Software testing company Code Intelligence today announced Spark, an AI test agent that can identify bugs and vulnerabilities without human interaction.
In its beta period, for instance, Spark found a vulnerability in WolfSSL where the only human involvement was running a single command to launch the agent. The agent handled analyzing the code, generating a test case, and running the test case all on its own.
“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.”
With Spark, Code Intelligence hopes to fully automate software testing, from identifying bugs to remediating them. It believes its solution will lower the barrier to entry for advanced testing techniques.
According to Code Intelligence, Spark can save up to 1,000 hours of manual effort for codebases with 100,000 lines of code.
The company will be holding an official launch event for Spark on January 28 at 9 AM EST, where it will go over more details about the new solution.