Scalac's blog

AI agents pushed GitHub to 275 million commits a week, and Microsoft's own cloud couldn't keep up. Microsoft and JetBrains just placed opposite bets on who should own the harness your coding agents run in.

What we learned building a Rust orchestration layer for a real multi-agent AI system — from A2A protocol churn and manual agent loops to Agent Skills and context design.

Here is what matters in distributed systems this month. Oracle proposed removing JVMCI — Amazon pushed back. Anthropic published a Claude Code production postmortem. OpenAI shipped WebSocket Responses API. MCP lands on the JVM.

How do we actually use AI in production Scala systems at Scalac? Our senior engineer shares what works, what slows you down, and why LLMs often miss what makes Scala valuable in the first place.

1. Introduction: Agentic AI is a Backend Engineering Challenge, Not Just Prompt Engineering LLM models are useless without access to data. They can generate text, but to “find suitable candidates for open vacancies,” they must call real APIs, read results from a database, and make decisions based on the current state of the system. While […]