---

name: arize-prompt-optimization description: Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement. metadata: author: arize version: "1.0" compatibility: Requires the ax CLI and a configured Arize profile.

Arize Prompt Optimization 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

Where Prompts Live in Trace Data

LLM applications emit spans following OpenInference semantic conventions. Prompts are stored in different span attributes depending on the span kind and instrumentation:

| Column | What it contains | When to use | |--------|-----------------|-------------| | attributes.llm.input_messages | Structured chat messages (system, user, assistant, tool) in role-based format | Primary source for chat-based LLM prompts | | attributes.llm.input_messages.roles | Array of roles: system, user, assistant, tool | Extract individual message roles | | attributes.llm.input_messages.contents | Array of message content strings | Extract message text | | attributes.input.value | Serialized prompt or user question (generic, all span kinds) | Fallback when structured messages are not available | | attributes.llm.prompt_template.template | Template with {variable} placeholders (e.g., "Answer {question} using {context}") | When the app uses prompt templates | | attributes.llm.prompt_template.variables | Template variable values (JSON object) | See what values were substituted into the template | | attributes.output.value | Model response text | See what the LLM produced | | attributes.llm.output_messages | Structured model output (including tool calls) | Inspect tool-calling responses |

Finding Prompts by Span Kind

• LLM span (attributes.openinference.span.kind = 'LLM'): Check attributes.llm.input_messages for structured chat messages, OR attributes.input.value for a serialized prompt. Check attributes.llm.prompt_template.template for the template.
• Chain/Agent span: attributes.input.value contains the user's question. The actual LLM prompt lives on child LLM spans -- navigate down the trace tree.
• Tool span: attributes.input.value has tool input, attributes.output.value has tool result. Not typically where prompts live.

Performance Signal Columns

These columns carry the feedback data used for optimization:

| Column pattern | Source | What it tells you | |---------------|--------|-------------------| | annotation.<name>.label | Human reviewers | Categorical grade (e.g., correct, incorrect, partial) | | annotation.<name>.score | Human reviewers | Numeric quality score (e.g., 0.0 - 1.0) | | annotation.<name>.text | Human reviewers | Freeform explanation of the grade | | eval.<name>.label | LLM-as-judge evals | Automated categorical assessment | | eval.<name>.score | LLM-as-judge evals | Automated numeric score | | eval.<name>.explanation | LLM-as-judge evals | Why the eval gave that score -- most valuable for optimization | | attributes.input.value | Trace data | What went into the LLM | | attributes.output.value | Trace data | What the LLM produced | | {experiment_name}.output | Experiment runs | Output from a specific experiment |

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
• LLM provider call fails (missing OPENAI_API_KEY / ANTHROPIC_API_KEY) → run ax ai-integrations list --space SPACE to check for platform-managed credentials. If none exist, ask the user to provide the key or create an integration via the arize-ai-provider-integration skill
• 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.

Phase 1: Extract the Current Prompt

Find LLM spans containing prompts

# Sample LLM spans (where prompts live)
ax spans export PROJECT --filter "attributes.openinference.span.kind = 'LLM'" -l 10 --stdout

# Filter by model
ax spans export PROJECT --filter "attributes.llm.model_name = 'gpt-4o'" -l 10 --stdout

# Filter by span name (e.g., a specific LLM call)
ax spans export PROJECT --filter "name = 'ChatCompletion'" -l 10 --stdout

Export a trace to inspect prompt structure

# Export all spans in a trace
ax spans export PROJECT --trace-id TRACE_ID

# Export a single span
ax spans export PROJECT --span-id SPAN_ID

Extract prompts from exported JSON

# Extract structured chat messages (system + user + assistant)
jq '.[0] | {
  messages: .attributes.llm.input_messages,
  model: .attributes.llm.model_name
}' trace_*/spans.json

# Extract the system prompt specifically
jq '[.[] | select(.attributes.llm.input_messages.roles[]? == "system")] | .[0].attributes.llm.input_messages' trace_*/spans.json

# Extract prompt template and variables
jq '.[0].attributes.llm.prompt_template' trace_*/spans.json

# Extract from input.value (fallback for non-structured prompts)
jq '.[0].attributes.input.value' trace_*/spans.json

Reconstruct the prompt as messages

Once you have the span data, reconstruct the prompt as a messages array:

[
  {"role": "system", "content": "You are a helpful assistant that..."},
  {"role": "user", "content": "Given {input}, answer the question: {question}"}
]

If the span has attributes.llm.prompt_template.template, the prompt uses variables. Preserve these placeholders ({variable} or {{variable}}) -- they are substituted at runtime.

