· MCP (Model Context Protocol)
Tool calling is retrieval: what Needle proves at 26M
A 26M-parameter model just matched Gemini at function calling. Here is what Needle's distillation result means for MCP and agent context engineering.
· MCP (Model Context Protocol)
MCP resources are the underused half of MCP
Every MCP discussion is about tools. The protocol's resources primitive is how you load context without paying for it every turn. Here's how to use it.
· Context Engineering
Agentic context engineering: how ACE evolves contexts
ACE (ICLR 2026) beats tuned prompts by 10.6% with self-evolving contexts that avoid brevity bias and context collapse, two real failures of prompt tuning.
· Context Engineering
Context engineering lives in substrates, not harnesses
Codex shipped codex-plugin-cc and AGENTS.md joined the Linux Foundation. The signal is consistent: context engineering is substrate work, not harness work.
· AI Hallucination
Long context tripled hallucinations in 35 open models
A 172-billion-token study across 35 open models found hallucination rates triple from 32K to 128K context, and exceed 10% at 200K for every model tested.
· MCP (Model Context Protocol)
Progressive tool loading is the new MCP context pattern
Preloading every MCP tool into an agent's context is the bottleneck of 2026. Progressive tool loading defers definitions until needed and saves tokens.
· AI Agent
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.
· MCP (Model Context Protocol)
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.
· Multi-Agent System
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.
· Tool Poisoning
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.