Augment Code

Intent is our vision for what comes after the IDE. AI has changed how we build software. But, it’s also made our workflows messier. One agent is great. Two work. Past that, things fall apart fast. Prompts go stale, context lives everywhere, and you end up spending more time on the tedious work of orchestrating agents. The bottleneck isn’t writing code anymore. It’s keeping the agents aligned. That’s why we built Intent.

Join our livestream tomorrow with @DynamicWebPaige from Google DeepMind where we put Gemini 3.1 Pro to the test and show you what it's capable of. Sign up to join live or receive the link to the recording. Last chance to register: luma.com/vfpdjkym

Read more: augmentcode.com/blog/gemini-3-…

Gemini 3.1 Pro is now available in our model picker. Its performance is comparable to Opus 4.6 on real-world engineering tasks, at 2.6x lower cost per message. We’re especially excited about how it performs on: - Planning and reasoning through changes across large codebases - Debugging and investigation - Navigating unfamiliar systems For planning and investigative work, try Gemini as your first pass.

If your team is drowning in PRs… Get started with SwipeReview™: swipe-review-augment.vercel.app Read the story: augmentcode.com/blog/code-revi…

Diffs weren’t sacred. They were just invented in 1991. Software changed. Interfaces didn’t. Until now.

Code review is broken. Not the tools. The format. PRs don’t fail because of quality. They fail because of attention. Today we’re launching something new. Introducing SwipeReview™.

Engineering leaders are being asked to deliver more, faster, and with higher quality. AI can help, but only if it’s embedded thoughtfully into the developer workflow. On Thursday, April 9, 2026 at 10:00 AM PT, we’re hosting a live webinar where we’ll dig into: · Where AI delivers the highest leverage in engineering today · How to reduce engineering toil without sacrificing quality or ownership · What AI-accelerated teams do differently to increase output per engineer · How to measure impact beyond just “velocity” If you’re thinking about how to effectively evolve your engineering org to become AI-native, this is for you. Register here for our session: watch.getcontrast.io/register/augme…

this is what it looks like to make things these days

We’re live this Friday, April 3 at 10 AM PT, diving into Gemini 3.1 Pro with @DynamicWebPaige from @GoogleDeepMind. See the model in action on real world engineering tasks and get some ideas on where to add it to your workflow. Register today to get reminded when we go-live: luma.com/vfpdjkym

A great conversation between @JeffMorhous and @Wattenberger on The AI-Augmented Engineer about how to think about Intent. One takeaway we keep coming back to: the unit of work isn’t a chat or a file. It’s the entire workspace. Code, context, decisions, and state all matter. Building with that in mind changes everything.

Spec-driven development is the workflow that keeps AI agents aligned. A good spec covers what to build, what to skip, and how to verify the work. Break complex tasks into small units. Let agents work individually. Use adversarial agents to check their work. Full breakdown here.