Skip to content

Arize Phoenix Integration

Observe with Phoenix, detect with Pisama.

Arize Phoenix (9,200+ stars) is the most popular open-source LLM observability platform. It captures traces from every major agent framework. Pisama adds multi-agent failure detection on top of those traces.

Phoenix tells you what happened. Pisama tells you what went wrong and why.

How It Works

Your Agents → Phoenix (tracing) → Export traces → Pisama (failure detection)

Pisama ingests Phoenix trace exports for failure analysis via the built-in PhoenixImporter. (Exporting Pisama results back into Phoenix as spans is on the roadmap, not yet shipped.)

Import Phoenix Traces

Option 1: Export from Phoenix UI

  1. In Phoenix, select the traces you want to analyze
  2. Export as JSON (OTEL format)
  3. Import into Pisama:
# CLI
pisama analyze phoenix_export.json

# Or via API
curl -X POST https://api.pisama.ai/api/v1/traces \
  -H "Authorization: Bearer $PISAMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d @phoenix_export.json

Option 2: Bulk Import

For historical analysis of many traces:

curl -X POST https://api.pisama.ai/api/v1/import-jobs \
  -H "Authorization: Bearer $PISAMA_API_KEY" \
  -F "file=@phoenix_traces.json" \
  -F "format=phoenix"

Monitor import progress:

curl https://api.pisama.ai/api/v1/import-jobs \
  -H "Authorization: Bearer $PISAMA_API_KEY"

Option 3: Python SDK

from pisama import analyze

# Analyze a Phoenix JSON export directly
result = analyze("phoenix_export.json")

for issue in result.issues:
    print(f"[{issue.type}] {issue.summary} (severity: {issue.severity})")
    print(f"  Agent: {issue.agent_id}")
    print(f"  {issue.recommendation}")

Export Results to Phoenix

Roadmap

Exporting Pisama detection results back into Phoenix as OTEL spans is planned but not yet available. For now, review detections in the Pisama dashboard or via the REST API.

Framework Auto-Detection

When importing Phoenix traces, Pisama automatically detects the agent framework from OTEL gen_ai.system and gen_ai.provider.name semantic conventions:

Framework Auto-Detected Additional Detectors
LangGraph Yes 6 LangGraph-specific (recursion, state corruption, etc.)
CrewAI Yes Core 32 detectors
AutoGen Yes Core 32 detectors
OpenAI Agents SDK Yes Core 32 detectors
Claude Agent SDK Yes Core 32 detectors
Amazon Bedrock Yes Core 32 detectors
Google Vertex AI Yes Core 32 detectors

Typical Workflow

  1. Instrument your agents with Phoenix (one-line auto-instrumentation)
  2. Run your agents — Phoenix captures all traces
  3. Export traces from Phoenix (JSON or via API)
  4. Analyze with Pisama — get failure classifications, severity scores, and fix recommendations
  5. Review detection results in the Pisama dashboard or via the REST API

Why Both?

Capability Phoenix Pisama
Trace capture & visualization Yes Via import
LLM call cost tracking Yes Yes
Multi-agent trace graphs Yes Yes
Failure pattern detection (84 detectors) No Yes
Framework-specific detectors (5 platforms) No Yes
Tiered detection ($0 for 90%+) No Yes
Self-healing & fix generation No Yes
F1-calibrated accuracy scores No Yes

Phoenix is the best open-source observability platform. Pisama is the best open-source failure detection platform. Use both.

Supported Formats

The Phoenix importer handles:

  • Phoenix JSON export: Native format from Phoenix UI export
  • OTEL JSON (resourceSpans format): Standard OTEL trace export
  • JSONL: Line-delimited JSON traces

All formats are auto-detected — just pass the file and Pisama figures out the format.