Ortus Solutions announces the release of BoxLang AI 3.7. Name a provider, model, params and API key once, then pick it by name for a call, an agent, or a single agent run. Embeddings get their own defaults, MCP servers you build get rate limiting and trusted proxies, and a handful of important fixes land along the way.

Ortus Solutions today announces the release of BoxLang 1.19.0, the software productivity platform for building, modernizing and running applications, with developers and AI agents working together. This release is about observability: built-in code coverage and execution profiling, the missing post-invocation events for BIFs, and new query and transaction events, and it pairs with the new BxLens beta, the debug bar and ops console that exposes hotspots and bytecode profilers. It also adds your own global settings in boxlang.json, static method interception, raw binary HTTP streaming and a lot of hardening across JDBC, Java interop and CFML compatibility.

Learn how to define, build, and run AI agents with BxAgents in a hands-on session organized by Malaga-AI and sponsored by Ortus Solutions! 🚀

Building an AI agent means connecting instructions, models, tools, and application logic. A clear project structure makes those pieces easier to organize and develop.