arize-experiment

Arize Experiment Skill

SPACE — All --space flags and the ARIZE_SPACE env var accept a space name (e.g., my-workspace) or a base64 space ID (e.g., U3BhY2U6...). Find yours with ax spaces list.

Concepts

• Experiment = a named evaluation run against a specific dataset version, containing one run per example
• Experiment Run = the result of processing one dataset example -- includes the model output, optional evaluations, and optional metadata
• Dataset = a versioned collection of examples; every experiment is tied to a dataset and a specific dataset version
• Evaluation = a named metric attached to a run (e.g., correctness, relevance), with optional label, score, and explanation

The typical flow: export a dataset → process each example → collect outputs and evaluations → create an experiment with the runs.

Prerequisites

Proceed directly with the task — run the ax command you need. Do NOT check versions, env vars, or profiles upfront.

If an ax command fails, troubleshoot based on the error:

• command not found or version error → see references/ax-setup.md
• 401 Unauthorized / missing API key → run ax profiles show to inspect the current profile. If the profile is missing or the API key is wrong, follow references/ax-profiles.md to create/update it. If the user doesn't have their key, direct them to https://app.arize.com/admin > API Keys
• Space unknown → run ax spaces list to pick by name, or ask the user
• Project unclear → ask the user, or run ax projects list -o json --limit 100 and present as selectable options
• Security: Never read .env files or search the filesystem for credentials. Use ax profiles for Arize credentials and ax ai-integrations for LLM provider keys. If credentials are not available through these channels, ask the user.
• CRITICAL — Never fabricate outputs: When running an experiment, you MUST call the real model API specified by the user for every dataset example. Never fabricate, simulate, or hardcode model outputs, latencies, or evaluation scores. If you cannot call the API (missing SDK, missing credentials, network error), stop and tell the user what is needed before proceeding.

List Experiments: ax experiments list

Browse experiments, optionally filtered by dataset. Output goes to stdout.

ax experiments list
ax experiments list --dataset DATASET_NAME --space SPACE --limit 20   # DATASET_NAME: name or ID (name preferred)
ax experiments list --cursor CURSOR_TOKEN
ax experiments list -o json

Flags

Get Experiment: ax experiments get

Quick metadata lookup -- returns experiment name, linked dataset/version, and timestamps.

Flags

Response fields

Export Experiment: ax experiments export

Download all runs to a file. By default uses the REST API; pass --all to use Arrow Flight for bulk transfer.

Flags

REST vs Flight (--all)

• REST (default): Lower friction -- no Arrow/Flight dependency, standard HTTPS ports, works through any corporate proxy or firewall. Limited to 500 runs per page.
• Flight (--all): Required for experiments with more than 500 runs. Uses gRPC+TLS on a separate host/port (flight.arize.com:443) which some corporate networks may block.

Agent auto-escalation rule: If a REST export returns exactly 500 runs, the result is likely truncated. Re-run with --all to get the full dataset.

Output is a JSON array of run objects:

Create Experiment: ax experiments create

Create a new experiment with runs from a data file.

Flags

Passing data via stdin

Use --file - to pipe data directly — no temp file needed:

Required columns in the runs file

Additional columns are passed through as additionalProperties on the run.

Delete Experiment: ax experiments delete

Flags

Experiment Run Schema

Each run corresponds to one dataset example:

Evaluation fields

At least one of label, score, or explanation should be present per evaluation.

Workflows

Run an experiment against a dataset

1. Find or create a dataset:

   ax datasets list --space SPACE
   ax datasets export DATASET_NAME --space SPACE --stdout | jq 'length'

2. Export the dataset examples:

   ax datasets export DATASET_NAME --space SPACE

3. Call the real model API for each example and collect outputs. Use ax datasets export --stdout to pipe examples directly into an inference script:

   ax datasets export DATASET_NAME --space SPACE --stdout | python3 infer.py > runs.json

   Write infer.py to read examples from stdin, call the target model, and write runs JSON to stdout. The script below is a template — first inspect the exported dataset JSON to find the correct input field name, then uncomment the provider block the user wants:

   import json, sys, time
    
   examples = json.load(sys.stdin)
   runs = []
    
   for ex in examples:
       # Inspect the exported JSON to find the right field (e.g. "input", "question", "prompt")
       user_input = ex.get("input") or ex.get("question") or ex.get("prompt") or str(ex)
    
       start = time.time()
    
