agentic rag
architecture judged 100% likely a named technique or architecture
See how it has spread across media tiers
Mentions over time
Table view
| Week | Articles | Sources |
|---|---|---|
| 2024-W25 | 1 | 1 |
| 2024-W26 | 1 | 1 |
| 2025-W03 | 1 | 1 |
| 2025-W19 | 1 | 1 |
| 2026-W11 | 2 | 1 |
| 2026-W20 | 1 | 1 |
| 2026-W24 | 1 | 1 |
| 2026-W32 | 1 | 1 |
In their words
Qdrant and Minima Deliver 2.92x More Agentic RAG Tasks per GPU-Hour Qdrant and Minima Engineering · August 13, 2026 On this page: Reducing Retrieval and Calls When a retrieval-augmented generation (RAG) agent runs, it often has to plan a search, check the evidence it gets back, and try again when that evidence falls short.
The Decision Flow# Follow this path: - Frequently changing knowledge + source citations needed → RAG - Frequently changing knowledge + low latency critical → Fine-tuning + RAG (fine-tune for speed, RAG for freshness) - Stable knowledge + consistent style/format → Fine-tuning - Stable knowledge + no style requirements → Prompt engineering (start simple) - Changing knowledge + consistent style + fac
To go deeper: The Weaviate MCP server release notes The weaviate/mcp-server-weaviate GitHub repository The official MCP protocol docs The tokenization post for the per-property tokenization rationale Related blog posts: What is agentic RAG and Hybrid search explained Ready to start building?
Agentic RAG — When AI Agents Drive Retrieval (2026) Standard RAG pipelines follow a fixed sequence: embed the query, retrieve chunks, generate a response.
Self-RAG and Agentic RAG Standard RAG retrieves once per query.
Uber Genie — Agentic RAG for Engineering Support# Uber's internal LLM-powered Slack bot answers engineering questions about security and privacy policy.
How to Build Intelligent Agentic RAG with CrewAI and Qdrant Kacper Łukawski · January 24, 2025 On this page: In a recent live session, we teamed up with CrewAI, a framework for building intelligent, multi-agent applications.
What's Next: Agentic RAG and Multimodal RAG# RAG in 2025–2026 is evolving beyond single-turn retrieve-and-generate into more sophisticated architectures.