Airbnb Is Building a ‘Company Brain’ for AI Agents

Sam CharringtonOct 22, 2026

Airbnb’s “Company Brain”
for AI Agents

AI agents need the institutional knowledge experienced employees rely on: why a system works a certain way, which policies apply, and what never made it into the documentation. Capturing that knowledge is hard. Keeping it useful as people and agents add more may be harder.

In this episode, Ahmad Al-Dahle, CTO of Airbnb, shares how his team is building Project Everest, a “company brain” that captures knowledge from employees’ workflows for AI agents. We explore stale information and context poisoning, why too much context can backfire, and how the team evaluates whether shared knowledge improves engineering work.

We also discuss measuring AI productivity beyond token usage and PR counts, the limits of chat-based interfaces, and deploying support agents in a marketplace where resolving disputes means mediating between conflicting interests.

Listen on

Apple Spotify Overcast Castbox Podcast Addict Pocket Casts

Top Reasons to Watch This Episode

Understand Airbnb’s three frontiers for AI adoption
Find out how Project Everest captures institutional knowledge from employee workflows to help agents work beyond the documentation
Explore why stale context can mislead agents and how progressive disclosure gives agents just enough context to move one step forward at a time
Understand AirChat, Airbnb’s multi-model approach to AI coding, which wraps various harnesses and leverages open-source models
See how Airbnb evaluates coding agents on engineering tasks and calibrates judges to distinguish model quality
Understand the complexities of guest-host disputes and why it remains a hard frontier problem requiring human judgment
Discover how Airbnb is testing natural-language search while preserving visual exploration and traveler control

Connect with Ahmad

Chapters

00:00 - Intro
01:35 - Three Pillars of AI at Airbnb
03:19 - AI for Engineering Productivity: Balancing Velocity and Craft
06:20 - Project Everest
10:30 - Everest architecture options: databases, files, and retrieval
12:25 - Stale context, context poisoning, and progressive disclosure
13:14 - AirChat and a multi-model coding stack
14:38 - Engineering evals and calibrating model judges
17:37 - Managing model costs without token quotas
20:12 - Measuring engineering value beyond tokens and PR counts
24:12 - Behind-the-scenes agents for marketplace trust and quality
26:36 - Adversarial support mediation: evidence, policies, and conflicting interests
30:33 - Deployed support agents and limits requiring human judgment
33:05 - Support workflows and choosing human escalation
36:05 - Natural language search without a chat-first interface
39:41 - External agent access, MCP, and travel trust
44:09 - Building agent frameworks versus adopting open source
45:55 - Post-training small models for specialized, low-latency tasks
48:25 - Scaling Everest and unresolved agent experience challenges
50:54 - Conclusion