> ## Documentation Index > Fetch the complete documentation index at: https://docs.tinyfish.ai/llms.txt > Use this file to discover all available pages before exploring further. # Build Your First Dataset > Go from one sentence to a filled, sourced table in the playground, then do the same from code This guide builds a small dataset in the playground, then shows the same flow with the CLI and the API. It takes about 15 minutes, most of it waiting for the run. > [!NOTE] > > Each build or populate uses one of your 3 beta runs per rolling 24 hours, across the playground, CLI, and API. Pick > one path below rather than running all three. ## In the Playground **1. Open the Datasets playground** Sign in and open [agent.tinyfish.ai/playground/datasets](https://agent.tinyfish.ai/playground/datasets). **2. Describe the dataset** Type what you want as one sentence: the kind of thing each row is, where or which ones, and the fields you need. ```text theme={null} Specialty coffee shops in Oakland with their website, neighborhood, and Google rating ``` Click **Build**. TinySet plans the columns from your sentence, which can take up to a minute. ![Datasets playground with a prompt for Oakland coffee shops typed in and the Build button](https://mintcdn.com/tinyfish/tZ8pK24QLFUf3bSL/images/datasets/prompt.png?fit=max\&auto=format\&n=tZ8pK24QLFUf3bSL\&q=85\&s=14d0811c4879fb27ec7d19810e609970) **3. Confirm the schema** Check the planned columns before anything runs: ![Confirm the schema dialog listing columns with their type, name, PK badge, and description, plus the Rows field and Build dataset button](https://mintcdn.com/tinyfish/tZ8pK24QLFUf3bSL/images/datasets/review-columns.png?fit=max\&auto=format\&n=tZ8pK24QLFUf3bSL\&q=85\&s=20f8d35ba50eaa10a1ed1339306505ee) * **Name** the dataset. * **Edit columns.** Rename them, change their type, or add an optional description that tells TinySet where to look for the value. * **Primary key.** Click **PK** to mark at least one column as the primary key. It decides when two rows are the same thing, so pick something unique to each one, like a website or street address. A name alone can merge two locations of the same chain. * **Filter.** Mark a yes/no column as the filter to keep only rows where it is true, such as "Has a roaster on site". * **Rows.** Set how many rows to fill to, from 1 to 250. Start with 25 to see results sooner. Click **Build dataset**. **4. Watch it fill** Rows appear in the table as TinySet finds them. A run usually takes 5 to 20 minutes, and you can leave the page and come back. Your datasets are listed under **Your datasets**. **5. Use the results** Click **Settings** on the dataset to: ![A filled dataset table of TinyFish events with the Settings menu open showing Share, Max rows, and Delete and populate](https://mintcdn.com/tinyfish/tZ8pK24QLFUf3bSL/images/datasets/dataset-table.png?fit=max\&auto=format\&n=tZ8pK24QLFUf3bSL\&q=85\&s=d064fd2d8a1c1d7271cf05cb6b5d9219) * **Share** to turn on a read-only link. Anyone with the link can view the table. * **Max rows** to change the row target. * **Delete and populate** to empty the table and fill it again from scratch. ## Write a Good Prompt * **Name the entity.** "Coffee shops" works better than "coffee in Oakland". Each row should be one thing. * **Scope it.** Add a place, a date range, or a category: "opened since 2024", "in the Bay Area", "Series A only". * **List the fields.** Every field you name becomes a column. Fields you leave out are left out. * **Prefer facts on public pages.** Websites, addresses, founders, prices, and ratings fill well. Private or paywalled data does not. * **Don't ask for a ranking.** "Top 10" returns 10 matching rows, not the 10 best. Ask for a column such as a rating and sort it yourself. ## From the CLI Install the CLI and sign in: ```bash theme={null} npm install -g @tiny-fish/cli@latest tinyfish auth login ``` Build a dataset and wait for its rows: ```bash theme={null} tinyfish dataset create "Specialty coffee shops in Oakland with their website and rating" --rows 25 --pretty ``` To review the columns first, plan the schema, edit the file, then create from it: ```bash theme={null} tinyfish dataset plan "Specialty coffee shops in Oakland with their website and rating" > spec.json tinyfish dataset create --from-spec spec.json --rows 25 --pretty ``` Then read and manage it: ```bash theme={null} tinyfish dataset list --pretty tinyfish dataset rows --all tinyfish dataset populate --rows 50 ``` `create` and `populate` wait for the run by default. Add `--async` to return right away, then follow the run with `tinyfish dataset watch `. ## From the API Create an API key at [agent.tinyfish.ai/api-keys](https://agent.tinyfish.ai/api-keys) and export it: ```bash theme={null} export TINYFISH_API_KEY="your_api_key_here" ``` The same two-step flow over HTTP. First plan the schema: ```bash theme={null} curl https://agent.tinyfish.ai/v1/datasets/plan \ -H "X-API-Key: $TINYFISH_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Specialty coffee shops in Oakland with their website and rating" }' ``` Edit the returned `spec` if you need to, then create the dataset from it: ```bash theme={null} curl https://agent.tinyfish.ai/v1/datasets \ -H "X-API-Key: $TINYFISH_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "spec": { ...the spec from plan... }, "target_rows": 25 }' ``` Follow the run with `GET /v1/datasets/{id}/runs/{run_id}/events`, or check `GET /v1/datasets/{id}` until `status` is `ready`, `failed`, or `cancelled`. A failed run explains why in `run.error`. Then page through `GET /v1/datasets/{id}/rows`. See the [reference](https://docs.tinyfish.ai/datasets/reference.md) for every field. ## Read Next > **[Datasets reference](https://docs.tinyfish.ai/datasets/reference.md)** > > Endpoints, the spec format, statuses, events, errors, and limits > **[CLI setup](https://docs.tinyfish.ai/cli.md)** > > Install the CLI and manage your API key This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.