How to build an enterprise-grade AI software factory

About this event

Join Matar Peles, Field CTO at Port, for a hands-on session on turning AI coding agents into a fully automated, end-to-end delivery pipeline. Learn how to build a unified context layer, set up step-by-step factory agents, implement human-in-the-loop approvals for high-risk paths, and track pipeline efficiency, taking a ticket directly to pull request live. We'll dig into: • Setting up the factory itself: map the full process end to end, from the moment work arrives to the moment it ships, so the line has defined steps instead of disconnected automations. • A unified context layer: pull signals from the tools your teams already run into the shared source of truth every agent reasons over: services, owners, dependencies and the standards that apply to each. • Factory agents for each step: onboard an agent per step with a named owner and a scope of what it can touch, so you can connect the next one without rebuilding the line. • Human in the loop gates: name which paths carry enough risk to stop for a person, route each one to whoever owns it, and write their decision back before the work moves on. • Insights and optimization: track what the line ships, how much of it ran without a human, and which step is holding everything up. Speaker: Matar Peles Field CTO, Port Matar Peles is a field CTO at Port, where he shapes how the company connects product and market and guides its technical strategy in the field. He works closely with customers and internal teams to translate real-world needs into product direction, helping ensure Port delivers meaningful impact for engineering organizations. Matar focuses on improving productivity, clarity, and developer experience at scale while supporting teams in getting the most out of Port’s platform.