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

Aug 13 • Jethro Kuan and Priya Kamdar

5

1

July 2026

Make Every PR Prove Itself

How we review 200+ agent-written pull requests a day with conclusive proof and a custom testing harness.

Jul 31 • Michel Chatmajian

6

2

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.

Jul 20 • Udayan Sarin and Meeraa Ramakrishnan

6

2

May 2026

Nora, Our First Agent Employee

How a Slack bot grew into the agent platform that runs Abnormal.

May 4 • Abnormal AI and Shrivu Shankar

12

2

April 2026

Specs, Not Sprints

The playbook we use to ship products fast with AI.

Apr 20 • Abnormal AI and Rishi Kavikondala

12

1

Going to Market with Go-To-Market Engineering

Understanding the human component of AI transformation.

Apr 3 • Abnormal AI and Mickey

8

1

March 2026

Piecing the Puzzle of GTM Engineering

What is the team actually building?

Mar 16 • Abnormal AI and Mickey

5

1

GTM Engineering With AI, Abnormally

Why we choose to build in-house and how our AI development gets better with every project.

Mar 9 • Abnormal AI and Mickey

10

4

Our Design Docs Write Themselves

How markdown files, a Zoom bot, and the Claude Code SDK replaced our design review cycle.

Mar 2 • Abnormal AI and Shrivu Shankar

17

1