Augment Code today unveiled an AI tool designed for software engineering teams to collaboratively employ large language models specifically trained to generate code.

Company CEO Scott Dietzen said the Augment Code platform provides software engineering teams with an alternative to rival GitHub Copilot offering that is based on a general-purpose large language model (LLM) developed by OpenAI, that was trained using code of varying quality collected from across the web.

Step 1 of 7

14%

Which of the following best describes how you currently monitor and manage systems across your hybrid cloud environment?(Required)

Multiple separate tools for different environments

Multiple separate tools for different monitoring and management functions

Single consolidated dashboard

Custom built monitoring and management solution

No full monitoring and management solution

Don’t know

How valuable would it be for your monitoring and management solution to incorporate predictive analytics to help you identify and address system issues that are critical and not waste time or effort working through all the data and “noise” that is not critical?(Required)

Extremely valuable

Moderately valuable

Somewhat valuable

Slightly valuable

Not valuable

How do you most typically address potential system issues BEFORE they impact your operations?(Required)

Automated workflows and playbooks to remediate potential issues as soon as they are detected

An orchestrated response process that leverages automation, AI, and human expertise to rapidly respond to potential issues

Advanced monitoring tools such as predictive analytics and anomaly detection to proactively identify and address potential issues

Respond to issues as they arise, using manual processes and troubleshooting techniques

A combination of automated remediation, orchestrated response, and/or proactive monitoring to address potential system issues

Don’t know

Other

What methods does your organization use to control and monitor cloud/IT spending?(Required)

Centralized procurement processes

Pre-approved budget thresholds

Automated cost monitoring tools

Department-level spending controls

Regular cost audits and reviews

Cloud cost optimization platform

Approval workflows for resource provisioning

Native financial operations tools provided by the cloud provider

No formal controls in place

Don’t know

Other

Please specify:

Which methods do you rely on most to detect security vulnerabilities in your systems?(Required)

Automated scanning tools

Manual assessments

Vendor notifications

Threat modeling (for early detection)

None of these

Don’t know

Other

Please specify:

What are the TWO most common ways you prioritize vulnerabilities to address within your environment?(Required)

Based on potential impact

Based on exploitability

Regulatory compliance requirements

Based on CVSS scores

Risk-based analysis of multiple factors

First-in-first-out approach

No formal prioritization process

Don’t know

How do you typically handle system updates and security patches?(Required)

Automated updates and patches

Manually review and apply updates and patches on a regular schedule

A combination of automation and manual review

Apply updates and patches on an as-needed basis.

Outsourced update and patch management

No defined process

Don’t know

Other

Δ

In contrast, Augment Code has been trained using code vetted using best practices before being exposed to a mix of proprietary and open source LLMs in real time using multiple retrieval augmented generation (RAG) techniques, said Dietzen. The output generated by GitHub Copilot is very naïve in comparison, he added.

Additionally, the Augment Code approach makes it possible to faster take advantage of AI advances more rapidly as updates are made to multiple LLMs versus being overly dependent on OpenAI, noted Dietzen.

In addition to generating code, software engineering teams can use a Slack chat interface directly from within their integrated development environment (IDE) to ask questions, to better understand how code has been constructed, and troubleshoot issues. Suggestions to improve code are surfaces inline to make it simple, for example, for software engineering teams to create tests or invoke an application programming interface (API). Software engineering teams can even chain together suggestions to create an entire pull request.

Early adopters of the Augment Code platform include Webflow, Kong, Collective and Pigment and thus far the company has raised more than $227 million in funding.

Many DevOps teams are already making extensive use of AI. A Techstrong Research survey finds a third (33%) of organizations are making use of AI to build software, while another 42% are considering it. However, only 9% have fully integrated AI into their DevOps pipelines, while another 22% have partially achieved that goal.

A separate DORA report from Google also suggests that AI has yet to substantially improve the rate at which software is actually being deployed. However, as the overall amount of toil that application developers today regularly encounter the overall quality of the code being developed should substantially improve simply because, for example, there is more time to conduct tests.
At the same time, it should become substantially simpler for software engineering teams to onboard new developers as AI platforms make it simpler to learn how a codebase has been constructed, noted Dietzen.

However, it’s not like AI platforms will replace the need for application developers and software engineers any time soon, added Dietzen. Data scientists are a long way from creating any kind of super intelligence that would be needed to exist to achieve that goal, he added. The one certain thing is the roles and job functions will need to evolve as more manual tasks are automated. The challenge now is to determine how best to assign tasks across a software engineering team that will soon consist of both AI agents and humans working in collaboration to achieve a common goal.