New Relic Takes Observability Beyond Dashboards With AI Agent-Friendly CLI

New Relic has announced Ground Truth CLI, a command-line interface designed to bring observability capabilities directly into developers’ workflows and enable AI agents to investigate production issues using live operational data.

Augmented with the New Relic Autopilot API, the CLI allows engineering teams to investigate incidents, verify recovery criteria and preserve operational evidence without switching between dashboards, development environments and collaboration tools.

New Relic Launches Infrastructure 360 to Tackle Cloud Blind Spots and AI Complexity

New Relic said untracked infrastructure changes contribute to around half of major production outages.

The Left ShiftThe Left Shift Bureau

The launch reflects a broader shift towards headless observability, where developers and AI agents can access monitoring capabilities programmatically within their existing workflows.

“Every developer and AI agent needs trusted operational context to understand what is happening in production and the consequences of a change. This need is driving the next generation of observability, which is headless. Traditional observability offerings are trapped in the dashboard era.

New Relic Ground Truth CLI brings critical intelligence directly into the environments where developers and agents work. Whether a human or an AI agent is driving, they can access the operational context and New Relic capabilities needed to investigate, verify and move forward with confidence,” said Camden Swita, New Relic Head, AI.

The CLI connects New Relic’s Autopilot, NerdGraph and memory APIs to provide a unified command-line experience. Developers can query operational data, examine services, logs, alerts, and changes, and use telemetry to investigate potential incident causes.

The tool also enables teams to define and evaluate recovery conditions from the terminal. This lets engineers and AI agents assess whether a service has genuinely recovered after a fix, rather than relying on checks that pass without confirming broader system health.

Entire Bets India Can Help Solve the Infrastructure Problems of AI Agents

“If you drop a pin somewhere in India, there’s a good chance you’ll find somebody working on a particular technology, maintaining an open-source project or specialising in a particular area.”

The Left ShiftPritam Bordoloi

Another feature preserves investigation results and operational evidence, allowing engineers to resume work, review findings and share context during handoffs. AI coding tools, scripts and continuous integration pipelines can also access operational intelligence programmatically.

For example, an engineer investigating rising checkout errors could use the CLI to examine telemetry, identify potential causes and subsequently monitor whether a fix meets predefined recovery criteria.

New Relic Ground Truth and New Relic Autopilot are already generally available to customers. Ground Truth CLI is planned to enter limited preview on October 8, 2026, with integrations for Autopilot, NerdGraph and memory APIs.

New Relic Ground Truth also supports connections between compatible AI tools and operational context through the Model Context Protocol (MCP).

Google Introduces Gemini Agent to Turn Enterprise AI Into an AI Coworker

Google said Gemini Agent can connect to enterprise tools including Microsoft 365, Slack, Salesforce, ServiceNow, Jira and databases such as BigQuery, Databricks and Snowflake.

The Left ShiftThe Left Shift Bureau

Automation Anywhere to Acquire Boost.ai in Push to Build ‘Autonomous Enterprise’

The deal follows Automation Anywhere’s acquisition of enterprise AI company Aisera in late 2025.

The Left ShiftThe Left Shift Bureau

CoreWeave Enters India With 240 MW AI Data Centre Campus in Navi Mumbai

CoreWeave plans to build the capacity across three 80 MW buildings and deploy NVIDIA’s Vera Rubin Platform on its AI Cloud

The Left ShiftThe Left Shift Bureau