What entails the LLM Completion are you talking sequence of prompts with files / mcp servers. Could you share a bit more, cause I have spent some time with this and have something that might be precisely what you are asking for...
This is awesome. Love seeing more teams investing early in observability and evals instead of treating them as an afterthought.
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.
Fluvio is streaming transport. And we built Stateful DataFlow on top of that for Stream Processing.
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.
We have had folks over the years asking us about the Kafka wire compatibility. We had a project 3 years ago which we archived. I think we have a case for reviving it in the near future.
Agree with you 100%. We are working on more elaborate benchmarking on bare metal instances. This was just an initial run to utilize the benchmarking tool which is usable by all fluvio users.
We will do a full setup and benchmarks comparing Kafka, Pulsar, RedPanda using a real dataset on barmetal servers soon.
Really cool project! Look forward to trying this out. I have been using the copilot extensions with local docs toRAG augmentation. This seems to be a step up.
That's a really good suggestion. I am trying to build some tutorial videos now. I feel the same way about listicles but they get a lot of impressions. People seem to love lists.
LOL. AI generated the image. But as far as I understand AJ wrote the rest. But it's a dry subject. I am curious what makes you say it is an AI generated Ad?
Fluvio is an edge to core cloud native streaming engine built from the ground up in rust. Compiles to a single 37 Meg binary and deploys on ARM64 devices.
We just released the first public beta version of Stateful DataFlow. Stateful DataFlow is a framework for building unbounded distributed stream processing based on wasm that runs on Fluvio streams.
We are going for a Lean alternative to Kafka + Flink with a user experience of Ruby on Rails.
BTW, Stateful DataFlow has integrations with Arrow, Polars, and the ability to use SQL for dataframes, and other wasm compatible programming languages to express business logic. And Fluvio has Rust, Python, and JS clients.
Umm it's more complex than that.
Open standard would still need money to survive.
And Big Tech will flex their philanthropic muscle and influence open standards.
There is a lot of empirical evidence of this. Look at Matter protocol in home automation, GS1 in retail. Starts as a good idea but as soon as there is adoption, there will be several market motions to mess everything up.
The only way for an open standard to grow is a large extremely committed community that is largely made of people who don't have to worry about survival.