Copado today revealed it has developed a series of generative artificial intelligence (AI) agents capable of automating specific tasks that DevOps teams routinely encounter when building and deploying applications on top of the software-as-a-service (SaaS) application platform from Salesforce.

Announced in advance of the Dreamforce 2024 conference hosted this week by Salesforce, the agents have been trained using data that Copado has been collecting for more than a decade.

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

David Brooks, vice president of products for Copado, said the first agents to be made available will focus on generating code and automating testing, followed shortly by agents that accelerate the creation of user stories, deploy scripts and surface suggestions to optimize application environments. Those agents can automate tasks versus providing a co-pilot capability that leverages generative AI to create code, noted Brooks.

DevOps teams will be able to orchestrate these agents to automate workflows in a way that should also serve to make best DevOps practices more accessible to a wider range of application development teams, said Brooks.

As DevOps continues to evolve in the age of AI more tasks will be automated using agentic AI, a method for using generative AI to create an agent that has been specifically trained to perform a task using a narrow set of data. That approach ensures that the accuracy of the agents assigned those tasks is much higher than can be achieved using a large language model (LLM) that has been trained using a corpus of data pulled randomly from across the Web.

It’s not clear at what pace agentic AI will transform DevOps workflows, but as software engineering continues to evolve teams will be made up of a mix of humans and agents that are assigned specific tasks. DevOps engineers will, of course, be needed to ensure those tasks are accurately completed but many of the rote tasks that often burn out DevOps engineers will soon be eliminated, noted Brooks.

As that level of toil is reduced it should also become possible to significantly increase the pace at which not only is generative AI used to write code, but also deploy applications, he added.

Each DevOps team will naturally need to decide to what degree they are comfortable assigning tasks to AI agents. However, as DevOps enters the AI era many of the issues that often conspired to limit the ability to build and deploy applications at scale are being eliminated. As the pace of application development starts to accelerate, each organization will need to determine how many applications that previously might not have been deployed because of a lack of resources can now be built. There may even come a day when the current level of application development backlog becomes much more feasible to manage.

In the meantime, DevOps teams would be well-advised to start identifying which routine tasks performed today should be assigned to an AI agent to provide the human members of a DevOps team with the time needed to manage workflows at a level of scale, that not too long ago might have seemed unimaginable.