Have you wondered why your single bug-fixing agent doesn't actually burn down your team's bug backlog effectively? Read this insight from Augment's CTO and co-founder @igoro, and let us know what you think!

Gemini 3.8 Flash is now half price in Augment for the next two weeks ($0.38/M input, $1.88/M output tokens). Our team has been throwing mockups and screenshots at the new model and getting back web pages that can ship without a redesign pass. This is the cheapest the model gets, so it's a good time to point it at your hardest frontend work and find out what @GeminiApp is capable of!

GPT-6 Astra is live in Cosmos! OpenAI's most capable model yet brings a significant jump on long-horizon coding and multi-step agentic work. Give it your hardest task to work on over the holiday weekend at

Two new models are live in Cosmos today! We've come a long way since declaring that the era of single-model engineering is over and more models are coming soon... GLM 5.3 Flash from @Zai_org (with US-based inference provided by @FireworksAI_HQ) is an order of magnitude cheaper than the most intelligent open-source models we've tested, while achieving the same level of intelligence as Sonnet 5. Gemini 3.8 Flash from @GoogleDeepMind achieves a clear step in intelligence over Gemini 3.7 Flash at the same price point. Try them both today:

Claude Fable 5.1 is now available in our model picker! We're starting off with the same use cases as Fable 5 - extremely long, multi-step tasks that require deep reasoning - and we're increasingly pushing the model to complete tasks that can run unattended. Try it today in Cosmos:

Gemini 3.7 Flash - the latest model from @GoogleDeepMind - is now live in Cosmos, our agent orchestration platform for building software factories. For the next two weeks, build with it at half price - $0.375/M input tokens - $1.875/M output tokens

Less than one month after @grok 4.5 came to Augment, @grok 4.6 is now available in Cosmos, our agent orchestration platform for building software factories. Together with Augment's Context Engine, @grok models have become a powerful option for working across large codebases. We're excited to see what our customers build with the most intelligent @grok model to date!

The best value for every token: GPT-5.6 Sol is now our default in Cosmos Eight models in eight weeks! After testing them all on real, long-horizon software development tasks, we’re making @OpenAI’s GPT-5.6 Sol the new default in Cosmos. It’s the most token efficient model that clears our quality bar for the engineering loops that teams are setting up with Cosmos, our agent orchestration platform. You still have the flexibility to pick any other models and when in doubt, just ask the Cosmos Advisor to pick the best model for the task.

Our users have been really excited to try Kimi K3 and we're excited to bring it to Augment's product family. It is the most capable open-source model that we have tested to date. Try it today in Cosmos, our agent orchestration platform! Congrats to the @Kimi_Moonshot team, and thanks to @FireworksAI_HQ for offering us US-hosted inference from day one.

@grok 4.5 saw the largest week-over-week increase in usage of any model in our picker. When the frontier is moving this fast, having your pick of models is a huge advantage: route to your favorite model today, not the top model from last quarter. More soon on what we've been using!

Opus 5 is live in Augment Code. In our internal evals it scored higher than Opus 4.8 on correctness, completeness, and code reuse. We trust it enough that we're upgrading one of our Cosmos code review experts that reviews all our code to Opus 5: near-Fable review quality at a lower price. Try it in Cosmos today!

For the first time ever: Grok 4.5 is now available. Welcome @SpaceXAI to Cosmos, our agent orchestration platform. Together with Augment's context engine, Grok 4.5 is a powerful option for working across large codebases. We're interested to see how Grok 4.5 performs for our customers - let us know your thoughts and what you plan to build

On July 22nd I am hosting a webinar on automated incident mgmt with AI, together with the folks at @augmentcode! That’s because I write a lot about my AI workflows with @tolariamd, but many people (rightfully) tell me that things are more complex in a real team. So I invited the team at Augment to share how they transformed their own engineering org, redesigning their main dev workflows. If you are interested you can RSVP here!

Your organization's token spend is off the charts because you've thrown everyone into the deep end and said "swim!". Of course there's deeply inefficient use of tokens, everyone is just doing their own thing. They're running loops hoping for some outcome, running local code review on every change, have agents polling for PR comments on their laptops. Not to mention the sheer volume of duplicative context, internal skills, and other support systems they've burned tokens creating. And this doesn't even account for the skill gap of effective users versus novice users. It's like the industry forgot 40 years of lessons learned on building efficient engineering teams and practices. Software engineering is a system, treat it like one and you might find tokens are actually worth the spend.

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.