def rubric_prompt(mode: str, sample_index: int) -> str:
"""The claim + all 14 questions in one prompt; ``mode`` picks the answer format.
``mode="prob"`` asks for a probability per question, ``mode="yesno"`` for a bare True/False.
``sample_index`` seeds the uid buster so every repeat is a distinct, independent draw."""
if mode == "yesno":
answer_format = (
"\n\nAnswer each question yes or no.\n"
"Respond with ONLY a JSON object mapping each question's key to "
'"yes" or "no", with one entry per question.'
)
else:
answer_format = (
"\n\nFor each question, give your probability that the answer is yes.\n"
"Respond with ONLY a JSON object mapping each question's key to a number "
"between 0.00 and 1.00, with one entry per question."
)
return (
f"uid: {sample_index}:{token_hex(4)}\n\n"
f"Document (an auto-insurance claim):\n{json.dumps(CLAIM, indent=2)}\n\nQuestions:\n"
+ "\n".join(f"- {key}: {question}" for key, question in QUESTIONS.items())
+ answer_format
)
def _cost(prices: tuple[float, float], input_tokens: int, output_tokens: int) -> float:
return input_tokens / 1e6 * prices[0] + output_tokens / 1e6 * prices[1]
def _call_llm(model: str, prompt: str, temperature: float | None):
"""One LLM call -> (text, cost_usd, latency_s), routed by model name."""
reasoning = model in REASONING_MODELS
started = perf_counter()
if model.startswith("claude"):
kwargs = {
"model": model,
"max_tokens": 4096,
"messages": [{"role": "user", "content": prompt}],
}
if reasoning:
kwargs["thinking"] = {"type": "adaptive"}
elif temperature is not None:
kwargs["temperature"] = temperature
response = anthropic_client.messages.create(**kwargs)
text = next((b.text for b in response.content if b.type == "text"), "")
usage = (response.usage.input_tokens, response.usage.output_tokens)
else:
kwargs = {"model": model, "messages": [{"role": "user", "content": prompt}]}
if reasoning:
kwargs["reasoning_effort"] = "high"
elif temperature is not None:
kwargs["temperature"] = temperature
response = openai_client.chat.completions.create(**kwargs)
text = response.choices[0].message.content
usage = (response.usage.prompt_tokens, response.usage.completion_tokens)
return text, _cost(LLM_PRICES[model], *usage), perf_counter() - started
# All samples (LLM and CosVec) are cached to ``json_cache.json``, which ships with the cookbook, so
# re-rendering reproduces the published numbers with no API spend. ``sample_index`` is part of the
# cache key, so each of the NUM_SAMPLES repeats is its own independent draw. Delete the file to
# re-sample live.
json_cache = JsonCache(Path("json_cache.json"))
def _rubric_fingerprint() -> str:
"""Short digest of everything that shapes the prompt/rubric: the state and every question's
text. Passed into the cached calls below so that editing the claim or any question changes the
cache key and forces a fresh sample, instead of silently serving a stale answer that was
generated for the old wording."""
payload = json.dumps([CLAIM, QUESTIONS], sort_keys=True, default=str)
return hashlib.sha256(payload.encode()).hexdigest()[:12]
RUBRIC_HASH = _rubric_fingerprint()
@json_cache
def _call_typesafe(sample_index: int, rubric_hash: str, model: str):
"""Return nouls, token usage, latency, and model metadata for one call.
``rubric_hash`` and ``model`` prevent reuse across rubric or model changes.
Preserve the returned model because an alias can resolve to a different version later.
"""
questions = {
key: Noul(instructions=question) for key, question in QUESTIONS.items()
}
started = perf_counter()
response = typesafe_client.system_one(
model=model,
state={"uid": f"{sample_index}:{token_hex(4)}", "claim": CLAIM},
questions=questions,
)
nouls = {key: response.answers[key].noul for key in QUESTIONS}
return (
nouls,
response.usage.input_tokens,
response.usage.output_tokens,
perf_counter() - started,
{"requested_model": model, "response_model": response.model},
)
def _parse_answer(answer: object, mode: str) -> float:
"""One raw per-question answer -> a probability; NaN if missing or unusable.
``mode="prob"`` reads the answer as a number; ``mode="yesno"`` maps True/False to 1.0 / 0.0.
Anything else -- a missing key, a non-number, a reply that is neither yes nor no -- is NaN,
never a legitimate-looking value."""
if answer is None:
return float("nan")
if mode == "yesno":
text = str(answer).strip().lower()
if text == "yes":
return 1.0
if text == "no":
return 0.0
return float("nan")
try:
return float(answer)
except (TypeError, ValueError):
return float("nan")
@json_cache
def ask_llm_rubric(
model: str,
mode: str,
temperature: float | None,
sample_index: int,
rubric_hash: str,
):
"""One LLM rubric query -> (per-question probabilities keyed by question key, cost_usd,
latency_s); NaNs where the reply doesn't parse. ``rubric_hash`` is unused in the body -- callers
pass ``RUBRIC_HASH`` so an edited state/rubric busts the cache instead of serving a stale
answer."""
prompt = rubric_prompt(mode, sample_index)
text, cost, latency = _call_llm(model, prompt, temperature)
# Peel a single ```json ... ``` fence (claude-haiku-4-5 adds one despite "ONLY a JSON object").
stripped = text.strip()
if stripped.startswith("```"):
stripped = stripped[stripped.find("\n") + 1 :] if "\n" in stripped else ""
if stripped.rstrip().endswith("```"):
stripped = stripped.rstrip()[: -len("```")]
try:
raw = json.loads(stripped)
except (ValueError, json.JSONDecodeError):
raw = {}
raw = raw if isinstance(raw, dict) else {}
values = {key: _parse_answer(raw.get(key), mode) for key in QUESTIONS}
return values, cost, latency
The factual checks hold steady across most conditions. The judgment-heavy ones are where
the LLM rows move: 
A review band absorbs fluctuation around