Agent Reliability Is a Distributed Systems Problem
From Kafka retries to durable workflows: how Abnormal rebuilt its agent platform to survive failure without losing progress
Abnormal Builder's Substack
Where real-time building with AI comes to life. Abnormally.
Subscribe:.rss.atom.json.md.m3u.pls
Live Last read · last published · next check
Latest episodes
Make Every PR Prove Itself
How we review 200+ agent-written pull requests a day with conclusive proof and a custom testing harness.
How We Made Multilingual Embeddings Work at 60,000 Queries a Second
At our scale, an embedding model has to be nearly free to run and still smart enough to be worth running. Here's how we got both.
Nora, Our First Agent Employee
How a Slack bot grew into the agent platform that runs Abnormal.
Specs, Not Sprints
The playbook we use to ship products fast with AI
Going to Market with Go-To-Market Engineering
Understanding the human component of meaningful AI transformation.
Piecing the Puzzle of GTM Engineering
A tour of the work our team is building across sales, customer success, marketing, and operations.
GTM Engineering With AI, Abnormally
Why we choose to build in-house and how our AI development gets better with every project.
Our Design Docs Write Themselves
How markdown files, a Zoom bot, and the Claude Code SDK replaced our design review cycle.