Introducing CodeMender: an AI agent for code security

What changed

While large language models are rapidly improving, mistakes in code security could be costly. CodeMender’s automatic validation process ensures that code changes are correct across many dimensions by only surfacing for human review high-quality patches that, for example, fix the root cause of the issue, are functionally correct, cause no regressions and follow style guidelines. As part of our research, we also developed new techniques and tools that let CodeMender reason about code and validate changes more effectively.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• Introducing Aardvark: OpenAI’s agentic security researcher
• Introducing AI Sheets: a tool to work with datasets using open AI models!
• The agent security gap: 54% of enterprises have already had an AI agent incident, and most still let agents share credentials

• Introducing Aardvark: OpenAI’s agentic security researcher similarity 0.26
• Introducing AI Sheets: a tool to work with datasets using open AI models! similarity 0.19
• The agent security gap: 54% of enterprises have already had an AI agent incident, and most still let agents share credentials similarity 0.19