Startup Zencoder, officially For Good AI Inc., today introduced a cloud platform called Zen Agents that can be used to create coding-optimized artificial intelligence agents.

The platform is rolling out about seven months after Zencoder launched. The startup is led by Chief Executive Officer Andrew Filev, who previously founded project management software provider Wrike Inc. The latter company was acquired by Citrix Systems Inc. in 2021 for $2.25 billion.

The new Zen Agents platform has two main components. The first is a catalog of open-source AI agents that can automate more than a half dozen programming tasks. The platform’s other component, in turn, is a tool that allows software teams to build their own custom AI agents. 

Developers can create an AI agent by entering a natural language description of the tasks it should perform. The prompt could, for example, specify that the agent will be used to find vulnerabilities in Java code. Optionally, software teams can add integrations with third-party tools. A company that wishes to automate the management of its code repositories could create a custom AI agent that integrates with its GitHub account.

According to Zencoder, customers’ AI agents connect to third-party tools using the MCP protocol that Anthropic PBC released last year. The protocol eases several of the tasks involved in moving data to and to an external application. That includes the process of encrypting the network connection through which information travels.

Zen Agents provides a collection of prepackaged AI agent integrations powered by MCP. The platform also offers access to third-party registries, or cloud services that host ready-to-use MCP connectors.

The company says AI agents powered by its platform lend themselves to a range of tasks. They can create documentation that explains developers’ code, as well as generate new code in multiple programming languages. Software teams can also deploy AI agents that automatically test application updates for bugs.

Zencoder has developed a technology it calls Repo Grokking to improve AI-generated code. It maps out the structure of an application’s code base, including details such as the programming best practices that the application’s developers follow. This information allows the AI models that power its platform to generate more relevant programming suggestions.

For added measure, the platform runs AI-generated output through a series of quality checks before providing it to developers. If a bug is found, the software can automatically generate a fix. It then repeats the quality assurance process with the updated AI output.

Zen Agents is generally available today.

Image: Zencoder