Quick start

pip install aevyra-origin

export ANTHROPIC_API_KEY=sk-ant-...

from aevyra_witness.runtime import span

@span("classify")
def classify(question: str) -> str:
    # Route the question to a topic
    ...

@span("retrieve")
def retrieve(topic: str) -> list[str]:
    # Fetch relevant documents
    ...

@span("answer", optimize=True, prompt_id="answer_v1")
def answer(question: str, docs: list[str]) -> str:
    # Generate the final response
    ...

def my_agent(question: str) -> str:
    topic = classify(question)
    docs = retrieve(topic)
    return answer(question, docs)

from aevyra_origin import diagnose_pipeline
from aevyra_origin.llm import anthropic_llm
from aevyra_origin.judges import judge_from_verdict
from aevyra_verdict import LLMJudge
from aevyra_verdict.providers import get_provider

judge = judge_from_verdict(LLMJudge(judge_provider=get_provider("anthropic")))

result = diagnose_pipeline(
    my_agent,
    "I was charged twice — how do I get a refund?",
    judge=judge,
    rubric="Accurate, grounded in the policy docs, and addresses the user's concern.",
    llm=anthropic_llm(),
)

print(result.render())

Origin attribution  (method=all, score=0.31)
  Summary: The retrieve span failed to surface the refund policy document,
  leaving the answer span without the grounding it needed.

  1. retrieve (id=n2)  [primary, confidence=0.89, fix=retrieval]
     Returned generic FAQ results; the refund policy doc was not in the
     retrieved set despite being present in the index.

  2. classify (id=n1)  [contributing, confidence=0.44, fix=routing]
     Classified as "billing/general" rather than "billing/refund",
     causing the retriever to miss the policy-specific corpus.

  3. answer (id=n3)  [minor, confidence=0.18, fix=prompt]
     Given the missing context, the answer defaulted to a generic apology
     rather than citing the 30-day refund window.

  --- Prompt-level rollup (for Reflex) ---
  prompt=answer_v1  [minor, confidence=0.18, spans=1]

def my_judge(trace) -> float:
    output = trace.nodes[-1].output
    return 1.0 if "refund" in str(output).lower() else 0.0

result = diagnose_pipeline(my_agent, question, judge=my_judge, rubric=rubric, llm=llm)

from aevyra_origin import Origin
from aevyra_origin.llm import anthropic_llm

origin = Origin(llm=anthropic_llm())
result = origin.diagnose(trace=my_trace, score=0.31, rubric=rubric)
print(result.render())

aevyra-origin diagnose trace.json \
  --score 0.31 \
  --rubric rubric.txt \
  --model anthropic/claude-sonnet-4-5

for pa in result.by_prompt():
    print(f"{pa.prompt_id}  severity={pa.severity}  confidence={pa.confidence:.2f}")