AI agent brings machining physics into CNC programming

Automating Precision: AI in CNC Manufacturing

The episode examines whether manufacturing AI can make complex CNC work faster and safer without removing expert judgment from the process.

3 key takeaways
  1. 1Limitless Labs combines CAD-aware models, machining physics, and shop-floor data to automate CNC programming.
  2. 2B-Rep geometry preserves the topology and precision that general-purpose language and vision models miss.
  3. 3An aerospace and defense customer automated roughly 60% of one part’s programming, cutting a multi-day task to half a day.

Don't miss

David Priev describes an aerospace and defense customer that automated roughly 60% of a part’s programming, reducing a multi-day task to half a day.

The brief

David Priev, CEO of Limitless Labs, describes an AI mechanical engineer built for the gap between CAD geometry, machining physics, CAM workflows, and shop-floor data.

The central technical problem is representation: mesh-based or general-purpose models miss the topology and precision of B-Rep geometry needed for reliable toolpaths.

Limitless Labs combines a proprietary CAD transformer, an open-source language model, physics simulations, sensor feedback, and human-trained guardrails to reason about cutting forces, heat, wear, and deformation.

The clearest result comes from an aerospace and defense customer: the agent automated roughly 60% of a part’s programming and reduced a multi-day task to half a day.

Priev’s broader claim is that automation will not eliminate expert machinists; it will let them supervise multiple agents while retaining difficult manufacturing decisions.

Weekly email

State of the Pod, every Monday

The week's most-discussed names and stories from podcasts, with the moments behind them. Free, five minutes, unsubscribe in one click.

Listen to the full episode and explore every guest, topic, and moment on PodLume.