Skip to main content
This guide walks through the fastest path to a result: sign in, connect data, and pick whichever of the three primary actions matches what you want to do.
1

Sign in

Go to summand.com and create an account. Free tier is the default — no card required..edu users can request an Education upgrade from support@summand.com for full Pro features at no cost.
2

Connect data

Click Upload and drop in a CSV (up to 50 MB on Free, 1 GB on Pro, 4 GB on Enterprise), or, on Enterprise, click Add connector for PostgreSQL, MySQL, Snowflake, Azure SQL, Delta Sharing, or any Fivetran-supported source.Summand registers the data as a dataset under a new connector and runs an immediate baseline analysis — column stats, types, missingness, distributions. Files under 100 MB land within a minute.There’s no setup wizard. No target column to pick. No schema review. Once the dataset shows Ready, you’re done with setup.
3

Pick what to do next

On the dataset, choose one of three primary actions:

Chat

Open Summand and ask in English. “What’s interesting in this data?” is a fine first question.

Create a view

Build a SQL transformation — visual or code — that you can re-use across chats and experiments.

Set up an experiment

Schedule a component (predictors, surprise finding, custom) to run on a cron. Outputs are versioned.
These aren’t sequential — pick whichever fits the problem you brought to Summand. The order in the rest of this guide is: chat first (lowest friction), then views (when you need durable SQL), then experiments (when you need recurring analysis).
4

Chat with Summand

Open the chat panel from the sidebar. Pin the dataset (or a view) to the conversation, and ask anything:
  • “How many rows are in this?” — quick fact.
  • “Which columns are most correlated with revenue?” — exploratory.
  • “Build me a view that joins this with the customer table.” — Summand drafts SQL and offers to save it as a view.
Answers come grounded in the dataset’s semantic layer, so the numbers match what queries return.
5

(Optional) Create a view

For SQL transformations you’ll re-use, go to Views in the sidebar. Either:
  • Build it visually — pick datasets, drag in joins and filters, watch live Athena preview update as you go.
  • Hand-write SQL — drop into the code editor; preview is live there too.
  • Have Summand draft it — ask in chat, accept the suggestion.
Saved views work as inputs to experiments and as data sources for chat.
6

(Optional) Set up an experiment

Go to Experiments in the sidebar and click + New experiment. Pick:
  • A source — a dataset or a view.
  • One or more components — predictors, surprise finding, column stats, semantic-layer pieces. Each component has typed inputs you fill in (e.g. which column to predict for the predictor component).
  • A schedule — daily 3 AM, every 6 hours, weekly Monday, or a custom cron.
Save and the experiment runs on schedule. Each run produces a versioned output you can read in chat or wire into another view.

​
What just happened

Behind the scenes, you created:
  • A connector — the typed pointer to your data source.
  • A dataset — one per table, with the curated Parquet copy and column-level stats.
  • (Optionally) one or more views and experiments that build on the dataset.
The dataset’s detail page has nine configuration tabs — Overview, Schedule, Schema, Components, Context, Access, Notifications, Run history, Advanced — for tuning behavior. Most users never need to touch them.

​
Next steps

Connect a database

PostgreSQL, MySQL, Snowflake, Azure SQL — Enterprise tier.

Create your first view

Visual builder, code editor, or Summand-assisted.

Set up an experiment

Components, inputs, cron, run history.

Share with teammates

Per-user grants and visibility settings.