Overview of AI Features

Overview

DevOps includes built-in AI features that streamline two common development tasks: generating code documentation and creating Salesforce test classes. These features reduce manual effort, improve code readability, and accelerate test coverage across your projects. This overview briefly explains each AI feature and the benefits of connecting your own AI model to DevOps.

Default AI Limitations

By default, Flosum provides a free shared DeepSeek AI model for DevOps through DeepSeek’s API. Because it is shared across tenants, performance and availability depend on system load and token capacity. During heavy usage, you may see higher latency or temporary errors. To avoid this, you can add your own custom AI model. See the following article.

• Adding a Custom AI Model

Custom AI Model

If you plan to rely on DevOps AI features, we recommend you connect your own cloud-hosted or self-hosted AI model to avoid issues caused by Flosum’s shared AI resources. Using your own model can improve performance, reduce latency, and help prevent temporary errors during heavy usage. A self-hosted model can also provide stronger information security than cloud AI providers. Depending on the provider and model you choose, you may see improvements in speed and reliability. DevOps supports connecting to models that use an OpenAI-compatible API endpoint, including DeepSeek and OpenAI models. To learn how to add a custom AI model, see the following article.

• Adding a Custom AI Model

AI Test Class Creator

The AI Test Class Creator automatically generates Salesforce test classes for selected code components in DevOps. It helps accelerate test coverage by generating a baseline test class that you can review and commit to the branch. To learn how to use the AI Test Class Creator, see the following article.

AI Code Documenter

The AI Code Documenter automatically adds comments to code components in DevOps. It helps teams document code by generating readable, structured comments that you can review and commit back to the branch. To learn how to use the AI Code Documenter, see the following article.