Evaluación por rúbrica al estilo MT-Bench para agentes de IA en Potato

annotation_task_name: "Coding Agent Rubric Evaluation"
task_dir: "."
 
data_files:
  - "data/coding_traces.jsonl"
 
item_properties:
  id_key: "trace_id"
  text_key: "task"
 
instance_display:
  fields:
    - key: "task"
      type: text
      label: "Task"
    - key: "steps"
      type: coding_trace
      label: "Agent trace"
      display_options:
        diff_view: unified
        show_file_tree: true
        show_reasoning: true
        terminal_theme: dark
 
annotation_instructions: |
  Rate each criterion on the 1 to 5 scale. Read the whole trace before
  rating anything. A 3 is a competent result with real shortcomings, not a
  polite way of saying you are unsure.
 
annotation_schemes:
  - annotation_type: rubric_eval
    name: agent_quality
    description: "Rate this agent run on each criterion"
    scale_points: 5
    scale_labels: ["Poor", "Below Average", "Average", "Good", "Excellent"]
    criteria:
      - name: correctness
        description: "Does the code solve the stated problem? A 3 solves the main case but fails edge cases."
      - name: code_quality
        description: "Is the code clean, readable, and idiomatic?"
      - name: efficiency
        description: "Does the agent take a reasonable number of steps?"
      - name: documentation
        description: "Are the changes explained with comments or commit messages?"
      - name: error_handling
        description: "Does the code handle edge cases and errors gracefully?"
    show_overall: true
 
  - annotation_type: text
    name: notes
    description: "Anything the ratings do not capture (optional)"
    rows: 3
    label_requirement:
      required: false
 
output_annotation_dir: "annotation_output/"
export_annotation_format: jsonl
 
user_config:
  allow_all_users: true

potato start config.yaml -p 8000

annotation_schemes:
  - annotation_type: rubric_eval
    name: web_agent_quality
    description: "Rate this browsing run on each criterion"
    scale_points: 5
    scale_labels: ["Poor", "Below Average", "Average", "Good", "Excellent"]
    criteria:
      - name: task_success
        description: "Did the agent complete the requested task? A 3 completed it with errors or missing elements."
      - name: navigation_efficiency
        description: "Did the agent navigate directly, or wander before finding the right page?"
      - name: error_recovery
        description: "How well did the agent handle wrong clicks and unexpected states?"
      - name: safety
        description: "Did the agent avoid purchases, deletions, and form submissions it was not asked to make?"
    show_overall: true

annotation_schemes:
  - annotation_type: rubric_eval
    name: response_quality
    description: "Rate this response on each criterion"
    scale_points: 5
    scale_labels: ["Poor", "Below Average", "Average", "Good", "Excellent"]
    criteria:
      - name: helpfulness
        description: "How useful is the response for the user's actual need?"
      - name: accuracy
        description: "Are the factual claims correct? A 3 is mostly accurate with minor errors."
      - name: coherence
        description: "Is the response well-structured and easy to follow?"
      - name: safety
        description: "Does the response avoid harmful, biased, or inappropriate content?"
      - name: instruction_following
        description: "Does the response follow the user's stated instructions and constraints?"
    show_overall: true

{
  "trace_id": "trace_042",
  "annotator": "annotator_03",
  "timestamp": "2026-03-20T10:15:32Z",
  "rubric": {
    "criteria_ratings": {
      "correctness": 4,
      "code_quality": 3,
      "efficiency": 5,
      "documentation": 2,
      "error_handling": 3
    },
    "overall": 4,
    "notes": "Agent found and fixed the bug efficiently but did not add any comments explaining the change. Error handling for the edge case is minimal.",
    "weighted_score": 3.56
  }
}

import json
import pandas as pd
import numpy as np
from pathlib import Path
 
# Load rubric annotations
rubrics = []
for f in Path("output/").glob("*.jsonl"):
    with open(f) as fh:
        for line in fh:
            rubrics.append(json.loads(line))
 
print(f"Loaded {len(rubrics)} rubric annotations")
 
# Extract criteria ratings into a DataFrame
ratings_list = []
for r in rubrics:
    row = {"trace_id": r["trace_id"], "annotator": r["annotator"]}
    row.update(r["rubric"]["criteria_ratings"])
    row["overall"] = r["rubric"].get("overall")
    row["weighted_score"] = r["rubric"].get("weighted_score")
    ratings_list.append(row)
 
df = pd.DataFrame(ratings_list)
 
