Quickstart

Connect a source, review what Ward AI drafts, and read your first insight. About twenty minutes.

20 min Owner: Platform Updated 13 Sep 2026 v1.2

Add a source

Sources, then + New source. Pick your warehouse, lake, ERP or POS and give Ward a read-only credential scoped to the schemas you name. Ward reads the schema and shows you what it found before anything else happens.

In the console: Sources

Review what Ward AI drafted

Ward profiles what landed and drafts the cleaning and conforming rules. They arrive as a proposal, not as a running pipeline. You read the diff and approve it, the same way you would review a colleague's work.

In the console: Pipelines

Ask the first question

Open Chat and ask in plain English. The answer arrives with the SQL underneath it and the reasoning steps beside it, so you can see whether it asked the right question before you trust the number.

In the console: Chat

Pin what you want watched

Anything worth seeing again becomes a card in Insights or a chart on a dashboard. Ward keeps computing it and tells you when it moves.

In the console: Insights

In the console

The screens this guide walks through, captured from a running tenant.

app.getward.ai

The Sources list in Ward, showing five connected systems with their type: two Parquet exports, an HTTP API, and two API connectors, above a New source button. — **Sources.** Every external system the lake reads, in one list, with the connector each one came in through.

Ward has read a plain-English description of a POS export and returned three suggested form values, each with its own Apply button: the source name, a description, and the file path. — **Lake assistant.** Ward AI drafts the connection from a sentence. Nothing binds until someone hits Apply.

The pos_transactions_csv source after creation, showing its name, type and description, with the assistant transcript that produced it still open on the right. — **Source created.** From one sentence to a live source, with the exchange that built it kept alongside.

The Inputs and Outputs tab of a Ward pipeline, mapping the pos_transactions_parquet source to the pos_transactions model, with updated_at set as the high-water-mark column for incremental syncs. — **Pipeline.** Source in, model out, and the column that makes the next sync incremental instead of total.

The Execution tab of the materialize_pos_transactions pipeline: schedule enabled on a daily-2am preset, expanded into its five cron fields, a batch size of 50,000 records, and one unsaved change pending. — **Schedule.** Cron, batch size and error handling, on the page, not buried in a hosted scheduler you cannot see.

Ward’s Sync page: four pipelines, one running mid-flight with 900,000 rows fetched, two succeeded at 7,868,333 and 2,056 rows, and one partial, each with its own Run control. — **Sync.** Live status for every pipeline in one place, and a Run button next to each one.

Ward’s settled answer: all six stores clustered between 31.2 and 31.7 per cent against a 32 per cent margin target, then the cause at Corpus Christi, where Electronics runs at 12 per cent margin with $389K of promotional lines sold below cost carrying $162K in discounts, followed by a suggested next question. — **The answer.** Six stores, one cause, and the follow-up worth asking. One question, seven round-trips, 87 seconds.

NextConnecting sources