Skip to main content
usedby

As published on augmentcode.com. Checked by usedby on Oct 9, 2026.

What happened

LMNT, an AI speech startup, uses Augment's coding assistant for code completions, codebase Q&A in chat, and refactoring across a stack that spans Python, React, Go, C++ and CUDA. It replaced earlier assistants that produced inconsistent suggestions for its diverse codebase.

Summary written by usedby from the source page, in English. The figures are those of Augment Code and LMNT, not ours.

Augment's consistent, quality suggestions reduced code review revisions. "Our PRs move faster, and there's less back-and-forth, which is a big win for us.”

From the page. augmentcode.com

Our technology stack spans from Python and React to CUDA and native Go / C++ code, Ansible for machine management, Docker configs, and more. To achieve the low latency and high quality our customers need, we manage everything from the kernel level up to the application layer.

Zach Johnson, Co-founder, LMNT. Source

What the story claims, and what we checked

What we compared with the page.

  • The passage quoted aboveCheckedCopied word for word from the page, near the name of LMNT.
  • LMNT uses Augment CodeCheckedConfirmed line.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

2.5x“train models 2.5x faster than previously experienced on NVIDIA H200s”Mistral AI uses CoreWeave. Same industry: Artificial Intelligence75%“saving 75% in cloud costs”NovelAI uses CoreWeave. Same industry: Artificial Intelligence90%“90% cost reduction”OpenAI uses CoreWeave. Same industry: Artificial Intelligence