RAG, Fine-Tuning & ContextManus (Yichao Ji)

Manus publishes Context Engineering for AI Agents

Context Engineering for AI Agents published — design around the KV-cache hit rate, mask logits instead of removing tools, use the file system as context, manipulate attention through recitation, keep traces of failures in the context

Why it matters

A primary record disclosing the context-engineering principles of an agent running in real production

Source — Primary sources first; secondary reports are labelled “Press”

Officialmanus.imhttps://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus

Added in Week 35, 2026 · See that week

Same week

OpenAI launches ChatGPT agent (merging Operator and deep research)OfficialChain of Thought Monitorability position paper publishedPaperLG AI Research releases EXAONE 4.0OfficialChroma publishes Context Rot technical reportOfficial

Nearby on the same axis

Chroma publishes Context Rot technical reportOfficialContext editing and memory tool launch in beta on the Claude APIOfficialACON publishedPaperJin et al. present Search-R1Paper