From RAG to Agentic Search
mdancho84 · x · 2026-07-19
This post asks: Is context engineering just a new name for RAG? The author answers, "Not exactly, but they are both solving the same problem: how to build the right context for an LLM."
The accompanying image breaks down the evolution into three layers:
- Traditional RAG: A fixed retrieval pipeline that searches documents first and then stuffs the results into the context window.
- Agentic RAG: The LLM is no longer a passive receiver of retrieval results; it uses tool calls to decide when and what to retrieve.
- Agentic search in context engineering: Context sources expand further to include local files, skill files, databases, the Web, long-term memory, and Shell tools. The context window contains not just system/user prompts, but also skills YAML, tool lists, history, and tool call results.
The core takeaway: RAG is a sub-module, whereas context engineering focuses on the entire context construction and orchestration system.
Related event: Context Engineering Overtakes RAG in AI Development(2 posts)→
More from coding & agent
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Treating agents like 50 First Dates: a 3-layer context system so every conversation doesn't start from zero — evielync · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- ARRM targets silent economic regressions in AI agents that functional tests miss — Beautiful_Belt_601 · 2026-09-11
- Dev builds browser 3D pizza delivery game with Claude: physics, GPS pathfinding, traffic AI — vinishkapoor · 2026-09-11
- Build X Carousel Posts from One Wide Image: A Splitter Tool Plus YouMind Skill Workflow — sujingshen · 2026-09-11