arize
You are an expert in Arize and its open-source Phoenix library for AI observability. You help developers monitor LLM applications with tracing, evaluation, embedding analysis, drift detection, and retrieval quality metrics — using Phoenix for local development (open-source, self-hosted) and Arize platform for production monitoring at scale.
What this skill does
# Arize (Phoenix) — AI Observability Platform
You are an expert in Arize and its open-source Phoenix library for AI observability. You help developers monitor LLM applications with tracing, evaluation, embedding analysis, drift detection, and retrieval quality metrics — using Phoenix for local development (open-source, self-hosted) and Arize platform for production monitoring at scale.
## Core Capabilities
### Phoenix Local Setup
```python
import phoenix as px
from phoenix.otel import register
# Launch Phoenix locally (browser UI on localhost:6006)
px.launch_app()
# Register as OpenTelemetry trace provider
tracer_provider = register(project_name="my-llm-app")
# Auto-instrument OpenAI
from openinference.instrumentation.openai import OpenAIInstrumentor
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
# Now all OpenAI calls are traced
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Explain CRDT to a junior dev"}],
)
# Open localhost:6006 — see traces, latency, tokens, cost
```
### RAG Evaluation
```python
from phoenix.evals import (
HallucinationEvaluator,
QAEvaluator,
RelevanceEvaluator,
run_evals,
)
from phoenix.evals.models import OpenAIModel
eval_model = OpenAIModel(model="gpt-4o")
# Evaluate RAG quality on your traces
hallucination_eval = HallucinationEvaluator(eval_model)
qa_eval = QAEvaluator(eval_model)
relevance_eval = RelevanceEvaluator(eval_model)
# Pull traces from Phoenix
traces_df = px.Client().get_spans_dataframe(
filter_condition="span_kind == 'LLM'",
)
# Run evaluations
results = run_evals(
dataframe=traces_df,
evaluators=[hallucination_eval, qa_eval, relevance_eval],
provide_explanation=True,
)
# Results: per-trace hallucination scores, QA accuracy, retrieval relevance
# All visible in Phoenix UI with explanations
```
### Embedding Analysis
```python
import phoenix as px
import pandas as pd
# Analyze embedding drift and clustering
embeddings_df = pd.DataFrame({
"text": documents,
"embedding": embeddings, # numpy arrays
"category": categories,
})
# Launch with embedding visualization
session = px.launch_app(
primary=px.Inferences(embeddings_df, schema=px.Schema(
embedding=px.EmbeddingColumnNames(
vector_column_name="embedding",
raw_data_column_name="text",
),
tag_column_names=["category"],
)),
)
# UMAP visualization in browser — see clusters, outliers, drift
```
### Production Monitoring (Arize Platform)
```python
from arize.pandas.logger import Client
from arize.utils.types import ModelTypes, Environments
arize_client = Client(
space_key=os.environ["ARIZE_SPACE_KEY"],
api_key=os.environ["ARIZE_API_KEY"],
)
# Log predictions for monitoring
arize_client.log(
dataframe=predictions_df,
model_id="support-chatbot-v2",
model_version="2.1.0",
model_type=ModelTypes.GENERATIVE_LLM,
environment=Environments.PRODUCTION,
schema=arize_schema,
)
# Arize platform: drift detection, performance dashboards, alerting
```
## Installation
```bash
pip install arize-phoenix # Open-source local
pip install arize # Arize platform client
pip install openinference-instrumentation-openai # Auto-instrumentation
```
## Best Practices
1. **Phoenix for dev** — Run locally with `px.launch_app()`; free, open-source, no data leaves your machine
2. **Auto-instrumentation** — Use OpenInference instrumentors for OpenAI, LangChain, LlamaIndex; zero code changes
3. **RAG evaluations** — Run hallucination + relevance + QA evals on production traces; catch quality regressions
4. **Embedding viz** — Use UMAP visualization to find clusters, outliers, and distribution drift in your data
5. **OpenTelemetry native** — Phoenix is an OTLP collector; integrates with existing observability stacks
6. **Arize for production** — Scale to millions of traces; automated drift detection and alerting
7. **LLM-as-judge** — Built-in evaluators use GPT-4 to score hallucination, relevance; provide explanations
8. **Trace filtering** — Filter by span kind, model, latency, error; drill into problematic traces
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.