New Relic announced monitoring for ChatGPT apps.
The solution gives businesses the ability to monitor the performance, reliability, and user experience of custom ChatGPT apps, extending critical insights to developers so they can proactively resolve costly application issues and confidently capitalize on opportunities with generative AI.
“Bringing business services into the natural flow of a ChatGPT conversation is a powerful, intuitive, and revenue-generating strategy,” said New Relic Chief Product Officer Brian Emerson. “But once your carefully crafted application instantiates inside ChatGPT, it traditionally enters a black box where standard browser monitoring tools can fail. At New Relic, we’ve worked quickly to stay steps ahead of customers who want to maximize this opportunity, ensuring that businesses monetizing gen AI aren't flying blind when it comes to user experience and system health.”
ChatGPT app monitoring offers deep telemetry to ensure AI-generated UIs are functional, high-performing, and conversion-ready. Before developers can begin to fix a hallucination, they have to know about it. Traditional telemetry remains the backbone of this visibility, and New Relic’s browser agent is uniquely equipped to collect and analyze the data. The agent delivers instant insight into the latency and connectivity of an application within the GPT i-frame, alerts developers if a dynamic AI response triggers script or syntax failures in the user's browser, and catches log items triggered to the console — providing real time granular monitoring.
New Relic automatically tracks exactly how a user interacts with the content in the business’s custom app, from successfully clicking "buy now" to not engaging at all. Businesses are in control of specific benchmarks and event-driven analytics. For example, users can send a custom event every time an LLM successfully populates a chart according to specification, allowing developers to build dashboards that track "AI Render Success" versus "User Bounce Rate." With New Relic, developers can stop guessing how their app performs when it’s hosted by someone else, while also maintaining the highest security and privacy standards.
The ChatGPT app monitoring solution delivers:
- User Frustration Detection: Rage clicks, error clicks, and dead clicks can help identify when an application is causing friction for end users.
- Layout Instability Monitoring: Track Cumulative Layout Shift (CLS) within the i-frame as the AI streams content in. Excessive CLS can cause a frustrating user experience.
- Cross-Origin Insights: Gain a deep understanding of how an application performs when it doesn't own the top-level window, helping developers optimize for different host environments.
- End-to-End Traceability: Connect the user's interaction in the ChatGPT i-frame all the way through to backend services, providing a complete picture of every transaction.
ChatGPT app monitoring is now available as part of the New Relic Intelligent Observability Platform.
The Latest
In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ...
In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...
When most people think about cybersecurity, they picture firewalls, encryption, and access controls — technical tools designed to protect systems and data. But beneath the technology lies a deeper set of principles about trust, decision-making, and resilience ... The best leaders don't eliminate risk. They manage it intelligently. And in many ways, cybersecurity offers a surprisingly useful playbook for doing exactly that ...
Many organizations assumed their infrastructure strategy was settled. It had been implemented, optimized and built into long-term plans. Recent changes in technology and vendor consolidation are forcing a second look. Cloud outages and licensing changes have exposed how much dependency exists on a small number of platforms. As a result, organizations are reevaluating whether those decisions still hold up under current conditions ...
Edge AI is strategically embedded in core IT and infrastructure spending across industries, according to the 2026 Edge AI Survey from ZEDEDA. The research shows that 83% of C-suite and IT executive respondents say edge AI is important to their core business strategy ...
As AI adoption accelerates, operational complexity — not model intelligence — is becoming the primary barrier to reliable AI at scale, according to the State of AI Engineering 2026 from Datadog ... The report highlights a compounding complexity challenge as AI systems scale ... Around 5% of AI model requests fail in production, with nearly 60% of those failures caused by capacity limits ...
For years, production operations teams have treated alert fatigue as a quality-of-life problem: something that makes on-call rotations miserable but isn't considered a direct contributor to outages. That framing doesn't capture how these systems fail, and we now have data to show why. More importantly, it's now clear alert fatigue is a symptom of a deeper issue: production systems have outgrown the current operational approaches ...
I was on a customer call last fall when an enterprise architect said something I haven't been able to shake. Her team had just spent four months trying to swap one AI vendor for another. The original plan said three weeks. "We didn't switch vendors," she told me. "We rebuilt half our integrations and discovered what we'd actually been depending on." Most enterprise leaders don't expect that to be the experience ...
Ask any senior SRE or platform engineer what keeps them up at night, and the answer probably isn't the monitoring tool — it's the data feeding it. The proliferation of APM, observability, and AIOps platforms has created a telemetry sprawl problem that most teams manage reactively rather than architect proactively. Metrics are going to one platform. Traces routed somewhere else. Logs duplicated across multiple backends because nobody wants to be caught without them when something breaks. Every redundant stream costs money ...
80% of respondents agree that the IT role is shifting from operators to orchestrators, according to the 2026 IT Trends Report: The Human Side of Autonomous IT from SolarWinds ...