Product safety
MCP as a Safe AI Integration Boundary
- Jiyu Yan
- Engineering
- 09 Jan, 2026
MCP is interesting because it makes AI integrations feel less like prompt magic and more like software boundaries. That is the part I care about. A model should no
read moreVercel AI SDK with Explicit Tool Boundaries
- Jiyu Yan
- Engineering
- 22 Aug, 2025
The risky part of an AI feature is not the chat UI. The risky part is what the chat is allowed to do. It is easy to make an assistant feel powerful by giving it tools. With something like the [Vercel
read more