What this episode covers
A multi-company view of agentic engineering, from coding assistants to autonomous workflows and the practices teams need before trusting agents in real repositories.
Key takeaways
- Where agentic engineering is working
- How teams evaluate coding agents
- Risks in autonomous software workflows
- What production agentic engineering requires
Why it matters for AI engineering teams
The through-line is production discipline. Teams need clear ownership, evaluation loops, source-of-truth workflows, and deployment patterns before AI systems can move from impressive demos to reliable business processes.
Agentic engineering is less about replacing engineers and more about changing the control loop around software delivery.