# Introducing DigitalOcean Insights: Built-in Observability for Your Agents, Applications, and Infrastructure > Source: > Published: 2026-10-12 13:05:00+00:00 Coding agents have changed how fast teams ship, and more of the software they ship now includes agents. A production agent spans model calls, routing decisions, tools, and the infrastructure underneath. When an agent run slows down or fails, the cause could be anywhere in that chain, and the evidence is split across separate logs, metrics, traces, and consoles. Applications running on DigitalOcean Kubernetes (DOKS) or App Platform have the same problem: a spike in a metric sends teams searching through logs in another. Connecting those signals often means building and maintaining integrations themselves or instrumenting their stack with a third-party observability tool. Either way, teams spend time on setup before they can figure out what went wrong. Today we are announcing the public preview for DigitalOcean Insights, part of DigitalOcean Agent Learning Services: one place to detect, investigate, and monitor what your infrastructure, applications, and agents are doing. Telemetry from DOKS, App Platform, Managed Agents, and more flows in through built-in integrations, with no additional instrumentation to set up. Insights is built into the DigitalOcean products you already run. Metrics, logs, and traces from those products flow into the Insights backend without requiring you to install, deploy, or instrument anything. It runs on [OpenTelemetry](https://opentelemetry.io/), the open standard for observability data, so your telemetry stays in an open, portable format rather than a proprietary one. Because all of it comes from the same platform, it shares the same dimensions, such as resource, project, and tag, so an anomaly on one signal helps you find the related signals rather than starting a new search in another tool. It is the same observability layer that already powers [DigitalOcean Managed Agents](https://www.digitalocean.com/blog/managed-agents-public-preview) (public preview), where a single run across Harness Runtime and Action Gateway is visible end to end, and it now extends to additional products across your stack. **Dashboards.** Assemble the signals that matter into a single view, and keep the charts you return to in one place. **Explorers.** Browse metrics, logs, and traces directly, drill from a product down to a single resource, and follow a trace from its root span to the exact call that failed. **Query.** Build charts with a visual builder or write PromQL directly, with the visualization pattern that fits your need: time series, stat, gauge, bar, or pie. Then save the result straight to a dashboard. **Alerts.** Set a condition on any metric, choose the evaluation window and how often to re-notify while it stays unresolved, and route it to the notification channels your team already uses. **API.** Manage alerting and notification channels through the public API, and query metrics, logs, and traces programmatically, so your observability setup lives as code alongside the rest of your infrastructure. **Access control.** Manage who on your team can view and configure Insights with role-based access control, consistent with the rest of your DigitalOcean account. Insights brings telemetry from supported DigitalOcean products into one place, from your agents down to the infrastructure they run on. It starts with the agent stack. Metrics and logs are available for Serverless Inference, Batch Inference, Inference Router, Managed Agents, and Action Gateway, so you can watch token throughput, latency, error rates, and cost estimates across the path a request actually takes. Action Gateway adds traces, so you can follow a single agent turn from the model call through each tool it invoked and back, and see exactly where it slowed down or failed. Coverage also extends to the infrastructure and applications underneath. DOKS and App Platform report their metrics into the same views, along with logs for DOKS, so a spike in a service and the container behind it show up next to the agents that depend on them. Because the telemetry lives in one backend, you can trace a problem straight to its cause without switching tools: from a slow agent response to the tool call behind it, or from a spike on DOKS to the pod driving it, without manually lining up timestamps. Detect, investigate, and monitor across your infrastructure, applications, and agents, in one place. **Open Insights in the control panel****or** **read the docs****to get started.** **A note for DigitalOcean Monitoring users:** We currently plan to consolidate the entire DigitalOcean observability experience under Insights around the time of general availability (GA). If you use DigitalOcean Monitoring today, your existing metrics and alerts will continue to work as they do today until the transition, and we plan to make the transition as smooth as possible. We will share details, including any steps you need to take or any changes to pricing before the transition happens. **A note on public preview:** Insights is provided at no additional charge during public preview, subject to the Insights Public Preview Terms and any usage or retention limits described in the Documentation. We expect to begin charging for Insights usage at GA and will announce pricing before billing begins. We plan to continue expanding coverage through the public preview phase, including custom telemetry from your own applications and support for more DigitalOcean products. This post contains forward-looking statements regarding product capabilities and availability. Insights is offered as a public preview; DigitalOcean expects but does not guarantee that public preview services perform for production-level workloads.