01.22.2026 CLI Prompt Commands: Pipe Prompts to AI Assistants

# List all prompts
px prompts

# View a specific prompt
px prompt my-evaluator

# Get prompt text for piping
px prompt my-evaluator --format text --no-progress

# Get optimization suggestions
px prompt my-evaluator --format text --no-progress | claude -p "Review this prompt and suggest improvements"

# Analyze for edge cases
px prompt my-assistant --format text --no-progress | claude -p "What edge cases might this prompt fail to handle?"

# Generate test inputs
px prompt my-classifier --format text --no-progress | claude -p "Generate 5 diverse test inputs for this prompt"

<system>You are an expert evaluator...

<rubric>
A correct answer:
- Matches the reference exactly
- Contains no hallucinations
</rubric></system>
<user>Evaluate this response: {{output}}</user>

# Get the production-tagged version
px prompt my-assistant --tag production

# Get a specific version by ID
px prompt my-assistant --version UHJvbXB0VmVyc2lvbjox

# Full JSON with model settings and tools
px prompt my-evaluator --format json

# List all prompts as JSON
px prompts --format raw --no-progress | jq '.[].name'

Fetch my "correctness-evaluator" prompt from Phoenix and help me make the rubric more specific for code review tasks

npm install -g @arizeai/phoenix-cli

npm update -g @arizeai/phoenix-cli