Discover · medium.com

Beyond the model: Engineering AI infra with scientific judgement

Medium medium.com

More ways to use this
Open on another device
Scan this QR code to open the same public page

Scan to open this page. Your saved notes and account access are not included.

Download QR code

Open the page link

Names and references

  1. Engineering — person

In the piece

How Airbnb’s agent harness transforms unstructured data exploration by encoding scientific methodology into scalable, reproducible, and audit-ready infrastructure.Ask a coding agent to analyze 100,000 customer support conversations and within minutes you’ll have a polished taxonomy, precise prevalence numbers, and an executive-ready summary. What you can’t see is the investigation that produced them: the methods it…The Airbnb Tech Blog - MediumThe challenge of unstructured data explorationIn 2025, Airbnb was preparing to launch an AI customer service assistant. Before it could ship, we needed to understand exactly what kinds of situations it would face in the real world. That included rare events that could be risky for AI to interact with, and…The Airbnb Tech Blog - MediumInsight Miner: Agent harness for unstructured text understandingInsight Miner starts with the engineering (the queries, the scaled labeling and embedding, the clustering and tracking), so that no one has to learn new infrastructure to run analysis at scale. The core method is well established: extract, embed, cluster.…The Airbnb Tech Blog - MediumGoing beyond technical teamsInsight Miner was initially designed as a tool for data science teams. However, it quickly evolved beyond that: a year in, dozens of teams are using it for hundreds of types of investigations. In fact, it has more users outside of technical roles than within…The Airbnb Tech Blog - MediumA new category of infrastructureThe Airbnb Tech Blog - Medium

Named in it

Keep going

Each of these is read from what this estate already kept: the feed a piece came through, the publisher behind it, the credits and topics the publisher printed. None of it is a recommendation, an identity or a record kept anywhere else.

More like this

Also from Medium

  1. Skipper, Airbnb’s embedded workflow engine, is now open sourceAndriy Sergiyenko medium.com
  2. CASTLE: training natural language search before the first real queryWendy Ran Wei medium.com
  3. Beyond synthetic testing: Capturing and replaying real database workloads at AirbnbZuofei Wang medium.com
  4. Personalization without user identityWei Jiang medium.com
  5. The guest journey, updated in real time: extending Airbnb’s sequence recommender with ChrononPengyu Hou medium.com
  6. Project Lighthouse — Part 3: Introducing project-lighthouse-anonymizeAdam Bloomston medium.com