Why GPT-5.2 is our model of choice for Augment Code Review

Developers are choosing older AI models

Augment Code’s pricing is unsustainable

#1 open-source agent on SWE-Bench Verified by combining Claude 3.7 and O1

Building custom embedding models and infra to index and embed codebase in near realtime for ai code assistant

How We Optimize LLM Inference for AI Coding Assistant