Running projects for AI features
In this article, Aaron the Technical Lead for the Post-incident team highlights the differences of running projects for AI powered features
Aaron Sheah
Finding relationships in your data with embeddings
Spotting relationships in your data can be hard especially when that data is free text. Here's how we used LLMs and vector embeddings to quickly search through our data for similar topics and even concepts.
Rob Liddle
Building a GPT-style Assistant for historical incident analysis
What looks like making GPT-style assistant in a little over a month
Teddy Aristide Necsoiu
Lessons learned from building our first AI product
If you're thinking of adding AI to your product, this is everything you should know in advance.
Milly Leadley
Supercharged with AI
Introducing our AI-powered features to enable incident responders to save crucial time, learn from previous incidents, and become more resilient over time.
Charlie Kingston
Debugging Go compiler performance in a large codebase
In a big Go codebase, compiling all that code can get slower over time. This is how I figured out some bottlenecks and made our builds much faster!
Isaac Seymour
Reflecting on a momentous 2023 at incident.io
With 2023 just about wrapped up, we wanted to take a look back on what was a special year at incident.io
Luis Gonzalez
Setting the foundations for on-call that’s fair, balanced, and human-focused
Before you drop folks into a rota, it's worthwhile to lay the groundwork for on-call that's fair for everyone and protects your company as well.
incident.io
Tracking developer build times to decide if the M3 MacBook is worth upgrading
When our CTO said "I'll upgrade your MacBook if you can prove it's worthwhile" we embarked on a journey including (re)building a Go hot-reloader, instrumenting developer builds, analysing compiler performance and feeding an AI model the data until we had an answer.
Lawrence Jones
