AI & MCP

Dataset Instructions

Dataset instructions provide the agent with lasting context: what the survey means, how fields should be interpreted, important caveats, and analysis conventions. Instructions are saved with the project.

AI & MCP

What instructions do

Instructions supplement what the agent can infer from metadata alone. Use them for:

  • Survey context the agent can't derive from variable labels (e.g. "this was a B2B panel, not general population").
  • Interpretation rules ("always weight by wgt_design", "report column percentages by default").
  • Caveats about the data ("Q12 was asked only in wave 3").
  • House style preferences ("use 95% confidence level", "always include unweighted base").

AI & MCP

Managing instructions

  • Draft, edit, and publish instruction blocks from the Instructions panel.
  • Filter blocks by scope (dataset-wide or variable-specific) and activation mode.
  • View version history and restore older versions.
  • Instructions are saved with the project file.

AI & MCP

How instructions reach the agent

Published instructions are included in the agent's context automatically — both for the in-app agent and MCP clients. You don't need to repeat them in every prompt.

AI & MCP

Tips

  • Keep instructions factual and specific. "This survey has 2,400 respondents from the UK aged 18+" is useful. "Analyse this data well" is not.
  • Use variable-scoped instructions for field-specific caveats rather than one large block.
  • Update instructions when the dataset or analysis requirements change.