idea0rbit

I’m building TraceDB[1] because I think observability needs an overhaul. We pay a premium to index millions of near-identical spans, sample away the rare ones that might explain an outage, and still have to piece together what failed, where it started, and how it spread. All the data is largely there, but no one can make sense of it! Observability was hallucinating before AI made it fashionable.

I’m seeing near-100% root-cause accuracy on synthetic test data and am looking to validate that on real production workloads using OpenTelemetry tracing. If you’re open to chatting or experimenting, drop me a line! I’d also love to hear ideas or how we can improve observability.

[1] https://tracedb.ai

I’m building an observability system that tries to surface answers instead of making people dig through huge amounts of raw telemetry.

The basic idea is that when one failure fans out across 20 services, you often end up with 20 alerts and 20 separate investigations, even though there is really just one root cause. I’m using distributed tracing to build a live model of how errors propagate through the system, and then exposing that context directly at each affected service.

Longer term, I want this to become a very high-precision RCA engine. Right now I’m looking to try it with a few early design partners that already have a lot of tracing data, especially OpenTelemetry or Datadog APM users. I'll love to chat with some folks who would be willing to try it out!

You are absolutely right. What could an alternate design and business model look like?

both. In general I think most observability systems are broken. This article captures the sentiment pretty well

https://www.linkedin.com/pulse/observability-broken-its-time...

After a decade building large-scale systems at Google, Datadog, and Meta, I’ve noticed the same pattern repeat: observability keeps getting louder, costlier, and less useful.

We’re drowning in telemetry but starving for insight. The industry incentives are misaligned: they reward ingestion and storage, not intelligence.

I recently started an open, collective movement called omji.ai to explore a fundamental shift: measuring insight per dollar of telemetry stored. We need to push vendors and internal teams toward intelligence, not ingestion.

I’m curious to hear from folks facing the pain - how do we fix this? We need practical, non-obvious ideas.

1. What technical or economic levers would actually shift the industry's focus from volume to intelligence?

2. Has anyone in a large organization tried benchmarking observability systems based on insight (e.g., MTTR impact) vs. telemetry cost?

3. How could open collaboration (tools, standards, benchmarks) make this practical for every engineering team?

Full background post: https://www.linkedin.com/pulse/observability-broken-lets-cha...