a16z Podcast: Taking the Pulse on Bio

The shift from empirical biology to engineering-driven approaches is enabling predictable, repeatable advances in biomedicine, particularly through AI in diagnostics and CRISPR in gene editing. Companies like Freenome exemplify how AI can interpret complex biological data—such as genomic signals from blood—to enable early cancer detection with high accuracy. The convergence of biology with engineering tools, including machine learning and biological circuit design, is reducing science risk and accelerating therapeutic development.

You’ll understand how engineering principles are transforming biotech from a science of trial-and-error into a scalable, predictable discipline—reshaping investment, innovation, and clinical outcomes.

1. 01AI in biomedicine is not just improving accuracy but enabling previously impossible insights by decoding complex biological systems without requiring full human understanding.
2. 02Engineering approaches are de-risking biotech by focusing on problems with known biology (e.g., sickle cell) and applying scalable solutions like CRISPR, rather than relying on hypothesis-driven experimentation (e.g., Alzheimer’s).
3. 03New platforms—like genomics or wearables—allow for repeatable diagnostic development akin to building apps on an operating system, drastically compressing timelines and costs.