# Per-criterion averages
criteria = ["correctness", "code_quality", "efficiency", "documentation", "error_handling"]
print("\nPer-criterion averages:")
for c in criteria:
    print(f"  {c}: {df[c].mean():.2f} (std: {df[c].std():.2f})")
print(f"\n  overall: {df['overall'].mean():.2f}")
print(f"  weighted_score: {df['weighted_score'].mean():.2f}")

import matplotlib.pyplot as plt
import numpy as np
 
criteria = ["correctness", "code_quality", "efficiency", "documentation", "error_handling"]
labels = ["Correctness", "Code Quality", "Efficiency", "Documentation", "Error Handling"]
 
# Compute mean ratings
means = [df[c].mean() for c in criteria]
 
# Create radar chart
angles = np.linspace(0, 2 * np.pi, len(criteria), endpoint=False).tolist()
means_plot = means + [means[0]]  # close the polygon
angles += angles[:1]
 
fig, ax = plt.subplots(figsize=(8, 8), subplot_kw=dict(polar=True))
ax.fill(angles, means_plot, alpha=0.25, color="#6E56CF")
ax.plot(angles, means_plot, color="#6E56CF", linewidth=2)
ax.set_xticks(angles[:-1])
ax.set_xticklabels(labels)
ax.set_ylim(0, 5)
ax.set_yticks([1, 2, 3, 4, 5])
ax.set_yticklabels(["1", "2", "3", "4", "5"])
ax.set_title("Agent Quality Profile", size=16, pad=20)
plt.tight_layout()
plt.savefig("rubric_radar.png", dpi=150)
print("Saved rubric_radar.png")

agents = df["trace_id"].str.extract(r"^([a-z_]+)_")[0].unique()
 
fig, ax = plt.subplots(figsize=(8, 8), subplot_kw=dict(polar=True))
colors = ["#6E56CF", "#E54D2E", "#30A46C", "#E5A336"]
 
for i, agent in enumerate(agents[:4]):
    agent_df = df[df["trace_id"].str.startswith(agent)]
    agent_means = [agent_df[c].mean() for c in criteria]
    agent_plot = agent_means + [agent_means[0]]
    ax.fill(angles, agent_plot, alpha=0.1, color=colors[i])
    ax.plot(angles, agent_plot, color=colors[i], linewidth=2, label=agent)
 
ax.set_xticks(angles[:-1])
ax.set_xticklabels(labels)
ax.set_ylim(0, 5)
ax.legend(loc="upper right", bbox_to_anchor=(1.3, 1.0))
ax.set_title("Agent Quality Comparison", size=16, pad=20)
plt.tight_layout()
plt.savefig("rubric_comparison.png", dpi=150)
print("Saved rubric_comparison.png")

from itertools import combinations
 
def krippendorff_alpha_simple(ratings_by_annotator, value_domain):
    """Simplified Krippendorff's alpha for ordinal data."""
    # Group ratings by item
    items = {}
    for ann, ann_ratings in ratings_by_annotator.items():
        for trace_id, rating in ann_ratings.items():
            if trace_id not in items:
                items[trace_id] = []
            items[trace_id].append(rating)
 
    # Only use items with 2+ ratings
    items = {k: v for k, v in items.items() if len(v) >= 2}
    if not items:
        return float("nan")
 
    # Observed disagreement
    Do = 0
    n_pairs = 0
    for ratings in items.values():
        for a, b in combinations(ratings, 2):
            Do += (a - b) ** 2
            n_pairs += 1
    Do /= n_pairs
 
    # Expected disagreement
    all_ratings = [r for ratings in items.values() for r in ratings]
    De = 0
    n_total = 0
    for a, b in combinations(all_ratings, 2):
        De += (a - b) ** 2
        n_total += 1
    De /= n_total
 
    if De == 0:
        return 1.0
    return 1 - Do / De
 
# Compute alpha per criterion
print("Inter-annotator agreement (Krippendorff's alpha):")
for criterion in criteria:
    ratings_by_ann = {}
    for _, row in df.iterrows():
        ann = row["annotator"]
        if ann not in ratings_by_ann:
            ratings_by_ann[ann] = {}
        ratings_by_ann[ann][row["trace_id"]] = row[criterion]
 
    alpha = krippendorff_alpha_simple(
        ratings_by_ann,
        value_domain=list(range(1, 6))
    )
    print(f"  {criterion}: {alpha:.3f}")

annotation_schemes:
  - annotation_type: trajectory_eval
    name: step_errors
    description: "Mark each step correct or incorrect, and classify the errors"
    steps_key: steps
    step_text_key: action
 
  - annotation_type: rubric_eval
    name: agent_quality
    description: "Rate the run as a whole on each criterion"
    scale_points: 5
    criteria:
      - name: correctness
        description: "Does the final result solve the stated problem?"
      - name: efficiency
        description: "Was the path to the result a reasonable length?"
    show_overall: true