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
- A roundup of AI agents and MCP resources, including how to evaluate agents — _jaydeepkarale · 2026-07-21
- A full course shows how to build and deploy an AI agent with OpenAI and LangChain — _jaydeepkarale · 2026-07-21
- A beginner guide to AI agents points readers to a Stanford webinar — _jaydeepkarale · 2026-07-21
- A practical guide on how to evaluate AI agents — _jaydeepkarale · 2026-07-21
- MCP is headed toward easier scale, event-driven extensions, and workable file uploads — EricBuess · 2026-07-21
- Developers debate the missing composition model for AI agents — threepointone · 2026-07-21