Skip to content

api-evangelist/context-engineering

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 

Repository files navigation

Context Engineering

Context engineering is the practice of curating the information that large language models receive at inference time so that the model can perform a task reliably and cost-effectively. It treats the context window as a finite attention budget and looks for the smallest set of high-signal tokens that maximize the likelihood of the desired outcome. Context engineering subsumes and extends prompt engineering, system prompts, tool design, retrieval, agent loops, structured note taking, compaction, and multi-agent decomposition.

URL: Visit APIs.json URL

Tags

  • Agents, AI, Anthropic, Compaction, Context Window, LLM, Memory, Prompt Engineering, RAG, Tools

Timestamps

  • Created: 2025-01-01
  • Modified: 2026-04-28

APIs

Effective Context Engineering for AI Agents

Anthropic's engineering guide framing context as a finite attention budget and walking through system prompts, tool design, just-in-time retrieval, compaction, structured notes, and multi-agent architectures.

Human URL: Anthropic engineering blog

Retrieval-Augmented Generation (RAG)

Pattern that augments LLM prompts with passages retrieved at inference time from a vector store, search index, or knowledge base.

Human URL: Original RAG paper

Prompt Engineering

The discipline of crafting model instructions and examples to guide model behavior, including chain-of-thought, few-shot, and structured output formats.

Human URL: https://www.promptingguide.ai/

Agentic Loops and Tool Use

Iterative reasoning patterns where an LLM plans, calls tools, observes results, and refines its plan.

Human URL: Tool use overview

Long-Horizon Context Strategies

Compaction, structured note taking, and multi-agent decomposition for tasks that exceed the context window.

Human URL: Contextual retrieval

Common Properties

Maintainers

FN: Kin Lane

Email: kin@apievangelist.com

About

Context engineering research and resources

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors