Bearprompt logo Bearprompt
Back to d1-ultra
d1-ultra Score
How to run d1-ultra

Score support urgency

Description

A Score from Liquid’s usage examples: a weighted position on a four-level rubric.

Copy

import os
from typesafe_sdk import Choice, Noul, Score, TypeSafeClient

client = TypeSafeClient(
    api_key=os.environ["LIQUID_API_KEY"],
    base_url="https://api.liquid.ai",
)

result = client.system_one(
    model="d1-ultra",
    state="Our production API is returning 500 errors on every request. All customers are affected. Revenue impact is approximately $12,000 per hour. Started 15 minutes ago.",
    questions={
        "urgency": Score(
            instructions="How urgent is this support request?",
            criteria=[
            "Can wait: no immediate business impact, can be addressed in normal queue",
            "Should handle today: minor inconvenience or non-blocking issue",
            "Time-sensitive: noticeable customer impact, needs attention within hours",
            "Blocking revenue: critical system failure affecting customers or revenue"
        ],
        )
    },
)

Worked example

Illustrative for this sample state, not a live run

Sample state

Our production API is returning 500 errors on every request. All customers are affected. Revenue impact is approximately $12,000 per hour. Started 15 minutes ago.
Score urgency

How urgent is this support request?

Score 3.00 on 0–3

  • 0. Can wait: no immediate business impact, can be addressed in normal queue 0%
  • 1. Should handle today: minor inconvenience or non-blocking issue 0%
  • 2. Time-sensitive: noticeable customer impact, needs attention within hours 0%
  • 3. Blocking revenue: critical system failure affecting customers or revenue 100%

Confidence 100%

What you might do next

If `urgency` is 2.5 or higher, page on-call immediately. If it is 1.5 or higher, escalate to senior support. Otherwise add it to the standard queue.

Tags

scoreincident
Loading...