LLM Observability: Tracing, Evaluations, and Real-Time Insights
LLM Observability: Tracing, Evaluations, and Real-Time Insights with John Gilhuly from Arize
Join this fireside chat as we speak with John Gilhuly, Head of Developer Relations at Arize about AI Observability for LLMs. We’ll talk about ways to accelerate your AI development with powerful insights allowing you to evaluate, experiment, and optimize AI applications in real time.
RSVP to attend live, ask questions, connect with the community, and get the recording.
⭐ Check out Phoenix, an open-source solution by Arize that enables LLM AI observability for monitoring in production and evaluating experimentations. github.com/Arize-ai/phoenix
Features include
- LLM Tracing
- Prompt Playground
- Evaluations
- Annotations
- Dataset Clustering & Visualization
- And more
Learn More About the Guest and Arize
- John Gilhuly is Head of Developer Relations at Arize (arize.com).
- LinkedIn: linkedin.com/in/johngilhuly
Connect with Arize
- Arize LinkedIn: linkedin.com/company/arizeai
- Arize X (Twitter): x.com/arizeai
Connect with the host
- Sage Elliott: linkedin.com/in/sageelliott
About Union:
Our AI workflow and inference platform unifies data, models and compute with the workflows of execution on a single pane of glass.
💬 Join our AI and MLOps Slack Community: slack.flyte.org
⭐ Check our open-source github.com/flyteorg/flyte
Check out everything else we’re doing at Union.ai