Beyond the CLI: Agentic AI for async workloads and non-developers

In this session from DX Annual, Christopher Sanson, Product Lead, AI Developer Experience, and Madison Capps, Engineering Manager, Infrastructure at Airbnb, challenge some of the most common assumptions about AI. Is AI primarily about replacing humans? Do organizations need mandates to drive adoption? And are the productivity gains really as small as some studies suggest?

Using examples from Airbnb's own AI journey, they share how the company achieved widespread adoption of agentic AI through AirChat, community enablement, and internal tooling rather than top-down mandates. They also discuss the impact AI is having on developer productivity, how non-developers are increasingly using coding tools, and how teams are rethinking product development in an AI-first world.

Finally, Madison takes a deeper look at the infrastructure powering Airbnb’s AI strategy, including AirChat CLI, the AirChat SDK, and AirChat Remote, along with the company’s vision for asynchronous agent workflows and the next generation of AI-powered development.

Where to find Christopher Sanson:

• LinkedIn: https://www.linkedin.com/in/christophersanson 

Where to find Madison Capps:

• LinkedIn: https://www.linkedin.com/in/madison-capps-66950625

In this episode, we cover:

(00:00) Intro

(01:37) Myth #1: AI is about replacing humans

(03:22) Myth #2: You need mandates to drive AI adoption

(05:21) AirChat, agentic AI, and Airbnb's adoption strategy

(08:07) Myth #3: AI has little impact on productivity

(09:33) Airbnb's increase in coding time and PR throughput

(14:20) Myth #4: AI coding tools are just for coders

(15:39) How non-developers are using coding tools

(17:24) Rethinking product development in an AI-first world

(20:30) Myth #5: Vibe coding isn’t coding

(22:16) Unsolved problems in agentic AI tooling and how Airbnb is addressing them

(26:30) Airbnb’s overall AI philosophy in practice

(29:15) Using agentic AI to accelerate code migrations

(30:18) AirChat SDK: How Airbnb enables teams to build AI-powered applications

(33:17) AirChat Remote and asynchronous agent workflows

(36:07) Predictions for what’s next

Referenced:

• ⁠Airbnb

• Steve Jobs’s Bicycles for the Mind 

• Jennifer St Pierre 

• Justin Reock

• AI-generated merged code holds steady at ~30%

• Andrej Karpathy's post on X