Context

An AI tool connected to raw data can read column names and run queries. What it can't do is know that revenue excludes refunds, that your fiscal quarter starts in February, or that last March's spike was a pricing change and not a trend.

Context is the knowledge you add so it doesn't have to guess. You add it once, it's stored with your data and your workspace, and every conversation after that starts informed, whether it happens in the AI Agent or in an AI tool you've connected.

The three layers

Layer	What it holds
Data context	What the data means. What each data set represents, what every column holds, its type and units, and the business names for your metrics and dimensions.
Business context	How to interpret it. The logic behind the numbers, what one row represents, the gaps to account for, your calendar of launches and outages, and the targets you measure against.
Skills	How the work gets done. Step-by-step procedures for analyses that repeat, including the output format and the checks to run before an answer is delivered.

They stack. Data context lets the AI pick the right columns, business context lets it read the result correctly, and a skill turns that into the same analysis your team would run by hand.

Where each layer lives

• Data context is stored on the data set, as column descriptions and schema details. Coupler.io detects it and provides it by default, so every data set has a semantic layer from the start, and you edit it to match the logic your data actually holds. The AI reads it before it queries anything.

• Business context is stored on the data set too, as a description you write or generate in the Context tab of the data set preview.

• Skills are stored in your workspace, so they apply across data sets rather than to one.

Because all three live with your data and your workspace instead of in a chat window, an update is picked up everywhere, including in a different AI tool and in conversations started by other people on your team.

Where to start

1

Refine the data context on the data set you query most. Coupler.io already detected one, so go through it and correct what doesn't match your logic. This is the fastest improvement to answer quality.

2

Add business context to the same data set. Cover what one row represents, how the key metrics are defined, and any known gaps in the data.

3

Add a skill for the analysis you run most often. Once the same question comes up weekly, write down the procedure instead of re-explaining it.