Code Intelligence Unveils Spark, Its AI Test Agent

Code Intelligence, a pioneer in AI-automated software testing, is launching Spark, an AI test agent that autonomously identifies bugs in unknown code without human interaction.

According to the company, it's the first AI Agent to find a real-world vulnerability by automatically generating and running a test for a widely used open-source software.

Spark is designed to fully automate software testing, from identifying bugs early in the development process to their actual remediation, drastically lowering the entry barrier to advanced security testing technologies like white-box fuzz testing.

When testing software, for a codebase with 100.000 lines of code, it saves up to 1.000 hours of manual effort, the company said.

During its final beta testing, Spark uncovered a vulnerability in WolfSSL, an open-source cryptography library widely used in developing embedded devices and IoT systems.

The only human involvement was launching a single command to run the AI Test Agent; analyzing the code, generating a relevant test case, and running it was done autonomously. The vulnerability, a heap-based use-after-free, could lead to unexpected behavior, crashes, or security exploits. The WolfSSL team resolved the issue immediately and released a new version with the fix in late December 2024.

"The uncovered real-world vulnerability proves that AI can effectively take over manual tasks in software testing, such as analyzing code, identifying the most likely attack vectors, generating and running tests, and can thereby yield great results," said Eric Brueggemann, CEO of Code Intelligence. "Next, we will focus on going even further by automatically fixing any uncovered bugs. This means the entire software testing process—from creating tests to bug remediation—will be completed in minutes without human interaction. However, humans will continue to make the final decisions. We will provide automatically generated pull requests with a proven fix."

Code Intelligence will host an official launch event for its AI Test Agent on January 28, featuring security and software development experts from companies such as Continental and Mozilla. Register here.

For more information about this news, visit www.code-intelligence.com.