Why Did My RAG Agent Get Worse? A Live Autopsy
Qdrant & Future AGI are coming together for a live technical session on what happens when a RAG agent that once worked well starts getting worse.
Overview
RAG agents in 2026 are rarely static. The knowledge base keeps growing, documents are repeatedly updated, embedding models change, and retrieval pipelines accumulate duplicate and fragmented context. The agent may still run, but its answers gradually become less reliable.
Session Description
As collections grow, documents change, chunks get duplicated, and retrieval pipelines evolve, agent quality can decline without an obvious breaking point. Dylan from Qdrant and Rishav from Future AGI will build, debug and fix one RAG agent through a single end-to-end workflow.
Qdrant powers the retrieval layer, while Future AGI will trace and evaluate the agent throughout the same workflow.
This is one continuous technical walkthrough. What we’ll cover:
Build a RAG agent and observe where the agent is losing quality
Migrate to a new embedding model with zero downtime
Remove duplicate and fragmented chunks from the collection
Add late interaction reranking
Compare evaluation scores before and after each change to verify what actually worked
Who should join
For AI engineers, ML engineers, and product teams running RAG agents in production or dealing with retrieval quality that has become harder to explain as the system has grown.
You’ll leave with a practical workflow for finding why a RAG agent degraded, fixing the right layer, and verifying that the change improved the agent - not just an isolated retrieval metric.
About Future AGI
Future AGI is an open-source AI engineering and optimization platform for shipping self-improving AI Agents. Teams use it to simulate agents before they ship, score them against real failure modes, and keep watching them in production so quality doesn't quietly degrade over time. It's self-hostable and OpenTelemetry-native, with tracing that plugs into 45+ frameworks.