· MCP (Model Context Protocol)
MCP Tasks: long-running work as context offloading
MCP Tasks let a server return a durable handle instead of a blocking result, keeping a long-running tool call's interim state off the agent's context window.
· Context Engineering
Meta context engineering beats hand-tuned context
Meta context engineering (ICML 2026) learns the context-engineering process itself, beating ACE-style curation by 18 points while training 13.6x faster.
· Context Portability
Claude Fable 5 put a price on context portability
Claude Fable 5 returns refusals as HTTP 200s and retries them on Opus 4.8. The fallback API reveals exactly what agent context survives a mid-task model swap.
· Context Engineering
Five criteria of good context for AI agents
A 2026 paper formalizes five criteria for good AI agent context: relevance, sufficiency, isolation, economy, and provenance. Here's how to design for each.
· Multi-Agent System
Sub-agent context isolation: the fix for context rot
Sub-agent context isolation gives each agent its own scoped window, stopping the context rot that kills multi-agent runs. Here's the pattern and its limits.
· Context Engineering
When to process AI context: ingestion, dreaming, query
There are three moments to process AI context: ingestion, a background pass some call dreaming, and query time. Match each kind of work to the right one.
· AI Hallucination
Claude Opus 4.8 hallucinates less by answering less
Claude Opus 4.8 tops a hallucination benchmark without getting more accurate. It learned to abstain. Why retrieval honesty is a context engineering win.
· RAG (Retrieval-Augmented Generation)
RAG, long context, or fine-tuning: how to choose
RAG, long context, or fine-tuning? A 2026 decision guide on cost, accuracy, and freshness, with a use-case table for choosing the right one in production.
· Structured Context
File-native agents: when reading files backfires
A 9,649-experiment study found file-native retrieval lifts frontier-model accuracy 2.7% and drops open-source accuracy 7.7%. Match architecture to the model.
· Context Engineering
AI notetakers ship the wrong artifact
AI notetakers ship transcripts, but downstream work needs decisions, drafts, or handoffs. The artifact gap is a context engineering problem, not transcription.