New Relic has announced AI Coding Observability, an open-source tool for monitoring AI-assisted software development workflows. As organizations adopt AI coding assistants, these tools often operate outside existing observability systems, limiting visibility into their use. AI Coding Observability extends monitoring into the software development process, enabling organizations to track, analyze, and audit AI-assisted coding activities.

“You can’t manage what you can’t see. AI coding assistants are having a measurable impact on businesses, but without real-time oversight into how they’re behaving, organizations are scaling risk as fast as they’re scaling output,” said New Relic Chief Product Officer Brian Emerson. “New Relic AI Coding Observability will close this gap, removing barriers to quality innovation that succeeds in production.”

Bringing enterprise-grade rigor to the AI coding phase

AI coding tools are now producing more code than ever, as Gartner predicts that 90% of enterprise software engineers will use AI code assistants by 2028. However, engineering organizations rarely standardize on just one AI tool. Instead, developers leverage a highly fragmented mix of coding assistants depending on the task.

New Relic AI Coding Observability is being designed to future-proof development strategies and introduce a unified, vendor-neutral pane of glass that normalizes telemetry across the major AI coding assistants and correlates it seamlessly with existing production infrastructure.

Key features and benefits of New Relic AI Coding Observability will include:

• Gain insights into code development actions – Teams will be able to move away from blind trust in their AI coding tools to gaining comprehensive insights into how these tools are actually behaving as applications and services are developed.
• Exercise cost control – AI coding assistants are a rapidly growing line item, yet most organizations treat them as an unmonitored expense. New Relic AI Observability will allow teams to track AI spend and eliminate black box invoices, and forecast spend against budgets and alert before thresholds are hit.
• Enhance productivity metrics – To understand productivity gains from coding assistant use, the capability will replace anecdotal success stories with hard data and catch inefficiencies and hidden failure modes.
• Ensure security and compliance – Local-only / zero-outbound mode will run queries entirely within the user’s private network, guaranteeing data sovereignty, privacy and regulatory compliance.
• Receive strong code transparency – Will eliminate black-box AI skepticism by providing fully readable, open-source and source-available code, empowering engineering and security teams to independently verify data privacy protocols and AI reasoning with certainty.
• Avoid vendor lock-in – Backed natively by the OpenTelemetry protocol and Model Context Protocol (MCP), the feature will deliver true vendor-neutrality that allows organizations to seamlessly port their telemetry data and AI workflows across any cloud ecosystem or language model provider.
• Provides broad coding assistant coverage – Will support Claude Code, Cursor, GitHub Copilot, Windsurf and Amazon Q.

New Relic AI Coding Observability will be available as an open-source feature on June 23 at no additional cost.