And by "~instant resolution by Fin" we DO mean instant! We are holding Fin's median reply time at ~7.5 seconds and it keeps going down!

Logging into all-the-slacks is the final boss of setting up a new laptop.

Doing a new talk!

A Honeycomb heatmap of a fleet whose downstream is rate limiting, with linear backoff and retry in the client.

John Arnold It's easier when there's a cheaper better substitute, and let us all hail the inventor who made it easier. But my species and my country should aspire to be able to ban horrific brain-damaging poisons even when it is a little tiny bit hard and might require a regulation.

Moving to PlanetScale added a 9 to our uptime.

Delighted to have Brett Chen from Perplexity join us, Cognition and Harvey for our AI event in SF next week! We'll be going deep on building frontier AI products, at all levels of the stack, including how and why we have built custom models for Fin. The content will

Honestly this was a big career highlight, I love this podcast. Link here: lastweekinaws.com/podcast/scream…

Fin (Intercom’s AI Customer Agent) has officially crossed 10 trillion tokens processed in production. This excludes backtesting, development traffic, and custom model usage. In Intercom, we split workloads across multiple vendors to optimize for cost, performance and

This morning, live from NYC, we announced big product updates. We announced Fin 3, a significant upgrade to Fin's ability to successfully resolve very complex customer issues. I also did a live demo of Fin resolving a complex subscription issue over the phone. We wanted to

Congrats to OpenAI shipping something called “atlas” - a rite of passage for tech companies. Looking forward to "compass".

Finally an answer to the question. Cool to see Intercom on this!

haha YES

Excellent article from John Collison - optimistic and relevant commentary on Ireland's most important problem.