arize-prompt-optimization
arize-ai
Better LLM prompts, grounded in real failures.
Prompt engineering
arize-ai
GitHub publisher15 Skills33.4k installs
Organization · Arize AI · www.arize.com · On GitHub since 2020
- 3k
- 2.9k
arize-experiment
arize-ai
Compare your models with Arize experiment results.
Model evaluation
- 2.9k
arize-dataset
arize-ai
Manage Arize datasets for your evaluations.
AI evaluation
- 2.8k
arize-evaluator
arize-ai
Score your app's AI responses with Arize.
AI evaluation
- 2.8k
arize-link
arize-ai
Share direct links to your Arize traces and data.
AI observability
- 2.8k
arize-ai-provider-integration
arize-ai
Manage your LLM provider connections in Arize.
AI platform administration
+5 - 2.7k
arize-annotation
arize-ai
Organize human review and label spans in Arize.
Data annotation
- 2.4k
arize-compliance-audit
arize-ai
Find compliance gaps in your AI app's code.
AI compliance
- 2.1k
arize-admin
arize-ai
Manage your team's access and spaces in Arize.
Access administration
- 2.1k
arize-prompts
arize-ai
Save and version your prompts in Arize Prompt Hub.
Prompt management
- 1.7k
phoenix-cli
arize-ai
Investigate LLM failures with Phoenix traces.
LLM debugging
- 1.7k
phoenix-tracing
arize-ai
Make your LLM app's traces easier to inspect.
AI observability
- 1.6k
phoenix-evals
arize-ai
AI quality checks tested against human labels.
AI evaluation
- 1.1k
arize-span-routing
arize-ai
Keep each tenant's traces in the right Arize space.
Application observability
- 893
arize-instrumentation-health
arize-ai
Find why your Arize traces look empty or flat.
Instrumentation auditing