Baize is a self-hosted sidecar that puts your existing internal APIs and tools behind an LLM agent, with a human checkpoint before anything that changes state. Here's what's new.
1. Human approval before every write
The agent can read freely, but any tool that changes state closing an order, deleting a record, shipping a shipment pauses and asks a person first. The approval card shows the evidence it gathered, the exact tool (with content hash and revision), and the arguments it's about to run. You approve or reject; nothing happens by surprise.
I just launched Baize, an open-source AI agent that helps add AI capabilities to existing services without rewriting them.
But I'm more curious about your experience: What's the biggest blocker when you try to bring AI into an existing product or system? Is it data access, deployment, security, or something else?
I'd love to hear what you've run into and what you wish existed to make it easier.
