Skip to content
Go back

Context Engineering

DRAFT
Published: Mar 7, 2026
Vancouver, Canada

What is context engineering and why should you care?

My inspiration for this post came after coming across

Lance shared five context engineering techniques:

  1. Offload

Move information out of the model’s prompt into external storage such as files, databases, or memory systems. The agent retrieves it when needed instead of keeping everything in the context window.

  1. Reduce

Compress or remove unnecessary context to keep prompts small and relevant. Common methods include summarization, pruning old messages, and condensing tool outputs.

  1. Retrieve

Fetch only the relevant information from external sources at runtime (often via RAG). Instead of sending all knowledge to the model, the system selects the most relevant pieces.

  1. Isolate

Separate tasks or reasoning into different contexts, often using multiple agents or modules. Each component works with a smaller, focused context to reduce interference and overload.

  1. Cache

Store and reuse previously computed context, such as prompts, tool results, or message histories. This reduces cost and latency by avoiding repeated computation.

In short:

  1. Offload → move context out
  2. Reduce → shrink context
  3. Retrieve → pull needed context
  4. Isolate → split context
  5. Cache → reuse context