AI expert Yan discusses context engineering as top priority for AI agent builders, featuring insights from Martin in an edito

Editorial illustration for Yan calls context engineering the #1 job for AI agent builders, per Martin

Yan calls context engineering the #1 job for AI agent...

Yan calls context engineering the #1 job for AI agent builders, per Martin

By AI Daily Post Edited by Brian Petersen, Editor-in-Chief

June 30, 2026 • 2 min read

The pipeline that now powers most production‑grade Retrieval‑Augmented Generation (RAG) systems is laid out in a series of four “bricks,” each emitting a typed artifact that feeds the next step. First, parsing turns raw text into relational tables; next, a question parser spits out a typed ParsedQuestion. Retrieval then pulls a filtered subset of lines and logs an audit of why those lines were chosen.

Finally, generation creates a Pydantic answer complete with cited evidence. All of that collapses into a single LLM call, using a fixed system prompt while the user content is assembled from the upstream pieces.

Here’s where the terminology shifts. In June 2025, Tobi Lütke tweeted that “prompt engineering” missed the point and coined “context engineering” – the art of feeding the model all the context it needs to solve a task plausibly. Andrej Karpathy echoed the idea a week later, calling it “

Yan's claim that "context engineering is effectively the #1 job of engineers building AI agents" is the line Lance Martin later quotes when he introduces the four-strategy taxonomy. The naming tweet: "I really like the term 'context engineering' over prompt engineering. It describes the core skill better: the art of providing all the context for the task to be plausibly solvable by the LLM." - Lance Martin, Context Engineering for Agents, June 23 2025.

Also republished on the LangChain blog under the LangChain Team byline. The endorsement: "+1 for 'context engineering' over 'prompt engineering'. People associate prompts with short task descriptions you'd give an LLM in your day-to-day use.

In every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step." - Drew Breunig, How to Fix Your Context, June 26 2025. A parallel taxonomy: six concrete tactics (RAG, Tool Loadout, Context Quarantine, Context Pruning, Context Summarization, Context Offloading) for keeping the context window healthy.

Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer - Towards Data Science

Why this matters

We see Yan’s push to rename prompt work as “context engineering” gaining traction, especially after Martin’s four‑strategy taxonomy mapped the process onto concrete RAG components. The breakdown—parsing into relational tables, a typed ParsedQuestion, filtered retrieval with an audit trail, and a Pydantic‑styled answer—offers developers a repeatable pipeline rather than a series of ad‑hoc prompts. The notebooks on GitHub give founders a starting point for building agents that rely on a single LLM call, which could simplify scaling concerns.

Yet, it’s unclear whether the community will adopt this as the dominant discipline or if other engineering challenges will eclipse it. Researchers gain a clearer target for measuring the impact of upstream steps on downstream generation quality, but the claim that context engineering is the “#1 job” remains a hypothesis, not a proven hierarchy. For now, the material provides a useful framework; we remain cautiously optimistic while watching how practitioners translate these typed inputs into production‑ready systems.

Yan calls context engineering the #1 job for AI agent...

Further Reading

Latest News