.webp)
AI visibility
New Relic has announced an open-source feature called AI Coding Observability for AI-assisted software development.
The feature is designed to give engineering and platform teams visibility into the use of coding assistants such as Claude Code, Cursor, GitHub Copilot, Windsurf and Amazon Q.
The announcement comes as companies adopt AI coding tools more widely across software development, often using several assistants for different tasks. That can create monitoring gaps because these tools sit outside traditional observability systems used to track applications and infrastructure.
AI Coding Observability is intended to extend monitoring into the coding phase of the software lifecycle. It will normalise telemetry across major AI coding assistants and connect that information with existing production infrastructure data.
Cost controls
New Relic is positioning the feature as a way to track several issues linked to AI-assisted development, including how coding assistants are used during development, what they cost, whether they improve productivity, and how organisations can address security and compliance concerns.
The feature will include cost tracking for AI coding tools, allowing teams to monitor spending, compare usage against budgets and set alerts before thresholds are reached. It is also designed to replace anecdotal assessments of productivity with measurable data.
For security and compliance, a local-only or zero-outbound mode will run queries entirely within a customer's private network. According to New Relic, this is intended to support data sovereignty, privacy and regulatory requirements.
Another element is source visibility. New Relic said the code will be readable, open-source and source-available, allowing engineering and security teams to examine data privacy protocols and AI reasoning more closely.
Open standards
The feature is also being built around OpenTelemetry and the Model Context Protocol to provide a vendor-neutral approach. That should allow organisations to move telemetry data and AI workflows across different cloud environments and model providers.
Industry forecasts point to further growth in AI coding tools. New Relic cited Gartner's prediction that 90% of enterprise software engineers will use AI code assistants by 2028, underscoring the scale of change facing software teams and the oversight questions that follow.
Managing risk
"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, organisations are scaling risk as fast as they're scaling output," said Brian Emerson, Chief Product Officer, New Relic.
"New Relic AI Coding Observability will close this gap, removing barriers to quality innovation that succeeds in production," added Emerson.
New Relic said AI Coding Observability will be available as an open-source feature at no additional cost, with standard ingest rates applying. The company added that local-only mode will also be introduced soon.