// TOPIC

#context-engineering

21 articles

◆◆◆AdvancedAnthropicHugging Face
01

Code Mode: why agents write code instead of calling tools

Why agents that write code against tool APIs beat JSON tool calling: the 150K-to-2K token math, a worked before/after, and when direct calls still win.

#agents#tool-use#mcp
17 min
◆◆IntermediateAnthropicMicrosoft
02

Agent Skills: packaging expertise as files, not code

How Agent Skills use progressive disclosure to load expertise on demand — the SKILL.md format, real token math, and when to pick skills over MCP.

#context-engineering#agents#tool-use
15 min
◆◆IntermediateAnthropicOpenAI
03

How AI coding assistants work

The engineering behind Copilot, Cursor, and Claude Code: repo maps, tree-sitter indexing, edit formats, long-file strategies, and how to evaluate code generation properly.

#agents#tool-use#context-engineering
16 min
◆◆IntermediateAnthropicGoogle
04

Long Context vs RAG: The Million-Token Question

When does stuffing a million tokens beat retrieval? The empirics on lost-in-the-middle accuracy, context-stuffing costs, and when RAG still wins at 1M tokens.

#rag#context-engineering#cost-optimization
14 min
◆◆◆AdvancedAnthropicOpenAI
05

Agent Memory Architectures: Episodic, Semantic, Procedural

How production agents store and recall knowledge across sessions — episodic logs, semantic stores, procedural caches, and sane forgetting policies.

#agents#context-engineering#architecture
17 min
◆◆◆AdvancedAnthropicLangChain
06

Agentic RAG: When Retrieval Becomes a Reasoning Loop

Agentic RAG swaps single-shot retrieval for a decision loop — retrieve, judge, rewrite, repeat. The patterns, failure modes, and when it pays off.

#rag#agents#tool-use
17 min
◆◆Intermediate
07

Prompt Anti-Patterns: The Failure Modes That Ship to Production Silently

Ten documented prompt defects — instruction-stacking, few-shot pollution, persona-stuffing — and why they survive code review and only surface under production load.

#prompting#context-engineering#production
17 min
◆◆IntermediateOpenAIAnthropic
08

Reasoning models plus tools: agentic workflows and function calling

How o3, o4-mini, and Claude extended thinking combine reasoning with tool calls to make harder agent tasks tractable — and the failure modes they introduce.

#reasoning-models#tool-use#agents
16 min
◆◆IntermediateAnthropicOpenAI
09

Context window management for agents: select, compress, isolate

How to keep agents from degrading when the context fills up — retrieval-based selection, compression strategies, multi-agent isolation, and the numbers behind each choice.

#context-engineering#agents#prompting
17 min
◆◆IntermediateOpenAIAnthropic
10

Context Windows, KV Cache, and the Reality Behind 1M Token Claims

What context windows actually cost in GPU memory, why effective recall degrades before the advertised limit, and how to make smart architectural choices about long context.

#llm-internals#inference#context-engineering
18 min
◆◆IntermediateAnthropicOpenAI
11

Prompt Caching: Cutting Costs 50-90% Without Changing Model Behavior

How Anthropic and OpenAI prompt caching works, what breaks the cache, and how to structure prompts to hit 80%+ cache rates in production.

#prompting#context-engineering#cost-optimization
17 min
◆◆IntermediateAnthropicOpenAI
12

Agent Memory: From Context Window to Persistent Knowledge

How agents remember things across tool calls, sessions, and deployments — in-context working memory, episodic stores, semantic vector DBs, and when each breaks.

#agents#context-engineering#rag
17 min
◆◆IntermediateOpenAIAnthropic
13

Few-shot prompting, chain-of-thought, and reasoning models

Master few-shot prompting and chain-of-thought, then learn why both techniques must be rethought entirely for o3, Claude extended thinking, and Gemini 2.x.

#prompting#reasoning-models#context-engineering
19 min
◆◆IntermediateAnthropicOpenAI
14

Prompt caching deep dive: prefix caching, semantic caching, and when each wins

How provider-side prefix caching and application-side semantic caching work, what they cost, where each breaks, and the decision framework for combining them in production.

#cost-optimization#latency#context-engineering
16 min
BeginnerOpenAIAnthropic
15

Prompting reasoning models: what changes and what breaks

The counter-intuitive rules for prompting o3, DeepSeek-R1, and Claude extended thinking — simpler prompts often outperform elaborate ones, and common techniques backfire.

#reasoning-models#prompting#cost-optimization
15 min
BeginnerAnthropicOpenAI
16

System Prompts: Design Patterns That Actually Hold Up in Production

Four-section structure, cache-friendly ordering, modular composition, and how to write system prompts that survive model upgrades and adversarial users.

#prompting#context-engineering#production
17 min
BeginnerOpenAIAnthropic
17

RAG from Scratch: Ingestion, Retrieval, and Generation in One Pass

Build a working RAG pipeline end-to-end — parse, chunk, embed, index, retrieve, and generate — understanding every decision before layering on complexity.

#rag#vector-search#embeddings
20 min
Beginner
18

From Prompt Engineering to Context Engineering: What Actually Changed

Why writing clever prompts is the wrong mental model for 2025 LLM systems, and how the context-window-as-RAM framing changes what you build.

#prompting#context-engineering#agents
15 min
BeginnerOpenAIAnthropic
19

Tokens, Costs, and the Context Window

Why text becomes tokens, how input/output pricing asymmetry drives your bill, what the context window actually limits, and how prompt caching cuts costs by up to 90%.

#tokenization#cost-optimization#context-engineering
15 min
◆◆IntermediateOpenAIAnthropic
20

Context Engineering: Filling the Window Right

The shift from prompt to context engineering: how to write, select, compress, and isolate what goes in the window — and the silent failure modes that ship to production.

#context-engineering#prompting#cost-optimization
17 min
◆◆Intermediate
21

RAG in One Pass: Build, Measure, Improve

Build a complete RAG pipeline end-to-end — ingest, chunk, embed, index, retrieve, generate — with evaluation wired in from day one so you catch failures before users do.

#rag#vector-search#evaluation
15 min