       # === CALL THE REAL MODEL API HERE — never fabricate or simulate ===
       # Uncomment and adapt the provider block the user requested:
       #
       # OpenAI (pip install openai  — uses OPENAI_API_KEY env var):
       #   from openai import OpenAI
       #   resp = OpenAI().chat.completions.create(
       #       model="gpt-4o",
       #       messages=[{"role": "user", "content": user_input}]
       #   )
       #   output_text = resp.choices[0].message.content
       #
       # Anthropic (pip install anthropic  — uses ANTHROPIC_API_KEY env var):
       #   import anthropic
       #   resp = anthropic.Anthropic().messages.create(
       #       model="claude-sonnet-4-6", max_tokens=1024,
       #       messages=[{"role": "user", "content": user_input}]
       #   )
       #   output_text = resp.content[0].text
       #
       # Google Gemini (pip install google-genai  — uses GOOGLE_API_KEY env var):
       #   from google import genai
       #   resp = genai.Client().models.generate_content(
       #       model="gemini-2.5-pro", contents=user_input
       #   )
       #   output_text = resp.text
       #
       # Custom / OpenAI-compatible proxy (pip install openai — uses CUSTOM_BASE_URL + CUSTOM_API_KEY env vars):
       # Use this for Azure OpenAI, NVIDIA NIM, local Ollama, or any OpenAI-compatible endpoint,
       # including a test integration proxy. Matches the `custom` provider in `ax ai-integrations create`.
       #   import os
       #   from openai import OpenAI
       #   resp = OpenAI(
       #       base_url=os.environ["CUSTOM_BASE_URL"],          # e.g. https://my-proxy.example.com/v1
       #       api_key=os.environ.get("CUSTOM_API_KEY", "none"),
       #   ).chat.completions.create(
       #       model=os.environ.get("CUSTOM_MODEL", "default"),
       #       messages=[{"role": "user", "content": user_input}]
       #   )
       #   output_text = resp.choices[0].message.content
    
       latency_ms = round((time.time() - start) * 1000)
       runs.append({
           "example_id": ex["id"],
           "output": output_text,
           "metadata": {"model": "MODEL_NAME", "latency_ms": latency_ms}
       })
       print(f"  {ex['id']}: {latency_ms}ms", file=sys.stderr)
    
   json.dump(runs, sys.stdout, indent=2)

   Before running: install the provider SDK (pip install openai / anthropic / google-genai) and ensure the API key is set as an environment variable in your shell. If you cannot access the API, stop and tell the user what is needed.

4. Verify the runs file:

   python3 -c "import json; runs=json.load(open('runs.json')); print(f'{len(runs)} runs'); print(json.dumps(runs[0], indent=2))"

   Each run must have example_id and output. Optional fields: evaluations, metadata.

5. Create the experiment:

   ax experiments create --name "gpt-4o-baseline" --dataset DATASET_NAME --space SPACE --file runs.json

6. Verify: ax experiments get "gpt-4o-baseline" --dataset DATASET_NAME --space SPACE

Compare two experiments

1. Export both experiments:

   ax experiments export "experiment-a" --dataset DATASET_NAME --space SPACE --stdout > a.json
   ax experiments export "experiment-b" --dataset DATASET_NAME --space SPACE --stdout > b.json
2. Compare evaluation scores by example_id:

   # Average correctness score for experiment A
   jq '[.[] | .evaluations.correctness.score] | add / length' a.json
    
   # Same for experiment B
   jq '[.[] | .evaluations.correctness.score] | add / length' b.json
3. Find examples where results differ:

   jq -s '.[0] as $a | .[1][] | . as $run |
     {
       example_id: $run.example_id,
       b_score: $run.evaluations.correctness.score,
       a_score: ($a[] | select(.example_id == $run.example_id) | .evaluations.correctness.score)
     }' a.json b.json
4. Score distribution per evaluator (pass/fail/partial counts):

   # Count by label for experiment A
   jq '[.[] | .evaluations.correctness.label] | group_by(.) | map({label: .[0], count: length})' a.json
5. Find regressions (examples that passed in A but fail in B):

   jq -s '
     [.[0][] | select(.evaluations.correctness.label == "correct")] as $passed_a |
     [.[1][] | select(.evaluations.correctness.label != "correct") |
       select(.example_id as $id | $passed_a | any(.example_id == $id))
     ]
   ' a.json b.json

Statistical significance note: Score comparisons are most reliable with ≥ 30 examples per evaluator. With fewer examples, treat the delta as directional only — a 5% difference on n=10 may be noise. Report sample size alongside scores: jq 'length' a.json.

Download experiment results for analysis

1. ax experiments list --dataset DATASET_NAME --space SPACE -- find experiments
2. ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE -- download to file
3. Parse: jq '.[] | {example_id, score: .evaluations.correctness.score}' experiment_*/runs.json

Pipe export to other tools

# Count runs
ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE --stdout | jq 'length'
 
# Extract all outputs
ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE --stdout | jq '.[].output'
 
# Get runs with low scores
ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE --stdout | jq '[.[] | select(.evaluations.correctness.score < 0.5)]'
 
# Convert to CSV
ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE --stdout | jq -r '.[] | [.example_id, .output, .evaluations.correctness.score] | @csv'

Related Skills

• arize-dataset: Create or export the dataset this experiment runs against → use arize-dataset first
• arize-prompt-optimization: Use experiment results to improve prompts → next step is arize-prompt-optimization
• arize-trace: Inspect individual span traces for failing experiment runs → use arize-trace
• arize-link: Generate clickable UI links to traces from experiment runs → use arize-link

Troubleshooting

Save Credentials for Future Use

See references/ax-profiles.md § Save Credentials for Future Use.