#context engineering
Context Engineering: 14 AI articles covering context engineering news, analysis, and research
Articles
Nace AI Launches Drex for Search: 92.05% on BrowseComp-Plus withβ8
Nace AI launches Drex for Search, a retrieval layer scoring 92.05% on BrowseComp-Plus with GPT-5 using just 12.6 search calls per question, built for agents and...
Nace AI Launches Drex for Search: 92.05% on BrowseComp-Plus withβ9
Nace AI launches Drex for Search, a hosted retrieval layer scoring 92.05% on BrowseComp-Plus with GPT-5 using just 12.6 search calls per question.
Tsinghua AI Open-Sources AKV: A Cache Engineering Server for LLMβ9
Tsinghua researchers open-source AKV, a KV cache engineering server on SGLang that cuts LLM agent inference costs by 27.7% while improving task scores by 1.7 po...
TinyFish Breaks Down Agentic Search Architecture for Productionβ9
TinyFish details a production agentic search architecture with four web primitives and a seven-phase control loop to fix incomplete evidence, wasted retries, an...
DeepSeek Harness v0.2 Ships Official Desktop Apps for Its Openβ8
DeepSeek Harness v0.2 ships official desktop apps for macOS and Windows, adding built-in tools, plugin management, file review, and automation for its open-sour...
Context Engineering Inside the Harness: 4 Mechanisms That Beatβ7
Long-horizon AI agents fail from context overflow and goal loss. Learn how compaction, memory, budgeting, and todo-state in the harness fix it.
Give Your Coding Agents a Memory You Ownβ9
Give your coding agents persistent memory you controlβboost efficiency, preserve project context across sessions, and overcome stateless AI limitations.
Google AI Introduces EnvHarness: A Programmable Layer Turningβ7
Google's EnvHarness adapts agent training environments dynamically, boosting performance by up to 9 points with 9.8% fewer steps.
AI Agents Donβt Need More Context β They Need Typed Contextβ10
Why AI agents fail from type confusion in promptsβlearn how typed context prevents instruction contamination and improves observability.
Loop Engineering for RAG: Small Loops Within Steps, Big Loopsβ9
Loop engineering in RAG: detecting failures, adjusting, and retrying steps to turn brittle one-shot pipelines into resilient systems that recover and deliver.