Quickstart

1. 1

   Get an API key#

   Open the console, go to API keys and choose Create key. The key is shown once, so copy it straight into your environment. Live keys start with dn_live_.

   Copy

   export DECISIONNODE_API_KEY="dn_live_..."

2. 2

   Send your first request#

   Post a state and your questions to https://api.decisionnode.com/v1/decidehttps://api.decisionnode.com/v1/decide. This one routes a support message, ranks its urgency and asks whether to refund it automatically.

   curlPythonTypeScript

   Copy

   curl https://api.decisionnode.com/v1/decide \
     -H "Authorization: Bearer $DECISIONNODE_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "decisionnode-latest",
       "state": "Customer: I was charged twice and nobody has replied for 3 days.",
       "questions": {
         "route": {
           "type": "choice",
           "instructions": "Where should this go?",
           "criteria": {
             "billing": "money",
             "bug": "broken",
             "account": "login"
           }
         },
         "urgency": {
           "type": "score",
           "instructions": "How urgent is this?",
           "criteria": ["routine", "today", "urgent", "critical"]
         },
         "refund": {
           "type": "truth",
           "instructions": "Refund this automatically?"
         }
       }
     }'

3. 3

   Read the answers#

   Each answer comes back under the key you gave its question. The route is billing with confidence 0.81, the urgency sits at 2.31 on your 0 to 3 scale, and the refund probability is 0.94. That last one is a Truth answer: the calibrated probability, from 0.00 to 1.00, that the statement is true, here that this charge should be refunded automatically. 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, as with a refund.

   Copy

   {
     "model": "decisionnode-1.0",
     "answers": {
       "route": {
         "type": "choice",
         "choice": "billing",
         "confidence": 0.81,
         "probabilities": { "account": 0.05, "billing": 0.87, "bug": 0.08 }
       },
       "urgency": {
         "type": "score",
         "score": 2.31,
         "confidence": 0.47,
         "legend": {
           "0": "routine",
           "1": "today",
           "2": "urgent",
           "3": "critical"
         },
         "probabilities": { "0": 0.01, "1": 0.09, "2": 0.48, "3": 0.42 }
       },
       "refund": { "type": "truth", "truth": 0.94 }
     },
     "usage": { "input_tokens": 62, "output_tokens": 0 }
   }

4. 4

   Branch on them#

   Answers are numbers and keys, so your code acts on them the moment they land. Sure cases go straight through; unsure ones take the safe path, still automatically.

   PythonTypeScript

   Copy

   route = answers["route"]
   urgency = answers["urgency"]
   refund = answers["refund"]
   
   if refund["truth"] >= 0.8:              # sure: refund now
       issue_refund(ticket)
       reply(ticket, template="refund_issued")
   elif route["confidence"] < 0.7:        # unsure: safe path
       reply(ticket, template="ask_for_order_id")
   else:                                  # sure: route it
       priority = round(urgency["score"])
       assign(ticket, route["choice"], priority)

What just happened#

• The model read the state once and answered all three questions in one pass, with decisionnode-latest.
• It generated no text: usage.output_tokens is always 0, and output is free.
• The request used 62 input tokens. At $0.042 per million, a million of these requests cost about $2.60.
• Up to 64k tokens fit in one request, so the state can be a whole thread or a JSON record.
• Choice, score and truth are three of the four question types. The fourth, Number, answers how many or what value, on a grid you set.

Next steps#

• Write better questionsOptions, scales and instructions that the model reads well.Read
• Gate on confidenceAct above a threshold, re-check the unsure middle with the full model, and take the safe path below it.Read
• Add an imageReceipts, photos and screenshots in the same request.Read
• Handle errors400 to 529: which to fix, which to retry, and what to do when credit runs out.Read