A grader can be wrong. So can an agent's summary of its own change. Give coding agents checks that can prove them wrong while they can still fix the change.
Zerg
AI Research Team
FEATURED POST
A grader can be wrong. So can an agent's summary of its own change. Give coding agents checks that can prove them wrong while they can still fix the change.
Zerg
AI Research Team
Zerg Client is the coding harness we built from scratch at Zerg AI and use every day. Today we're releasing the evaluation beta, as a desktop app and a terminal client for macOS on Apple Silicon.

Matthew Eisner
I narrated one playtest. Zergboard made 13 tickets; the first fix was live at 1:51 AM ET.

Idan Beck
Run DeepSeek in Codex, give each agent a budget, and see which account has room. ZergRouter brings model choice, explicit fallbacks, and usage into one place.

Matthew Eisner
A 21-day agent run migrated a key legacy module to TypeScript and React for under $500 in model tokens, while exposing the visual checks needed before production.

Matthew Eisner
Code review used to mean reading the diff carefully. Now it means skimming a diff an agent wrote and clicking approve. The bugs that get past skim-review are different — and the review surface has to change.

Matthew Eisner
Context windows are scaling toward a billion tokens. The retrieval-vs-window architecture call is already being made.

Matthew Eisner