> For the complete documentation index, see [llms.txt](https://docs.infotopics.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.infotopics.com/trulyp/ai/using-ai-responsibly.md). # Using AI responsibly AI is a big part of Trulyp. It can help you explore your data, answer questions, spot patterns and get to insights faster. AI works best as a capable co-pilot: combine its speed with your knowledge of the business. Use it to explore, summarise and investigate, while keeping a few things in mind. ### Check important results AI can make mistakes, miss context or give an answer that sounds convincing but isn't correct. You don't need to second-guess every response, but when an answer matters, check important conclusions against the source data. For decisions with a significant impact, consider having a second person review the result as well. ### Give it the context it needs Good context leads to better answers. Be specific about what you're trying to understand and provide the relevant data or background. At the same time, try to keep that context focused. A smaller, relevant dataset is often better than sharing everything available. Never include passwords, API keys, access tokens or other credentials. Take extra care with sensitive information such as customer data, financial information, HR data or confidential business plans. Always follow your organisation's data classification, privacy and security policies when deciding what information can be used. ### Use your organisation knowledge AI only knows the context available to it. It may not know how your organisation defines a metric, why an exception exists or what happened outside the data. If something looks surprising, investigate it. Add missing context, ask a follow-up question or check the source data. Your knowledge of the business is an important part of interpreting the answer. ### Be careful with unexpected instructions Data and documents can contain instructions too. AI responses may also occasionally suggest something you weren't expecting. Treat these instructions critically. They shouldn't be a reason to change access rights, share data or perform an action without the checks you would normally make. ### Review actions before confirming them When AI can perform an action using a connected tool, review what it is about to do before confirming. Check the proposed action, its scope and the data involved. For anything important or difficult to reverse, make sure the action is what you intended before it goes ahead. ### Keep the final decision with people Use AI to support decisions; keep accountability and final approval with the appropriate person. This is especially important when a decision has a significant impact on people, customers or the organisation. ### In practice A few habits go a long way: * **Check** important conclusions against the source data. * **Focus** the context and data you provide on what's actually needed. * **Apply** your knowledge of the organisation when interpreting results. * **Review** important decisions and actions before they happen. * **Ask someone else to review** decisions with a significant impact. AI can help you move much faster and discover things you might otherwise miss. Use that capability freely — just keep your data, your context and your judgment in the loop. --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.infotopics.com/trulyp/ai/using-ai-responsibly.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.