Modern Kubernetes platforms generate massive volumes of logs, yet most teams still rely on keyword searches and dashboards to debug production issues. This slows down incident response and hides valuable operational knowledge inside unstructured data.

In this talk, we’ll demonstrate how to build an AI-assisted observability pipeline using Fluent Bit, OpenSearch, and Retrieval-Augmented Generation (RAG) to transform raw logs into queryable, contextual insights. We’ll walk through a cloud-native architecture that streams logs from Kubernetes workloads, enriches and indexes them in OpenSearch, and uses RAG to answer operational questions in real time.

Attendees will see how this approach helps SREs and platform teams reduce MTTR, improve root-cause analysis, and move from reactive troubleshooting to proactive observability—using open-source, CNCF-aligned tooling.

Key Takeaways

How to design a cloud-native log pipeline with Fluent Bit and OpenSearch

How RAG augments observability by adding context to unstructured logs

Practical patterns to reduce MTTR and improve incident response in Kubernetes environments

Target Audience

SREs, Platform Engineers, and DevOps practitioners

Kubernetes users dealing with large-scale logging and observability challenges

Engineers exploring AI + Cloud-Native integrations using open source

Technical Level

Intermediate

Why this works better for KCD

Strong Kubernetes + CNCF alignment

Clear problem → solution → outcome

No vendor pitch, fully open-source focused

Concrete benefits (MTTR, RCA, real-time ops)