- Developers
- Learn how to build robust, integrated autonomous systems beyond just the core AI model.
- Business
- Understand the operational and economic factors for scaling autonomous logistics and enterprise AI.
This episode features leaders from a company with a proven, large-scale autonomous system, offering practical insights into real-world deployment.
Inside Zipline's Autonomous System: 140M Miles, Zero Incidents
Audio streams from Sequoia Capital. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Sequoia Capital's Training Data podcast features Zipline co-founder Keller Rinaudo Cliffton and Eric Watson discussing their autonomous drone delivery system. Zipline has achieved 140 million autonomous miles with zero incidents, demonstrating success beyond the drone itself. The episode covers their journey from delivering blood in Rwanda to significant cost reductions and ambitious plans for scaling deliveries.
This episode explains how Zipline built a huge drone delivery network. It shows that making drones fly is only a small part; managing everything else, like inventory and air traffic, is key. This matters because it proves autonomous systems can work safely and cheaply at a large scale.
This episode offers insights into building and scaling a massive autonomous system, highlighting that technology is only part of the equation. It's for anyone interested in logistics, enterprise AI, and real-world autonomous operations. Zipline's focus on safety, efficiency, and integration provides a case study relevant to how frontier AI labs are thinking about deploying complex AI systems in the physical world, especially in areas like autonomous systems and logistics.
- HostSequoia Capital
- GuestKeller Rinaudo ClifftonCo-founder, Zipline
- GuestEric WatsonLead, Systems Engineering and Safety, Zipline
- Episode Title: Inside Zipline's Autonomous System: 140M Miles, Zero Incidents
- Show: Training Data (an official AI show)
- Length: 55 minutes
- Autonomous Miles Flown: 140 million
- Safety Incidents: Zero
- Cost Per Delivery: $12
The largest commercial autonomous system on earth isn't a robotaxi fleet — it's Zipline, which has flown 140 million autonomous miles with zero safety incidents. Co-founder Keller Rinaudo Cliffton and Eric Watson, who leads systems engineering and safety, explain why the drone itself is only 15% of the solution. The rest spans inventory management, air traffic integration, and engineering systems such as a dual flight computer failover protocol that recently saved a delivery mid-flight. They trace Zipline's path from launching blood delivery in Rwanda in 2016 (when drone delivery was illegal in the US) to a 51% reduction in maternal mortality in that country, a $550 million commercial diplomacy partnership with the State Department, and a cost curve that fell from $300 per delivery to $12. Zipline is now racing toward a million deliveries a day, and a quiet inflection point when autonomous delivery becomes cheaper than sending a car.
Hosted by Alfred Lin and Pat Grady, Sequoia Capital
- failover protocol
- Eric Watson
- a backup system that takes over automatically if the main system fails.
David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
WithDavid Silver, Lasse Espeholt
Making Cities Awesome: Peregrine’s Nick Noone & Ben Rudolph
WithNick Noone, Ben Rudolph
The AI Duopoly Is Over: Grok 4. 5 , GPT-5 . 6 , and Muse Spark in One Week | #270
WithSalim Ismail, Dave Blundin, Dr. Alexander Wissner-Gross
Questions people ask
- What is Zipline's biggest achievement in autonomous delivery?
- Zipline has flown 140 million autonomous miles with zero safety incidents, operating the largest commercial autonomous system.
- What are the key components of Zipline's autonomous system?
- The drone itself is only 15% of the solution; the rest involves inventory management, air traffic integration, and engineering systems like dual flight computer failover.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Sequoia Capital.




