> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/operate/v1/data-consumer/trust-and-monitor.md). # Trust and monitor Before you build a report, a model, or a decision on a product, decide whether you can trust it, and keep an eye on it after. You do not run the product, but you depend on it, so reading its published signals is your operating discipline. ## The signals to read Every published product surfaces trust signals; check them before you rely on it: * **Quality.** Are the product's quality checks passing? A product with open quality issues may be returning wrong-but-green numbers. * **Freshness.** When did it last refresh, and did the run succeed? Stale data is a common cause of a wrong decision. * **Lineage.** Where does a figure come from? Tracing it tells you what a number actually represents before you cite it. * **Run history.** Is the product running reliably, or are runs failing intermittently? * **AI-readiness.** If you consume through an AI client, whether the product is configured for safe AI consumption. How to read each of these is in [Evaluate](https://v2.dataos.info/consume/evaluate/overview) in the Consume guide, and specifically [Trust and freshness](https://v2.dataos.info/consume/evaluate/trust-and-freshness) and [Track activity](https://v2.dataos.info/consume/evaluate/track-activity). The shared [Observability model](/operate/v1/observability-model.md) explains where these fit. ## Operating practices * **Check trust before first use, not after a bad number.** Make the quality and freshness check a habit before you build on a product. * **Re-check after changes.** If a product's owner ships a version or a breaking change, re-confirm the signals before trusting downstream outputs. * **Follow what you depend on.** Following a product keeps you aware of its health and changes; see [Raise issues and track changes](/operate/v1/data-consumer/support-and-changes.md). * **Escalate stale or failing data.** If freshness or quality is off, contact the owner rather than working around it; you may be the first to notice. A product that is fresh, passing its checks, and running reliably is one you can build on. One that is not is a conversation with its owner. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://v2.dataos.info/operate/v1/data-consumer/trust-and-monitor.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.