Valory has launched an artificial intelligence (AI) agent, dubbed Propel Genie, that is specially designed to act as a software engineer that enables application developers to create agents trained for specific descriptions defined in natural language specifications.

Originally developed to create agents for the open-source Olas framework for cryptocurrency transactions, Propel Genie presents developers with an interface similar to ChatGPT. It then translates natural language descriptions into a technical roadmap, known as a Finite State Machine (FSM) specification, that outlines the structure for the agent architecture. That roadmap is then used to generate the agent described in the specification using Genie code planner, code generation and code evaluation agents.

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

Valory CEO David Minarsch said Genie is essentially a super-agent that employs large language models (LLMs) to convert a design specification written in natural language to create the code that drives a fully functional autonomous AI agent. Each agent invokes different LLMs that might lend themselves better to one task than another, said Minarsch.

Genie also enables rapid prototyping through automated workflows to facilitate the swift creation of autonomous agents that developers can iteratively build, test, and refine agent prototypes as needed over a few days, he added.

Available via the Propel platform that Valory makes available for developers of crypto applications, Olas is already being used to enable multiple AI agents created using Propel Genie to interact with one another. Propel Genie, however, can also be applied more widely to enable organizations to build their own custom agents, said Minarsch.

In the long term, Valory is working toward enabling anyone to create their own AI agent by reducing the complexity. In the meantime, however, Genie essentially functions as a software engineer that enables developers of varying skill levels to create an AI agent based on a natural language specification.

Humans and AI Agents

It’s not clear how the role of software engineers will evolve in the age of AI, but many of the manual tasks are becoming increasingly automated. In the future, most DevOps teams will be made up of a mix of humans and AI agents specifically trained to handle specific tasks. The challenge will then become orchestrating workflows across a team that includes those AI agents. As the time and effort required to create new agents starts to decrease, it also becomes possible to add or replace AI agents as needed across a wide range of digital business processes.

In the short term, however, most AI tools are squarely focused on enabling developers to write more code. There is not nearly as much focus on applying AI to the workflows that DevOps teams employ to shepherd all that code into an application running in a production environment. However, with the advent of AI tools such as Genie the art of what might soon be possible is coming into sharper relief.

The one thing that remains to be seen now is the degree to which agents such as Genie might one day fundamentally change the economics of software development.