Anthropic's Managed Agents memory: what it changes
Anthropic launched Memory for Managed Agents on April 23, 2026 in public beta. What the design means for agent scope, freshness, and context engineering.
AI Agent
All posts
The Wire Blog
Page 5 of 9
What MCP's 2026 roadmap means for context delivery
The MCP 2026 roadmap reframes Model Context Protocol as enterprise context infrastructure: stateless transport, MCP Apps SEP-1865, audit logs, SSO auth.
MCP (Model Context Protocol)
Why every agent handoff corrupts your context
Every multi-agent handoff is a lossy compression event. Learn which five types of context degrade at agent handoff boundaries and how to preserve them.
Multi-Agent System
Tool poisoning: how MCP tool descriptions hijack agents
Tool poisoning hides instructions inside MCP tool descriptions the agent reads as trusted context. The MCPTox benchmark recorded a 72.8% attack success rate.
Tool Poisoning
Tool-based agent memory: why 2026 benchmarks favor it
Tool-based agent memory exposes store, retrieve, and navigate as callable MCP tools. 2026 benchmarks from Mem0, Memanto, and Wire show why the pattern wins.
AI Agent
Why AI customer support replies sound generic
AI support replies sound generic because teams treat brand voice as a prompt problem. Context engineering fixes it by selecting the right exemplars.
Context Engineering
TOON vs JSON: why smaller doesn't mean cheaper for LLMs
TOON looks more compact than JSON, but a 9,649-test study found it cost LLMs 38% more tokens. The reason: model training distribution beats format size.
Structured Context
GPT-5.5 hallucination rate: what the numbers actually say
GPT-5.5's hallucination rate depends on grounding: 23% fewer wrong claims with tools, but 86% on AA-Omniscience without them. The real numbers, explained.
AI Hallucination
Agent drift: why long-running AI agents lose the plot
Agent drift is how AI agents silently deviate from their goal over long tasks. Goal drift, stale context, and four more mechanisms cause it, not the model.
Agent Drift
Provenance is a context engineering primitive, not a trust score
Retrieval provenance for AI agents isn't an audit log or a trust verdict. It's structural metadata (source, position, time, edges) agents use to plan.
Context Engineering