Hey HN, we're Justin and Cole, the founders of Helicone (https://helicone.ai) or self-deploy with our new fully open-source helm chart (https://helicone.ai/selfhost). Yet even with detailed traces, probabilistic systems are notoriously hard to debug at scale. So, we released evaluators (either via LLM-as-judge or custom Python evaluators leveraging the CodeSandbox SDK - https://codesandbox.io/docs/sdk/sandboxes).... - Source: Hacker News / 8 months ago

In part 3, we implemented comprehensive observability for our restaurant agent using LangFuse. Now we're taking it further by adding automated evaluation that not only measures performance but also sends evaluation scores back to LangFuse for centralized monitoring. - Source: dev.to / about 1 month ago

Selecting the right observability platform is critical for ensuring your AI agents perform reliably, efficiently, and safely in production. The following features are essential for modern AI agent observability platforms, as demonstrated by industry leaders like Maxim AI, Langfuse, Arize AI, and others. - Source: dev.to / 2 months ago

For monitoring, there are separate full-fledged monitoring solutions like Opik, PostHog, Langfuse or OpenLLMetry, maybe will try some next time. - Source: dev.to / 4 months ago

Langfuse has emerged as a favorite in the open-source community, and for good reason. It is incredibly powerful, offering deep, detailed tracing and extensive features for monitoring, debugging, and analytics. It requires a few more environment variables for its public key, secret key, and host, but the setup is still minimal. - Source: dev.to / 4 months ago

And then there’s evaluation and observability—two things you must consider when your AI app is live. You need to know if the model is doing its job, and why it failed when it didn’t. Tools like LangSmith and LangFuse can help with this, but you’ll need to spend time experimenting with what works best for your stack. - Source: dev.to / 4 months ago