Evaluation suite

ingest /events  ──▶  AgentEye  ──── POST /evaluate ────▶  Evaluator service
   (agent_end)        server   ◀──── done | pending ────
                          │
                          │     GET /evaluate/{job_id} ─────▶
                          │     ◀──── done ──────────────
                          ▼
                     evaluations  (terminal results)

{
  "schema_version": "1",
  "session_id":     "session-abc123",
  "agent_id":       "planner",
  "environment":    "production",
  "started_at":     "2026-05-10T12:00:00Z",
  "ended_at":       "2026-05-10T12:05:00Z",
  "events": [
    { "id": 1234, "ts": "...", "event_type": "agent_start", "payload": { ... } },
    ...
  ]
}

{
  "status": "done",
  "scores": { "helpfulness": 0.85, "tool_efficiency": 0.6 },
  "reasoning": {
    "helpfulness": "answered the question directly with citations",
    "tool_efficiency": "called list_files three times when one would have done"
  },
  "summary": "strong answer quality, weak tool selection"
}

{ "status": "pending", "job_id": "abc-123", "next_poll_secs": 30 }

{ "status": "error", "error": "model service unavailable" }

pip install agenteye-evaluator

import os
from agenteye_evaluator import Evaluator, EvalRequest, EvalResponse

app = Evaluator(token=os.environ["EVALUATOR_TOKEN"])

@app.evaluator
def run(req: EvalRequest) -> EvalResponse:
    # Inspect req.events (the full session transcript) and return scores.
    tool_calls = sum(1 for e in req.events if e.event_type == "tool_use")
    return EvalResponse(
        scores={"tool_calls": float(tool_calls)},
        reasoning={"tool_calls": f"{tool_calls} tool invocations in the transcript"},
        summary="tight tool loop" if tool_calls < 5 else "agent looped on tools",
    )

FROM python:3.12-slim
WORKDIR /app
RUN pip install --no-cache-dir agenteye-evaluator uvicorn
COPY my_evaluator.py .
RUN useradd --uid 10001 --create-home --shell /usr/sbin/nologin evaluator \
    && chown -R evaluator:evaluator /app
USER evaluator
EXPOSE 9000
CMD ["uvicorn", "my_evaluator:app", "--host", "0.0.0.0", "--port", "9000"]

kubectl -n agenteye create secret generic evaluator-token \
  --from-literal=token="$(openssl rand -hex 32)"

# Edit deploy/examples/evaluator/deployment.yaml first to point
# `image:` at your registry, then:
kubectl apply -k deploy/examples/evaluator/

EVALUATOR_ENDPOINT=http://evaluator:9000
EVALUATOR_TOKEN=<the value generated above>

kubectl -n agenteye port-forward svc/evaluator 9000:9000
curl -s http://localhost:9000/health   # → {"status":"ok"}

# helpfulness in [0.5, 0.8]
GET /evaluations?score_filters=helpfulness:0.5..0.8

# tool_efficiency at most 0.3 (no lower bound)
GET /evaluations?score_filters=tool_efficiency:..0.3

# helpfulness >= 0.5 AND factuality >= 0.9
GET /evaluations?score_filters=helpfulness:0.5..,factuality:0.9..