Introducing AI Code Insights
As adoption of AI coding tools matures, the key question for engineering leaders is no longer whether developers are using AI—it’s whether AI is being used effectively.
Leaders face critical questions that are difficult or impossible to answer with existing tooling: How are developers actually using these tools, and what are they spending on tokens? Are teams providing AI with sufficient context and clarity to generate useful output? Are codebases and systems structured in ways that AI can effectively navigate?
Today, we’re announcing AI Code Insights—a new set of capabilities from DX that give organizations real-time visibility into how AI tools are being used and where they’re falling short.
Meet AI Code Insights
AI Code Insights provides real-time visibility into AI-generated code across your organization—down to specific commits—along with deep insight into how developers are using AI tools day to day.
AI-generated code attribution. See exactly which commits and PRs contain AI-generated code. The new AI Code Overview report lets you explore critical SDLC lifecycle metrics bucketed by the percentage of AI in each PR—so you can start to understand how AI-generated code moves through your development process differently than human-written code.
How it works
AI Code Insights is powered by a lightweight, self-hosted daemon that runs on developer machines across macOS, Windows, and Linux. It integrates with supported AI coding tools through native hooks and plugins, capturing session events, file edits, and other activity before reconciling that information with local Git state and pushed commits.
For supported tools, DX attributes AI-generated code by connecting agent activity directly to committed code. Rather than inferring which changes were AI-generated, the daemon uses native integrations to identify edits made during an AI session and reports line-level attribution for every commit. Where supported, DX also links attributed code back to the session that produced it, making it possible to connect AI usage with downstream pull requests, deployments, and engineering outcomes.
For organizations that enable transcript capture, AI Code Insights also powers Agent Experience. After each supported session, DX uses a separate evaluation model to assess the interaction between the developer and the coding agent across three dimensions: the quality of the initial requirements and context, the effectiveness of the developer’s guidance throughout the session, and whether the work remained appropriately scoped. The result is an Agent Experience Score that helps teams identify patterns in how developers collaborate with AI, not just how often they use it.
The daemon is enterprise-ready and can be deployed and managed through standard MDM solutions, making it straightforward to roll out across hundreds or thousands of developer machines.
AI Code Insights is designed with security at its core. All attribution analysis happens locally on the developer’s machine. Source code, source snapshots, and raw diffs never leave the machine. DX receives only repository and commit metadata along with aggregated attribution metrics. Transcript capture is an optional capability used to power Agent Experience, and qualifying enterprise customers can request a source code review of the daemon.
Availability
AI Code Insights is generally available today for all DX Data Cloud customers. To learn more or get started, reach out to your account representative or request a demo.