How does Arize use OpenTelemetry for AI agent observability?
Answered at 3:26 in Ep. #44, Beyond the Model: Observing AI Agents with Mikyo King · Heavybit Podcasts
How does Arize use OpenTelemetry for AI agent observability?
All solutions around agent observability at Arize revolve around open telemetry. OpenTelemetry comes from traditionally the DevOps world, and while it comes with some overhead, it is the most common ground through which agents are able to observe data. Teams are already onboarded to OTEL, making it a huge unlock for agents because there are many unknown unknowns in agents on top of DevOps. OTEL has been a really good medium and the right way of thinking of things as they scale up.
Full answer and detailsRead the whole answer, key facts and every other question from this episode
In short
All solutions around agent observability at Arize revolve around open telemetry.
Mikyo King, Head of Open Source at Arize · Ep. #44, Beyond the Model: Observing AI Agents with Mikyo King · Heavybit Podcasts · answer at 3:26
Key takeaways
- All solutions around agent observability at Arize revolve around open telemetry.
Quote to remember
“It's one thing to capture the information. It's another thing to kind of make that the fossil fuel for improving your system as the next step.”
— Mikyo King
The full answer · about 4 min
All solutions around agent observability at Arize revolve around open telemetry. OpenTelemetry comes from traditionally the DevOps world, and while it comes with some overhead, it is the most common ground through which agents are able to observe data. Teams are already onboarded to OTEL, making it a huge unlock for agents because there are many unknown unknowns in agents on top of DevOps. OTEL has been a really good medium and the right way of thinking of things as they scale up.
Key facts
- Mikyo King has been a software developer for more than 20 years
- Last three years specifically focused on open source at Arize
- Arize started open source initiative around three years ago for observability and evaluation tooling
- Three years ago questions centered on LLM hallucinations, now focus shifted to agents as a service with higher levels of abstraction
People, companies and topics mentioned
More answers from this episode
- 5:27What is the difference between Open Telemetry semantics and OpenInference semantics for AI observability?
- 13:44How should teams approach starting with evaluations for AI agents?
- 16:01Why did Arize choose to open source AI observability tooling instead of building a closed SaaS product?
- 19:05What security challenges does Arize face when open sourcing AI agent observability?
- 23:44How should open source maintainers handle pull requests from AI coding agents?