> For the complete documentation index, see [llms.txt](https://docs.coupler.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.coupler.io/ai/readme.md). # Coupler AI Coupler AI works with your business data through conversation. Describe what you need in plain language, and it connects sources, prepares the data, answers questions about it, and turns the analysis into a report. No SQL, no code. ## Where it runs * **Inside Coupler.io.** The AI Agent, available in the app. It can reach every data set in your workspace. * **In the AI tool you already use.** Claude, ChatGPT, Cursor, Custom MCP, Gemini CLI, OpenClaw, and Perplexity. Add the tool as a destination on a data flow, and it can work with the data sets you sent to it. See [MCP](/ai/mcp.md) for how the connection works, and the tool's page under **Destinations → AI integrations** for how to set it up. {% hint style="info" %} Everything below works in every one of these tools. What changes from one to the next is which data sets are in reach, not what you can do with them. {% endhint %} ## What it does * **Sets up your data.** [Build and configure a data flow](/ai/set-up-coupler-io.md) from a description: the source, the destination, the schedule. * **Prepares the data your analysis needs.** Join, aggregate, or pivot data sets with SQL and save the result as a data set you can keep using. * **Answers questions and writes reports.** [Explore and analyze your data](/ai/data-analysis.md), then turn the analysis into a structured report. * **Refreshes your data on demand.** Ask for the latest data and it runs the flow, so the next question is answered against current numbers. Answers are backed by Coupler.io's validated calculations. Your AI tool doesn't estimate the numbers or query your source systems directly. It asks Coupler.io, which runs the query and returns checked results. ## What makes the answers yours [Context](/ai/context.md) is what you add so the AI reads your data the way your team does, instead of seeing only column names and rows. It comes in three layers: * [**Data context**](/ai/context/data-context.md) covers what each data set and column means: types, units, allowed values, and your names for your metrics. * [**Business context**](/ai/context/business-context.md) covers how to interpret the numbers: the logic behind them, the known gaps, your calendar of launches and outages, and the targets you measure against. * [**Skills**](/ai/context/skills.md) are reusable procedures for the work that repeats, so a recurring analysis is done the same way every time. Context lives with your data and your workspace, not in a single chat, so it applies in the AI Agent and in every AI tool you connect, and every new conversation starts already informed. --- # 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://docs.coupler.io/ai/readme.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.