AI agents are now operating on real web applications, not just helping you build them. So for a team working on a new or existing PHP app the question is no longer "which assistant should we adopt" but "is our app ready to be driven by an agent"?

Agent-readiness is a design problem, and PHP devs already have the skills to solve it. In this session w see how to expose a Laravel app via an MCP server, turning operations into a small and constrained set of enumerated tools that an agent can call safely, with structured output and scoped permissions.

A working agent built on the open source Strands SDK and Amazon Bedrock, demonstrates the design end to end: it discovers the available tools, reasons about a request, and acts on the app.