<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Constant Labs Blog</title><description>Practical engineering articles about software, governed AI, and workflow automation.</description><link>https://constant-labs.com/</link><language>en</language><item><title>How We Built Sofia: An AI Lead Intake Agent That Calls, Summarizes, and Hands Off to Booking</title><link>https://constant-labs.com/blog/how-we-built-sofia-ai-lead-intake-agent/</link><guid isPermaLink="true">https://constant-labs.com/blog/how-we-built-sofia-ai-lead-intake-agent/</guid><description>A practical case study of building Sofia, an AI voice agent that calls new leads, captures structured context, and sends a meeting-booking follow-up.</description><pubDate>Fri, 17 Jul 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>Workflow Automation</category><category>Voice AI</category><category>Case Study</category><author>Giona Granchelli</author></item><item><title>Why I Built TramAI: Governed AI for JVM Applications</title><link>https://constant-labs.com/blog/why-i-built-tramai/</link><guid isPermaLink="true">https://constant-labs.com/blog/why-i-built-tramai/</guid><description>The engineering decisions behind TramAI and why production AI systems need explicit boundaries, permissions, portability, and auditability.</description><pubDate>Thu, 16 Jul 2026 00:00:00 GMT</pubDate><category>TramAI</category><category>Governed AI</category><category>JVM</category><category>AI Architecture</category><author>Giona Granchelli</author></item></channel></rss>