Model-neutral context engineering
Choose what the model gets to see.
Context engineering is the craft of building the information environment around an LLM: goals, instructions, retrieved evidence, memory, examples, constraints, and output contracts. The hard part is not filling the window. The hard part is curating it.
The user task, success criteria, and decision boundary.
Sources ranked by relevance, authority, freshness, and conflict.
System constraints, policies, formatting contracts, and tool limits.
Stable preferences and prior decisions, not every historical token.
The shape the answer must take so it can be judged and reused.
Key facts
Context Engineering Guide
- Context engineering is the design of the full inference payload: task, instructions, evidence, memory, tools, examples, constraints, and output contract.
- The central rule is curation over dumping: put answer-critical material in the prompt, citations in the audit trail, and everything else behind retrieval.
- The site is model-neutral and independent, with sourced guidance for RAG, long context, compression, structure, and evaluation.
- Free browser-only tools on this site estimate token counts and visualize context-window budgets without sending text anywhere.
Why this exists
Curation beats dumping because attention is not uniform.
Long context windows changed what is possible, but they did not remove the need for selection. Research on long-context use repeatedly shows that placement, length, and task complexity change how well models use evidence.
"performance is often highest when relevant information occurs at the beginning or end"
Guide map
The context pipeline, page by page.
Each page answers one operational question. Read them in order when designing a new system, or jump to the failure mode you are debugging.
What Belongs in the Context Window
A practical rubric for deciding which goals, instructions, evidence, examples, metadata, and constraints belong in an LLM context window.
02RAG vs Long Context
An evidence-backed comparison of retrieval augmented generation, long context prompting, context rot, and hybrid context pipelines.
03Context Compression
How summarization, chunking, prompt compression, and hierarchical memory reduce tokens without throwing away the facts that matter.
04Structuring Context
Ordering, delimiters, source cards, priority rules, and output contracts that make curated context easier for LLMs to use.
05Evaluating Context Quality
How to measure whether curated context improves retrieval, faithfulness, answer relevance, latency, and downstream task success.
06Context Window Management
A practical workflow for managing context-window budgets, drift, overflow, and refresh decisions in LLM systems.
07Context Engineering Glossary
Plain-language definitions for context engineering, context curation, RAG, context rot, prompt compression, memory, and related terms.
08Sources and Machine-Readable Files
Research sources, primary papers, and the llms.txt files behind Curated Context.
09Context Engineering FAQ
Answers to common questions about context engineering, RAG, long context, compression, context rot, and evaluation.
Free tools
Estimate the window before you fill it.
The tools run entirely in the browser. Use them to size a prompt, reserve output room, and see where context budget is going before a system starts ignoring the wrong thing.
Model-neutral, source-backed
This is about context, not one vendor's prompt style.
Curated Context complements claudecontext.com by staying model-agnostic. The pages cite research on RAG, long-context behavior, prompt compression, memory systems, and evaluation so the guidance can travel across model families and tooling stacks.
Cite This Page
Curated Context. "Context Engineering Guide." Accessed July 6, 2026. https://curatedcontext.com/
https://curatedcontext.com/