needed for the task 0.04 false: the call never runs, and the agent gets it back to plan a narrower one.
3 questions, one call
Allow, limit or remove each comment the moment it is posted, with a toxicity level and a promotion check in the same call.
remove0.61action, toxicity harsh
account 2 days old, 1 earlier removal
This is useless. Anyone who ships this should quit programming. Check my profile for a REAL tool, 50% off today only.
what the code did
answers, one call
actionChoice, removetoxicityScore, harshpromotionTruth, strips links at 0.80then your code
remove 0.61 is under 0.7, so the safe action runs at once: the comment is hidden before anyone replies. Promotion 0.88 true clears 0.80: links stripped.
5 questions, 1 image, one call
Read a receipt photo against the expense claim: total, date, currency and policy, in one call.
input: receipt photo
input: expense claim
0.97truetotal matches, pays at 0.90
answers, one call
total_matchesTruth, pays at 0.90date_matchesTruth, pays at 0.90currencyChoice, SEKlegibleScore, fully readablealcoholTruth, splits at 0.80then your code
total 0.97 true and date 0.95 true both clear 0.90, currency SEK 0.94: the claim is paid. Alcohol 0.91 true moves the wine to the entertainment budget.
3 questions, one call
Score each signup from its note and first-week usage, and tell production builds from evaluations.
input: signup
2.49hotfit, hot
rate limit, set by the answer
fast track 0.90 true, upgrades at 0.85
answers, one call
fitScore, hotintentChoice, productionfast_trackTruth, upgrades at 0.85then your code
fit 2.49 (hot), production 0.78, fast track 0.90 true: the account moves to production limits and gets the production onboarding email now.
3 questions, 1 image, one call
Check the photo shows the item the seller describes, and grade its condition from the picture.
0.93truephoto matches, publishes at 0.85
input: listing photo + description
goes live as
Vintage 35mm rangefinder camera
answers, one call
matchesTruth, publishes at 0.85itemChoice, film cameraconditionScore, goodthen your code
match 0.93 true clears 0.85, film camera 0.90, condition good: the listing goes live with a verified photo and a condition tag.
3 questions, one call
Read a customer statement, count what is overdue and how late the oldest is, and send the right reminder on its own.
4(0.84)overdue invoices, acts at 0.70
input: customer statement
| invoice | issued | due | amount | status |
|---|---|---|---|---|
| INV-2041 | 2026-06-15 | 2026-07-15 | 1,240.00 | open |
| INV-2058 | 2026-07-03 | 2026-08-02 | 410.00 | paid 2026-08-01 |
| INV-2063 | 2026-07-21 | 2026-08-20 | 860.00 | open |
| INV-2069 | 2026-07-29 | 2026-08-28 | 395.00 | paid 2026-09-02 |
| INV-2077 | 2026-08-06 | 2026-09-05 | 1,120.00 | part paid, 300.00 open |
| INV-2081 | 2026-08-13 | 2026-09-12 | 640.00 | open |
| INV-2090 | 2026-08-31 | 2026-09-30 | 780.00 | paid 2026-09-29 |
| INV-2094 | 2026-09-10 | 2026-10-10 | 520.00 | open |
| INV-2102 | 2026-09-24 | 2026-10-24 | 915.00 | open |
answers, one call
overdueNumber, expected 3.99oldest_daysNumber, expected 78.08reminderChoice, firmthen your code
4 (0.84) overdue and firm 0.76 both clear 0.7, so the firm reminder goes out today with every open invoice listed. The oldest reads 78 days at 0.61, under 0.7, so the letter says more than 60 days instead of an exact count.
2 questions per frame, one open session
coming soonOpen one session with the mission brief and two questions, then stream every telemetry frame and get the flight mode and an abort check back for each one.
More than 10 decisions a second?Use a session.
1. open oncePOST /v1/sessions
2. then stream framesWebSocket /v1/sessions/{id}/stream
frames in, one decision back for each
battery 0.36, wind 11.0 m/s, home 835 m
battery 0.34, wind 11.2 m/s, home 830 m
battery 0.31, wind 11.4 m/s, home 820 m
aborts at 0.80; below it the mission flies on
then your code
Frame 17 comes back return 0.84, abort 0.07 false. The supervisor hands return-to-home to the drone's flight controller, which flies the route back; the next frames keep checking abort on the way.
latest wins
Every card on this page is the same call with a different state and different questions. Paste this one as it is, then make it yours in the playground and copy it out as curl, Python or TypeScript.
curl https://api.decisionnode.com/v1/decide \ -H "Authorization: Bearer $DECISIONNODE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "decisionnode-flash-latest", "state": "Charged twice for order #4471, no reply in 3 days.", "questions": { "route": { "type": "choice", "criteria": { "billing": "money", "bug": "broken" } }, "urgency": { "type": "score", "criteria": ["routine", "today", "urgent"] }, "refund": { "type": "truth", "criteria": { "true": "Charged twice", "false": "Anything else" } } } }'