Google today previewed an experimental edition of the Jules coding agent, that makes use of next-generation multimodal Gemini 2.0 models to automate coding tasks.

Designed to be integrated with code repositories such as GitHub, Julles is capable of creating and executing multi-step plans and processes, including modifying multiple files, preparing pull requests and fixing bugs in software.

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

Available today for a select group of Python and Javascript developers, Google plans to make Jules more widely available to developers early next year as its Gemini 2.0 models become more widely available.

At the same time, Google also revealed that Colab is updating its AI agent for automating data science tasks to add support for Gemini 2.0 models.

Those next-generation Gemini 2.0 multimodal models can now be invoked via a single Multimodal Live application programming interface (API) that Google is also launching. The first in that series is a Gemini 2.0 Flash model that makes it simpler for development teams to mix and match video, voice, spatial understanding and text within their applications in real-time using a single API.

Google AI Studio tools and the Vertex AI service provided by Google will be able to invoke that API to build those applications, with general availability of that integration scheduled for early 2025. Google is also making available three starter application experiences in Google AI Studio that can be customized along with open-source code for spatial understanding, video analysis and Google Maps exploration.

Developers can also use Gemini 2.0 Flash in Gemini Code Assist to embed this capability into their integrated development environments (IDEs). Gemini 2.0 AI models will in the months ahead also be embedded in Android Studio, Chrome DevTools and Firebase in the coming months.

The overall goal is to make it simpler for application developers will also be able to invoke native text-to-speech audio output depending on the quality required across eight different options. Gemini 2.0 Flash also natively generates images and supports conversational, multi-turn editing to enable developers to build on previous outputs they may have created,

Additionally, application developers will be able to use Gemini 2.0 to build AI agents to automate a wide range of tasks in addition to taking advantage of a Project Mariner initiative that will integrate AI agents with browsers

Logan Kilpatrick, a senior product manager for Google, said the overall goal is to make it simpler to build multimodal AI applications using Gemini 2.0 models that, based on industry benchmarks, will be twice as fast as the previous generation of Gemini 1.5 models.

It’s not clear to what degree AI agents will transform DevOps workflows, but interest in applying generative AI to software engineering is clearly running high. A Techstrong Research survey finds a third (33%) of DevOps practitioners are working for organizations that make use of artificial intelligence (AI) to build software, while another 42% are considering it. However, only 9% have fully integrated AI into their DevOps pipelines. Another 22% have partially achieved that goal, while 14% are doing so only for new projects. A total of 28% said they expect to integrate AI into their workflows in the next 12 months.

There will, of course, soon be no shortage of options for employing AI agents across DevOps workflows. The challenge now is determining what task to allocate to those AI agents in a way that ultimately increases the actual pace at which more applications are built and deployed.