Skip to main content
Summand is the AI assistant inside every Summand dataset. It answers questions in plain English and generates charts on demand, grounded in the dataset’s computed-context layer.

​
What Summand can do

  • Answer questions about the data (“What’s the mean of revenue by segment?”).
  • Generate one-shot SQL and run it against your curated data via Athena.
  • Generate charts (“Show me a histogram of tenure colored by churned.”).
  • Explain feature importance and shape functions when a Predictors experiment has run.
  • Drill into surprising rows when a Surprise-finding experiment has run.
  • Draft views — “build me a view that joins orders with customers” — with a save button on the rendered SQL.
  • Suggest findings and dataset or column descriptions, which you save from the card it shows.

​
What Summand can’t do

  • Modify the dataset. No re-uploads, no schema changes, no sharing actions from chat — those are explicit UI operations.
  • Run mutations. SQL is read-only; no INSERT / UPDATE / DELETE.
  • Reach data you can’t already access. Same authorization model as the rest of the product, enforced through OpenFGA.

​
How to ask better questions

1

Be specific about the column

Instead of “what’s the relationship between price and sales,” say “plot unit_price against units_sold and add a regression line.” Summand performs better with explicit column names.
2

Add context once, not every message

A workspace’s AI Context tab, which workspace admins edit, is included in every Summand turn for that workspace. Put shared facts there — “orders in USD, B2C only, Q1 2026” — instead of repeating them per message.
3

Iterate on charts

The first chart is rarely the right one. Ask for changes in plain English: “color this by region,” “flip the axes,” “only show the top 10 categories.” Summand edits the chart in place.
4

Use Summand to navigate, not to write

Summand is most useful for questions that map to one or two computed-context reads. For multi-paragraph reports, use it to draft, then edit by hand — don’t rely on it to write narrative analysis end-to-end.

​
Limits

The context window is how much of the conversation history Summand can see at once. When a conversation grows past it, Summand sees only the most recent turns.

​
Privacy

Summand’s prompts and responses are processed through Anthropic’s API. The full dataset is not sent. Anthropic receives the schema, column statistics and example values, and the results of queries Summand runs to answer you, up to 1,000 rows per result. Anthropic processes these requests under a zero-data-retention agreement: inputs and outputs are not stored after the response is returned, and are not used for training. Anthropic is a listed subprocessor; see Compliance for the data-handling agreement. There’s no setting to turn the assistant off for an organization. Members with the Chat org role can use the assistant but can’t make changes.

​
Troubleshooting

Sanity-check against the dataset’s Overview tab or run the SQL Summand surfaces directly. If the numbers don’t match, the issue is almost always Summand picking the wrong column. Reword the question with explicit column names and try again. If it still disagrees with what queries return, please report it via support@intelligible.ai — we treat ground-truth disagreements as bugs.
Usually means the requested chart doesn’t make sense for the column types — e.g. a histogram of a free-text column. Summand will explain why; switching to a different visualization (counts, top-N) usually works.
Free-tier limits reset every Monday at 00:00 UTC. If your week-of-use spans a Sunday-to-Monday boundary, the count resets mid-session.