Phase 2: Gather Performance Data

From traces (production feedback)

# Find error spans -- these indicate prompt failures
ax spans export PROJECT \
  --filter "status_code = 'ERROR' AND attributes.openinference.span.kind = 'LLM'" \
  -l 20 --stdout

# Find spans with low eval scores
ax spans export PROJECT \
  --filter "annotation.correctness.label = 'incorrect'" \
  -l 20 --stdout

# Find spans with high latency (may indicate overly complex prompts)
ax spans export PROJECT \
  --filter "attributes.openinference.span.kind = 'LLM' AND latency_ms > 10000" \
  -l 20 --stdout

# Export error traces for detailed inspection
ax spans export PROJECT --trace-id TRACE_ID

From datasets and experiments

# Export a dataset (ground truth examples)
ax datasets export DATASET_NAME --space SPACE
# -> dataset_*/examples.json

# Export experiment results (what the LLM produced)
ax experiments export EXPERIMENT_NAME --dataset DATASET_NAME --space SPACE
# -> experiment_*/runs.json

Merge dataset + experiment for analysis

Join the two files by example_id to see inputs alongside outputs and evaluations:

# Count examples and runs
jq 'length' dataset_*/examples.json
jq 'length' experiment_*/runs.json

# View a single joined record
jq -s '
  .[0] as $dataset |
  .[1][0] as $run |
  ($dataset[] | select(.id == $run.example_id)) as $example |
  {
    input: $example,
    output: $run.output,
    evaluations: $run.evaluations
  }
' dataset_*/examples.json experiment_*/runs.json

# Find failed examples (where eval score < threshold)
jq '[.[] | select(.evaluations.correctness.score < 0.5)]' experiment_*/runs.json

Identify what to optimize

Look for patterns across failures:

1. Compare outputs to ground truth: Where does the LLM output differ from expected?
2. Read eval explanations: eval.*.explanation tells you WHY something failed
3. Check annotation text: Human feedback describes specific issues
4. Look for verbosity mismatches: If outputs are too long/short vs ground truth
5. Check format compliance: Are outputs in the expected format?

Phase 3: Optimize the Prompt

The Optimization Meta-Prompt

Use this template to generate an improved version of the prompt. Fill in the three placeholders and send it to your LLM (GPT-4o, Claude, etc.):

You are an expert in prompt optimization. Given the original baseline prompt
and the associated performance data (inputs, outputs, evaluation labels, and
explanations), generate a revised version that improves results.

ORIGINAL BASELINE PROMPT
========================

{PASTE_ORIGINAL_PROMPT_HERE}

========================

PERFORMANCE DATA
================

The following records show how the current prompt performed. Each record
includes the input, the LLM output, and evaluation feedback:

{PASTE_RECORDS_HERE}

================

HOW TO USE THIS DATA

1. Compare outputs: Look at what the LLM generated vs what was expected
2. Review eval scores: Check which examples scored poorly and why
3. Examine annotations: Human feedback shows what worked and what didn't
4. Identify patterns: Look for common issues across multiple examples
5. Focus on failures: The rows where the output DIFFERS from the expected
   value are the ones that need fixing

ALIGNMENT STRATEGY

- If outputs have extra text or reasoning not present in the ground truth,
  remove instructions that encourage explanation or verbose reasoning
- If outputs are missing information, add instructions to include it
- If outputs are in the wrong format, add explicit format instructions
- Focus on the rows where the output differs from the target -- these are
  the failures to fix

RULES

Maintain Structure:
- Use the same template variables as the current prompt ({var} or {{var}})
- Don't change sections that are already working
- Preserve the exact return format instructions from the original prompt

Avoid Overfitting:
- DO NOT copy examples verbatim into the prompt
- DO NOT quote specific test data outputs exactly
- INSTEAD: Extract the ESSENCE of what makes good vs bad outputs
- INSTEAD: Add general guidelines and principles
- INSTEAD: If adding few-shot examples, create SYNTHETIC examples that
  demonstrate the principle, not real data from above

Goal: Create a prompt that generalizes well to new inputs, not one that
memorizes the test data.

OUTPUT FORMAT

Return the revised prompt as a JSON array of messages:

[
  {"role": "system", "content": "..."},
  {"role": "user", "content": "..."}
]

Also provide a brief reasoning section (bulleted list) explaining:
- What problems you found
- How the revised prompt addresses each one

Preparing the performance data

Format the records as a JSON array before pasting into the template:

# From dataset + experiment: join and select relevant columns
jq -s '
  .[0] as $ds |
  [.[1][] | . as $run |
    ($ds[] | select(.id == $run.example_id)) as $ex |
    {
      input: $ex.input,
      expected: $ex.expected_output,
      actual_output: $run.output,
      eval_score: $run.evaluations.correctness.score,
      eval_label: $run.evaluations.correctness.label,
      eval_explanation: $run.evaluations.correctness.explanation
    }
  ]
' dataset_*/examples.json experiment_*/runs.json

#