7 stories
Consider these scenariosAn MCP server quietly returning extra tool descriptionsPrompt injection through a calendar inviteAn Agent invokes a tool that the principal should not have access toCost overruns It isn't the model that failed. It isn't the tool that failed. What failed
53% of MCP servers use static API keys. Learn the four governance primitives your team needs to control shadow MCP, credentials, and audit trails in production.
Learn what an AI agent gateway is, how it differs from an LLM gateway, and why autonomous agents need centralized routing, guardrails, and observability.
The harness is converging. Context is what separates teams. A platform team's guide to owning Claude Code, Cursor, and Codex across your engineering org.
coding agents need context to be useful. skills registry lets teams author skills once, review and version them, and sync to claude code, cursor, and codex.
Portkey's mission has always been to help teams run AI in production reliably, with full governance and visibility. We spent the last few years building that stack for LLM calls. Thousands of teams run on it today, processing over 1 trillion tokens every day.
AI agent governance goes beyond policies. Learn the five pillars for controlling autonomous, multi-step agent behavior in production.
Showing 7 of 7 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Portkey Blog
Join 15,000+ AI enthusiasts
