https://docs.newrelic.comRSS for NodeFri, 12 Jun 2026 15:26:51 GMTU1JFIEFnZW50LTEuMQ==https://docs.newrelic.com/docs/release-notes/sre-agent-release-notes/sre-agent-26-06-11Thu, 11 Jun 2026 00:00:00 +0000<div><p>We're still working on this feature, but we'd love for you to try it out!</p><p>This feature is currently provided as part of a preview program pursuant to our <a href="https://docs.newrelic.com/docs/licenses/license-information/referenced-policies/new-relic-pre-release-policy">pre-release policies</a>.</p></div> <h3>What's new</h3> <ul> <li> <p><strong><div>New Relic AI Knowledge</div> is now in the <div>SRE Agent</div></strong></p> <ul> <li>Connect <div>Confluence</div> retros, postmortems, runbooks, and custom documents like PDFs, CSVs, and text files so the agent delivers recommendations grounded in your team's best practices, not generic guidance.</li> <li>Reduce investigation time by surfacing the past incident that matches what you are seeing, the steps that resolved it, and the team who handled it.</li> <li>Ask about standard triage steps for an alert or request the runbook for a specific error, and get a direct answer from your own documentation.</li> <li>Update documentation on a recurring schedule so the agent always reflects your most current content as your environment evolves.</li> </ul> <p>For more information, refer to <a href="https://docs.newrelic.com/docs/agentic-ai/knowledge-integration/overview/"><div>New Relic AI Knowledge</div></a>.</p> </li> <li> <p>Improvements to investigation completion - with testing showing a 21% increase in completion rates.</p> </li> <li> <p><strong>Get the right investigation for the problem you actually have:</strong> The <div>SRE Agent</div> now picks its strategy based on whether you are seeing a latency spike, an error burst, or missing data, rather than following a fixed template. Coverage now spans <div>APM</div> applications, browser apps, synthetic monitors, external services, <div>Kubernetes</div> workloads, mobile apps, and infrastructure hosts.</p> </li> <li> <p><strong>Get answers from your data without writing <div>NRQL</div>:</strong> The <div>SRE Agent</div> now translates plain-language questions about your telemetry into <div>NRQL</div> queries and returns the results, so you can investigate ad hoc questions without knowing the query language or jumping to the query builder.</p> </li> <li> <p><strong>Compare before-and-after performance after a deployment:</strong> The <div>SRE Agent</div> uses purpose-built change event tools to give you structured deployment correlation rather than guesswork.</p> </li> <li> <p><strong>Identify who changed what before an incident:</strong> A new audit skill correlates configuration changes to alert policies, monitors, and workloads using <code>NrAuditEvent</code> data, so you can connect a change to the symptom.</p> </li> <li> <p><strong>Trace requests across services:</strong> The <div>SRE Agent</div> uses distributed tracing call graphs to identify the upstream and downstream dependencies driving latency or errors.</p> </li> <li> <p><strong>Better <div>Kafka</div> investigations:</strong> Consumer lag, producer throughput, and partition balance analysis are integrated into <div>Kafka</div>-related investigations.</p> </li> <li> <p><strong>Investigations that read your dashboards and help build new ones:</strong> The <div>SRE Agent</div> now pulls context from the dashboards you have already built and generates JSON code so you can easily create dashboards from a question, so the views your team has already curated inform every answer and you can walk away with a tailored visualization rather than just text.</p> </li> <li> <p><strong>Get <div>APM</div>-native answers for <div>APM</div> entities:</strong> Investigations on <div>APM</div> applications now query <div>APM</div>-specific metrics directly rather than relying solely on golden signals.</p> </li> <li> <p><strong>Ask broader questions and get a complete answer in one pass:</strong> A single investigation can combine multiple analysis techniques, so you no longer need a chain of follow-up prompts to get a comprehensive picture.</p> </li> <li> <p><strong>Find out why telemetry went missing:</strong> When data appears to be gone, the agent queries <code>NrIntegrationError</code> to surface dropped data, rejected payloads, rate limits, and pipeline failures.</p> </li> <li> <p><strong>Investigations are tailored to your environment from the start:</strong> Before the <div>SRE Agent</div> picks a strategy, it gathers your entity relationships, recent deployments, and active alerts so the investigation reflects what is actually happening in your environment rather than following a generic playbook.</p> </li> <li> <p><strong>Catch the signal you would have missed before:</strong> Alert-triggered investigations now use wider time windows, and issue lookups use the full default lookback period so you see the complete context around each incident.</p> </li> <li> <p><strong>Know what the agent could not see:</strong> When tool results are truncated or come back empty, the agent tells you exactly what was limited and why.</p> </li> <li> <p><strong>Vague questions get a useful response:</strong> Asking "what's wrong with my app" now triggers a targeted clarifying question instead of silently failing, so you get to an actionable target faster.</p> </li> <li> <p><strong>Simple questions get simple answers:</strong> General and low complexity questions get a direct response instead of being forced through the full investigation pipeline.</p> </li> </ul>ReleasedOn: Thu, 11 Jun 2026 00:00:00 +0000.