Augment Code
@augmentcode
The only AI coding Agent built for professional software engineers and large codebases.
Claude Haiku 4.5 is now live in Augment Code. In our internal evals, we found it delivered ~90% of Sonnet 4.5’s performance at 34% faster response speed. We're giving up to 20 free user messages over the next two weeks to everyone subscribed to a monthly paid plan once the…
Ever wondered how to build an MCP server from scratch? We're building one live with the @getsentry team. 🗓 Wed 11/5, 9am PT 📺 Watch it here → youtube.com/live/v7V7JY3A-…
Engineering teams are turning AI into real results, not just experiments. Last month at the @SFELC_ Annual in SF, Redis Principal Field Engineer Josh Rotenberg joined Vinay Pertneti from @AugmentCode, Anand Kumar Sankaran from @Workday, and Forrest Thomas from @GetGarner for a…
We're teaming up with @Railway to make infrastructure context available on demand, right in your IDE. 💡Prompt: "Is the API service on Railway healthy? Show recent errors." Shoutout to Mahmoud Abdelwahab (Senior DevRel Engineer @ Railway) for this great insight on what's next…
We’ve partnered with @getpostman to bring API context on demand. You can pull collections, configs, and responses directly into your IDE, no tab switching. 💡Prompt: “Hit the GET /invoices request from our Postman collection and mock a 200 response test.” Loved this take from…
> AI writes code like a junior engineer. Do you agree with this? @amateurhuman delivering amazing CLI-based demo and slides to introduce us to @augmentcode!
The past few weeks, we've been evaluating and working with GPT-5 Codex. Ultimately, we decided not to include it in the available models in Augment. Why? 🧵
Haiku 4.5 advances small-model performance significantly. In our internal tests, Haiku 4.5 came close to Sonnet 4.5 in terms of quality, yet at a much higher speed: → Head-to-head preference: In testing across identical prompts, internal testers preferred responses from Sonnet…
Vibe coding is a big topic these days -- as is the generic looking designs that result. Something to think about for designers looking to inject more of their taste into 0-1: how do we talk to agents about design so they listen? augmentcode.com/blog/brand-gui…
On the flip side, AI coding works less well on properly architected codebases. But context engineering can bridge the gap.
The reason AI coding works so well is that the source code of the median app was already slop before LLMs.
United States Tendenze
- 1. #WWERaw 25.2K posts
- 2. Cowboys 36.3K posts
- 3. Koa Peat 1,750 posts
- 4. Logan Paul 5,053 posts
- 5. Daron Bland N/A
- 6. Cardinals 18.7K posts
- 7. Monday Night Football 11.3K posts
- 8. Cuomo 127K posts
- 9. Marvin Harrison Jr 2,212 posts
- 10. #RawOnNetflix 1,041 posts
- 11. Turpin N/A
- 12. #OlandriaxCFDAAwards 9,666 posts
- 13. Jacoby Brissett 1,283 posts
- 14. Josh Sweat 1,283 posts
- 15. Caleb Wilson N/A
- 16. CM Punk 19.2K posts
- 17. Kyler Murray 1,368 posts
- 18. Nikki 74K posts
- 19. Condon 3,213 posts
- 20. Teen Vogue 6,464 posts
Something went wrong.
Something went wrong.