Augment Code

"Excited, anxious, invigorated." That's how one engineering leader described going AI-native. We asked 218 others how they feel. The results? Remarkably consistent: "Insecurity, mistrust, hope." "Optimistic, excited, threatened." It's the same people, holding many feelings at once. That's the baseline running through our new report, The State of AI-Native Engineering in 2026, co-authored with @VinayPerneti and @EmmaStarks.

The team building Codex at @OpenAI has a front row seat to how engineering organizations are changing, as agents become part of the team. Join a live fireside chat on Thursday, May 21 at 10 AM PT with @TheRohanVarma, Product Lead for Codex, OpenAI, and Vinay Perneti, VP of Engineering, Augment Code, as we discuss: · How the Codex team builds software end to end with agents · What's actually shifting inside engineering orgs adopting them · Which change management tactics are working, and which aren't If you lead an engineering team and are trying to make sense of this moment, this is the conversation for it. Register today: watch.getcontrast.io/register/augme…

The demand for engineering managers is actually surging in the agentic coding era. Agents can write a lot of code, but that code still needs someone to set the direction, review the output, and maintain system coherence. Our VP of Engineering @VinayPerneti shared his perspective with @TheLeadDev 's @SageLazzaro in the piece, and it's worth a read for any engineering leader thinking through what their role looks like in an agent-first world. Read the story: leaddev.com/career-develop….

Uber's internal agent platform now generates 11% of all PRs across the company. Join a live conversation on Friday, 5/15 at 10 AM PT with Nikhil Ramakrishnan, Senior Software Engineer at Uber. In our discussion, he will uncover the platform foundation and reveal how engineering work at Uber has actually changed. See how Uber built their agentic developer platform, and how engineers actually use it. Register today: watch.getcontrast.io/register/augme…

Download the survey: augmentcode.com/resources/stat…

The engineering leaders we spoke to ranged from managers to CTOs, overseeing teams of 1 to 1,000+ engineers. The sample skews AI-forward. Here’s what they told us. → 48% of their code is now AI-generated. → 55% are concerned or very concerned about losing shared understanding of the codebase. → 63% say their engineers are raising fears about skill relevance to their managers. → At the largest teams (201-1,000 engineers), that last number rises to 89%.

"Excited, anxious, invigorated." That's how one engineering leader described going AI-native. We asked 218 others how they feel. The results? Remarkably consistent: "Insecurity, mistrust, hope." "Optimistic, excited, threatened." It's the same people, holding many feelings at once. That's the baseline running through our new report, The State of AI-Native Engineering in 2026, co-authored with @VinayPerneti and @EmmaStarks.

At @augmentcode , we took a counter-intuitive bet on our AI architecture. Instead of using the primary coding model to preserve KV cache (the industry standard), we used Mercury 2 by @_inception_ai as a dedicated subagent. The payoff for our users: 82% faster context compaction, 90% lower summarization costs, <1s tool-search summaries, 30% lower LLM spend via Prism routing Read the full story here: inceptionlabs.ai/blog/rise-of-r…

We surveyed 219 engineering leaders in April 2026 and asked them what's actually happening inside their organizations. The finding that stuck: most have adopted AI tools. Most haven't changed how they build software. That gap, between tool adoption and actual transformation, is where most engineering orgs are sitting right now. And the leaders who've crossed it have a few things in common. We're hosting a webinar to walk through the data. What it shows, what surprised us, and what it suggests you should do next. Register here for our session on May 14 at 10 AM PT: watch.getcontrast.io/register/augme…

@radzserg Great tweet here! Nice idea reframing PR review feedback.

I figured out what’s missing in the @augmentcode PR reviews - actual praise. It would be nice to see comments like "great refactoring here" or "nice idea renaming this method" 😎

@guymograbi Reactions of affirmation is my love language 🤖💚

I don't know if to feel joy or rage...

Harvey built their coding agents to be collaborative by design. Engineers, PMs, and researchers all contribute context to the same agent, not parallel ones running on separate laptops. They published a blog post on how it works. We're going behind it. We're hosting a live conversation with Joey Wang, Engineering Lead at Harvey, to dig into what the blog post didn't cover: the architecture decisions, the tradeoffs, and what didn't work the first time. If you're thinking about where cloud agents fit into your engineering org, this is the conversation to be in. Register here for our session on May 5 at 10 AM PT:  watch.getcontrast.io/register/augme…

Prism is in the picker today: VS Code, JetBrains, CLI (/model), and web. Billing rolls up under a single Prism line item. The underlying model that handled any given turn isn't surfaced. The point is to stop making you think about it. Read more on how we built it: augmentcode.com/blog/augment-p…

Augment can do this because we are model agnostic. No single model wins every task, so we give our customers access to all the industry leaders. That's the foundation Prism is built on: a pool of frontier models, with the routing decision made per turn rather than at the start of a session.

Today we're shipping Prism: a new option in the Augment model picker that efficiently routes each turn to the model that fits the work. On our internal multi-turn coding benchmark, Prism matches the best individual model on quality at 20–30% lower cost per task than frontier models.

@karpathy @jiayuan_jy @openclaw Full post by @VZhenylenko here: augmentcode.com/blog/karpathy-…

Quality: basically unchanged for Auggie and Codex. Claude Code dropped −0.07, with more conservative trajectories and ~5% fewer files touched per task. Karpathy-style guidelines don’t transfer uniformly across agent harnesses and repositories. In Codex, the guidelines likely add useful structure (improving efficiency). In Augment, the baseline prompt already encodes similar constraints, so the marginal impact is smaller. In Claude Code, the system prompt may already be highly constrained, so layering additional constraints could reduce exploration and degrade performance.

We added @karpathy -inspired coding rules from @jiayuan_jy to AGENTS.md and ran 40 @openclaw PRs through three coding agents. The result: Code quality was basically unchanged, but the agents got there with less work. Fewer tool calls, lower time and cost.