Augment Code Unveils AI-Powered Coding Tool to Challenge GitHub Copilot’s Dominance

Using Augment Code to generate code for an app. Image credit: Augment Code

Six months after raising a $227 million Series B round of funding, Augment Code is finally revealing its secret: it’s building an alternative to GitHub’s Copilot. It’s billed as a developer AI made for teams capable of understanding codebase and how engineers build software.

“Our deep understanding of our customer’s software and how it is built enables us to be vastly more effective in helping teams of developers with their day-to-day tasks,” Augment Code Chief Executive Scott Dietzen says in a statement. “Unlike Copilot, which currently outsources much of its AI to OpenAI, we have our own internal AI research team. This allows us to build a smarter AI for code. We’re already seeing Copilot customers switch to Augment because it’s a quantum leap forward.”

Augment Code is entering an ever-growing marketplace filled with competitors. In addition to GitHub, it must contend with Cognition’s Devin, Magic, Tabnine, Refact, Harness, Oracle, AWS’s CodeWhisperer, Google’s Gemini Code Assist, and others.

What Comes With Augment Code?

Now that it has launched, Augment Code highlights a few features of its AI-powered code development platform. The first, and seemingly the main interface, is chat. It enables users to ask questions about the codebase or repository, troubleshoot bugs, and outline new features.

Unsurprisingly, it can also run code completions, providing real-time in-line code suggestions and completing tasks such as accessing APIs or using third-party SDKs. This feature integrates with IDEs such as Visual Studio Code or JetBrains to provide autocomplete-like suggestions as developers code—perhaps the equivalent of Grammarly for programming. Augment Code boasts its emphasis on context awareness mitigates the risk of hallucinations and will generate more relevant suggestions.

The platform also serves as a code editor, recommending changes across the repository.

How to use the @Augment Slackbot. Image credit: Augment Code
How to use the @Augment Slackbot. Image credit: Augment Code

The final feature is that Augment Code is integrated with Slack. This means users can interact with a Slackbot, receive real-time answers to questions and have detailed conversations about system operations — all without needing to be on Augment’s website. This eliminates the need for app-hopping and could save developers time and energy.

Creating an AI-Powered Coding Assistant for Development Teams

Founded in 2022 by Dietzen, former CEO of Pure Storage; Igor Ostrovsky, ex-Chief Architect at Pure Storage; and Guy Gur-Ari, a former Google engineer, Augment Code is pursuing developing an ideal AI code assistant for the enterprise. “I continue to be struck by how that joy of programming solo I experienced fails to translate to far more talented teams building far more meaningful software,” Dietzen wrote back in August. He outlined some of the issues plaguing software teams:

  • Too much drudgery sorting mundane code & tests;
  • Too much time trying to understand code;
  • Too much toil in updating libraries and dependencies;
  • Too much effort required for code reuse and refactoring;
  • Too much time doing code reviews and ramping newbies; and
  • Too many meetings trying to coordinate efforts.

He claims GitHub Copilot and OpenAI’s ChatGPT fail to “address the complexity of programming at scale: While they are modestly proficient in programming, they are unable to take advantage of the knowledge represented within your existing codebase—they function more like a fresh [computer science graduate] than a programmer steeped in your environment; While they indeed look over the shoulder of an individual programmer, they are unaware that the programmer is part of a broader team; and while they make it easy to add code, they do not sufficiently help reuse code, so your software gets more bloated, more complex, and more fragile.”

To that end, Augment Code boasts its AI can understand large codebases. “We want you to feel like you are working with the joint intuition of your most seasoned engineers at the company and those with deep expertise on the dependencies that you use,” product lead Dion Almaer explained in August.

From left to right: Augment Code CEO Scott Dietzen, Igor Ostrovsky, and Guy Gur-Ari. Photo credit: Augment Code
From left to right: Augment Code CEO Scott Dietzen, Igor Ostrovsky, and Guy Gur-Ari. Photo credit: Augment Code

Though its claims may be valid, Augment Code isn’t the only one that provides an AI solution for software teams. GitHub has an enterprise assistance, which it launched in February 2024. Copilot Enterprise can generate code suggestions, answer queries, and summarize changes based on the organization’s codebase and standards.

Eric Schmidt, Google’s former CEO and an Augment Code investor, believes AI will “at least double software programmers’ productivity…Augment isn’t focused on the individual developer but on teams: the 100-person software team working on millions of lines of code where nobody knows what’s going on. That’s a really good problem for AI to solve.”

Augment Code tells me that it currently has “multi-100” active customers and offers developers free trials to test on their most complex repositories. The company charges a monthly subscription fee of $60 per active developer with usage-based pricing.

Leave a Reply

Discover more from Ken Yeung

Subscribe now to keep reading and get access to the full archive.

Continue reading