> AI agents: this is one page from Mammoth Analytics documentation. The index of all pages as Markdown is https://mammoth.io/docs/llms.txt. Append `.md` to any docs URL, or send `Accept: text/markdown`, to get Markdown. # Pick tables and columns in the connector workspace > Use Mammoth's connector workspace: read table statuses, find missing tables, join columns from two tables, fill missing columns and ask the agent in the chat. > > Applies to: Where: Data → Connections › connector workspace The connector workspace is where you choose what a connector reads before you save it as a dataset. It opens when you connect a source (see [Connect a database or app](https://mammoth.io/docs/learn/get-data-in/connect-a-source/)) and is a page in the Data Library (**Data → Connections**). It has three parts: on a narrow screen they appear as the tabs **Tables**, **Your table** and **Chat**; on a wide screen they sit side by side. ## Tables: what the connection can read **Tables** lists the tables, objects, endpoints or files the connection can read. Use **Filter tables** to narrow it. | Source | Click a table to | | --- | --- | | Database | Open its rows with the query that read them above. See [Query a database and choose how it refreshes](https://mammoth.io/docs/learn/get-data-in/query-a-database/). | | **Cloud app** (CRM, marketing, accounting, analytics) | See its columns and sample rows, then tick the columns you want. Ticked columns gather in **Your table**. | | Drive or file server | Browse the folders and open a file. A spreadsheet opens to its tabs. If a file can't open in the panel yet, ask the agent in the chat to import it. | ### What each table status means | Status | What it means | | --- | --- | | **Returned rows** | The table was read and returned rows | | **Read, and it has no rows yet** (**empty**) | The table was read but is empty | | **403: this key can’t read it** | The route exists, but your key has no access. An admin of the source can grant it, or use **Copy a note for the HubSpot admin**. | | **404: not found** | The vendor may not offer it, or it has another name. Click **Refresh list**, or ask the agent. | | **Needs your account ID to read it** (names the input it needs) | The table needs an input, such as an ID: tell the agent, or answer its question | | **per record** | "Read once for each row of its parent table", for example the line items of each invoice | | **Not tried yet** | Not read yet. Tables listed from the vendor's guide show a line such as **From the HubSpot guide · not read yet**. | | **Failed when tried** (**Error**) | Reading it failed | ### Find a missing table with Refresh list 1. Click **Refresh list**. 2. In **Refresh the list of HubSpot tables**, optionally type the tables you want under **Tables to look for** (for example, `invoices`). 3. Click **Refresh**. The agent searches the source's documentation for more tables, then reads each one with your key. You can keep working meanwhile. New tables appear under **Just found**. If nothing new turns up, you see "Nothing new found. The chat says why." and can click **Ask the agent to find them** or **Copy a note for your admin**. ## Your table: the dataset you are building **Your table** has one column for each column you ticked, and each header shows its source table. Click a column's name to rename it. Click **Preview 100 rows** to see sample rows before you save. ### Join columns from a second table When you tick columns from a second table, Mammoth joins it to the main table on a shared key. A line under **Your table** names the join and the match count, such as **Owners joined on** Owner ID and **812 of 830 rows matched**. - If only part of the table has been read, the line says the save joins every row. - Click **Change** to pick another key. Each option shows how many rows it would match. - If no column links the tables, you see, for example, "Owners isn’t joined to the main source yet". ### Start from a sample table If **Your table** is empty, click **Use a sample table**, or drop a CSV, TSV or Excel file with a header row shaped like the table you want. Mammoth looks for each column in the source, by name and by matching values, and shows the result, such as **12 of 14 columns of HubSpot found**. Columns it can't find are marked **not found**. ### When a column can't be found A card explains why, such as **Amount: not found.**, or that your key can't reach that part of the source. | Option | What it does | | --- | --- | | **Find it in HubSpot** | Asks the agent to look for the column in another part of the source | | **Fill from a report export** | Drop a CSV or Excel export with the column and a column to match rows on. Mammoth shows "Matched 812 of 830 rows on Deal ID." | | **Copy a note for the HubSpot admin** | Copies a request asking the source's admin to give your key access | | **Save 5 columns now** | Saves the dataset without the missing column | Columns filled from a file stay as uploaded; the other columns refresh from the source. ## Chat: ask the agent for tables and columns **This connector's chat** answers questions about what a source returns and can pick tables and columns for you. Ask it what you want in the table. Clicks you make in **Tables** show up in the chat. On a database, the chat starts closed: click **Ask AI** to open it. When **Your table** is ready, click **Save as dataset** (see [Save the data as a dataset](https://mammoth.io/docs/learn/get-data-in/connect-a-source/#save-the-data-as-a-dataset)). ## Related - [Connect a database or app](https://mammoth.io/docs/learn/get-data-in/connect-a-source/): open the launcher, connect, and save the dataset. - [Query a database and choose how it refreshes](https://mammoth.io/docs/learn/get-data-in/query-a-database/): the SQL view for database tables. - [REST API](https://mammoth.io/docs/learn/get-data-in/connectors/rest-api/): how the agent builds a connector from API documentation. - [Manage saved connections](https://mammoth.io/docs/learn/get-data-in/connections/): reuse, edit and delete connections. --- Source: https://mammoth.io/docs/learn/get-data-in/connector-workspace.md · Updated: 2026-11-08