Arize AI
Official@arize-ai
Unified AI engineering and evaluation platform to accelerate development and improvement of AI apps and agents
Agent Skills by Arize AI
Showing 50 vetted skills indexed across 4 GitHub repositories.
Arize-aijs-docs-sync
Verify and update hand-written docs/ documentation in JS packages against source code.
Arize-aijava-code-reviewer
Reviews Java OpenInference instrumentation packages against project conventions and semantic conventions.
Arize-aipython-canary-fix
Investigate and fix Python canary cron failures in openinference instrumentation packages.
Arize-aigenai-conformance
Runs and iterates the OpenInference GenAI conformance harness against OTel semantic conventions.
Arize-aiphoenix-cli-development
Guides design and implementation of noun-verb commands for the Phoenix CLI.
Arize-aiphoenix-client-development
Guides development of the phoenix-client TypeScript SDK covering experiments, prompts, tracing, and vitest testing.
Arize-aiphoenix-otel-development
Guides OpenTelemetry registration and global tracer provider lifecycle management in TypeScript.
Arize-aiphoenix-server
Guides backend development of Phoenix's FastAPI, Strawberry GraphQL, and SQLAlchemy server codebase.
Arize-aiagent-browser
Automates browser interactions via a CLI using Chrome DevTools Protocol and accessibility-tree snapshots.
Arize-aiphoenix-skills-audit
Audit recent Phoenix client, CLI, and API changes and patch stale agent skill documentation.
Arize-aipxi-eval-dataset
Generate synthetic YAML evaluation datasets for the PXI eval harness.
Arize-aimintlify
Build and maintain Mintlify documentation sites with MDX pages and docs.json configuration.
Arize-aigh-stack
Manages stacked GitHub pull requests and splits multi-part work into reviewable branch layers.
Arize-aiphoenix-sqlean
Maintains the vendored sqlean.py fork by bumping pinned SQLite, sqlean, and xxHash versions.
Arize-aiphoenix-integration-snippets
Generates onboarding code snippets for Phoenix tracing integrations and wires them into the onboarding UI.
Arize-aiphoenix-typescript
Enforces TypeScript naming, typing, and import conventions across the Phoenix monorepo.
Arize-aiphoenix-release-notes
Generate Phoenix release documentation from analyzed commits and GitHub releases.
Arize-aiphoenix-frontend
Enforces React, TypeScript, and Relay conventions for Phoenix frontend development.
Arize-aiphoenix-docs-gap-audit
Audit recent commits against all Phoenix documentation surfaces to produce a grounded gap report.
Arize-aiphoenix-release-please
Force release-please to propose a specific version via a Release-As commit trailer.
Arize-aiphoenix-playwright-tests
Write Playwright end-to-end tests for the Phoenix AI observability platform UI.
Arize-aiphoenix-llms-txt
Maintains and audits the Phoenix llms.txt machine-readable documentation index.
Arize-aiphoenix-evals-new-metric
Create built-in classification evaluators for Phoenix evals from YAML configs.
Arize-aiphoenix-rest-api
Guides development and review of Phoenix REST API endpoints under the v1 router.
Frequently Asked Questions About Arize AI
FAQPage SchemaWhat specific tasks are enabled by these observability capabilities?▼
These capabilities enable granular inspection of distributed system traces, evaluation of prompt performance, and systematic debugging of production sessions. Users can capture spans, manage experimental datasets, and refine prompt logic based on empirical performance signals derived from live production traffic.
Which personas benefit most from these technical capabilities?▼
Machine learning engineers, reliability engineers, and system architects benefit most from these capabilities. These personas utilize the platform to maintain system transparency, ensure model accuracy, and optimize performance metrics within complex, multi-component production environments.
What are the prerequisites for implementing these tracing standards?▼
Implementation requires an existing environment utilizing OpenTelemetry standards for data collection. Users must integrate the relevant instrumentation packages into their application codebase to enable trace capture, span inspection, and data export to the evaluation platform.