Joined 6 years ago
Your setup (LLM-assessed complexity, semantic success metrics, tool-level telemetry) hits what a lot of orgs miss, tying evaluation and observability together. Most teams stop at traces and latency, but without semantic evals, you can’t really explain or improve behavior.
We’ve seen the same pattern across production agent systems: once you layer in LLM-as-judge evals, distributed tracing, and data quality signals, debugging turns from “black box” to “explainable system.” That’s when scaling becomes viable.
Would love to hear how you’re handling drift or regression detection across those metrics. With CoAgent, we’ve been exploring automated L2–L4 eval loops (semantic, behavioral, business-value levels) and it’s been eye-opening.
Arroyo is SQL first stream processing. Fluvio is streaming transport which can send data to Arroyo and there is an integration.
Stateful DataFlow and Arroyo are similar in the stream processing pattern and the use of Apache Arrow.
The interfaces are different. Fluvio and Stateful DataFlow support for SQL is the same dialect as columnar SQL supported by Polars. The Fluvio and Stateful DataFlow paradigm is more intricate more expressive and the platform is broader and deeper.
What if we wrote it in Rust. And leveraged and WASM.
We have been at it for the past 6 years. https://github.com/infinyon/fluvio
For the past 2 years we have also been building Flink using Rust and WASM. https://github.com/infinyon/stateful-dataflow-examples/
We will do a full setup and benchmarks comparing Kafka, Pulsar, RedPanda using a real dataset on barmetal servers soon.
