Loading Tool Schemas on Demand Is How Agents Scale
An agent connected to five MCP servers can burn 55,000 tokens on tool schemas before it reads the first word of your request. GitHub's server ships 35 tools at roughly 26K tokens. Slack adds 11…
Posts tagged “context-engineering”
The Million-Token Context Window Changes What You Put In It
The 1M-token context window is here. Opus 4.8, 4.7, and 4.6, plus Sonnet 4.6, now carry the full million-token context on the Claude API, Amazon Bedrock, and Vertex AI — no surcharge, generally…
Stop Adopting AI. Start Exposing Your Context.
The AI adoption pathway that's actually working in 2026 is not "deploy a copilot to your team." It's "expose your org's context to whichever model your team already chose." That sounds like a…