> 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/context/business-context.md). # Business context Business context is what your team knows and the data doesn't show: how the numbers are built, the gaps to account for, what happened when, and the targets you measure against. Branded search ROAS looks excellent until someone points out that the revenue is inflated by duplicate purchase events. Direct traffic looks like your best channel until someone explains that UTM overwriting sends half of paid there. An AI tool reading the data alone will report both figures with confidence. Business context is the layer that prevents that. It's what your team knows about how the numbers came to be, written down once, stored with the data set, and read by the AI before it answers. ## What to include * **How the data set works.** What it's built from, what one row represents, what the numbers are calculated from, and how it should and shouldn't be aggregated. * **Business logic and conventions.** How a metric is defined in your company, which rows to deduplicate or exclude, what a placeholder value really means, and when your fiscal periods start. * **Key terms and segments.** The names your team uses for customer tiers, regions, product lines, or campaign types, and how they map onto the data. * **Known gaps and instrumentation quirks.** Tracking that broke for a week, a channel that isn't in this data set at all, attribution that can't be compared across platforms. * **Your business calendar.** Launches, price changes, campaigns, outages, and busy and quiet seasons, so the AI explains a change instead of guessing at it. * **Goals and targets.** What good looks like for each metric, so a result is compared against your plan rather than reported with no reference point. ## Add business context in Coupler.io Open a data flow, go to the data set preview, and select **Context**. {% stepper %} {% step %} **Generate context with AI.** The AI inspects the data set and drafts the context for you. The first draft includes `TODO` tags wherever it didn't want to guess, marking the points that need a human to confirm. {% endstep %} {% step %} **Or add it manually.** Prefer to write it yourself? Choose to add context manually instead. {% endstep %} {% step %} **Review and fill in the TODOs.** The context opens in an editor. Replace each `TODO` with the right detail from your team, refine the wording, and save. You can also ask your AI tool to read the TODOs and work through them with you. {% endstep %} {% endstepper %} {% hint style="info" %} The context is a free-form description, so anything your team would explain to a new analyst belongs in it, including the calendar and the targets that no source system provides. {% endhint %} ## Add or update it by chatting You can also ask your AI tool to **document a data set**. It explores the data, asks you the few questions it can't answer on its own, and saves the result back to the data set. That's usually the faster route for the things only you know. The AI can see that revenue dropped in week two of March. It can't see that you changed pricing that Monday unless you tell it. ## Keep it current Business context is stored with the data set, so update it whenever the data or its meaning changes: a new definition, a fixed tracking gap, a new quarter's targets. The new version is used everywhere Coupler AI runs, in the AI Agent and in every AI tool you've connected, with nothing to re-share. {% hint style="info" %} Business context explains how to read the numbers. For what each column is, including its type, units, and your name for it, see [data context](/ai/context/data-context.md). {% endhint %} ## Available in Business context is used by the Coupler AI Agent and across every AI destination: Claude, ChatGPT, Cursor, Custom MCP, Gemini CLI, OpenClaw, and Perplexity. --- # 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.coupler.io/ai/context/business-context.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.