Riveter

account Information about the account associated with the API key: plan, credit balance, and the key's metadata. Unchanged from the legacy API (response uses the legacy `request_status` format).

get_account

build configured dataset Run a **configured dataset** — a reusable, pre-configured dataset template (id `cds_...`) set up for your account. The spec, prompt template, row cap, and per-run credit cost are all defined on the template; you only supply `parameters` to fill in its `{{ placeholder }}` values. Returns the dataset-build run; poll [GET /runs/{id}](#tag/runs/get/runs/{id}). **Example — Fill in template parameters:** { "parameters": { "practice_type": "dentists", "state": "ohio" } } **Workflow:** Starts an async run of a configured dataset. Poll `get_run`, then fetch with `get_run_result`.

build_configured_dataset

build dataset Build a dataset from a natural-language prompt, a structured spec, or both. Riveter finds the rows for you. - **Prompt only** — e.g. "top 50 US SaaS companies with their websites". The builder analyzes the prompt into identifiers/qualifiers/attributes automatically. - **Structured spec** — `identifiers` (what each row is, e.g. "Company name") and `qualifiers` (constraints rows must satisfy). Optional `attributes` are saved as the enrichment columns described above. - **Both** — the prompt is combined with the spec. **Note**: The result contains the identifier columns only (e.g. company name + website). `attributes` are not immediately filled in by the build — they become the output columns of an enrichment that can run later, as a separate step. To get attributes filled: pass `auto_run_enrichment: true`, or call [POST /enrich](#tag/enrich/post/enrich) with `dataset_id` once the build completes. This is a second paid run: `dry_run` shows the combined estimate. Returns the dataset-build run; poll [GET /runs/{id}](#tag/runs/get/runs/{id}) and fetch rows with [GET /runs/{id}/result](#tag/runs/get/runs/{id}/result), or pass `dataset_webhook_url`. **Example — Prompt with identifiers and qualifiers:** { "prompt": "Top 50 US SaaS companies with their websites", "identifiers": [ "Company name", "Website" ], "qualifiers": [ "US-based", "SaaS" ], "max_items": 50 } **Example — Refuse the build if it could cost more than 200 credits:** { "prompt": "Top 50 US SaaS companies with their websites", "max_items": 50, "max_credits": 200 } **Example — Structured spec:** { "identifiers": [ "Company name", "Website" ], "qualifiers": [ "US-based", "SaaS" ], "attributes": [ "CEO", "Employee count" ], "max_items": 50 } **Example — Build and auto-enrich in one step:** { "prompt": "Top 50 US SaaS companies", "attributes": [ "CEO", "Revenue" ], "max_items": 50, "auto_run_enrichment": true, "auto_run_enrichment_webhook_url": "https://your-server.com/webhook" } **Workflow:** Starts an async dataset build run. Poll `get_run` until status is 'success', then fetch the rows with `get_run_result`. Pass `auto_run_enrichment: true` to enrich the rows in the same flow.

build_dataset

create enrichment Create an enrichment (no run) from a **completed dataset build**: the dataset's rows become the enrichment's input rows, and its attributes become output columns. Configure further in the UI or via [PATCH /enrichments/{id}](#tag/enrich/patch/enrichments/{id}), then run with [POST /enrich](#tag/enrich/post/enrich).

create_enrichment

create extraction Create an **extraction** — a reusable recipe for scraping structured records from a website — and start its agent discovery. Discovery explores the site, builds the scrape/extract plan, and validates it against your schema. Poll [GET /extractions/{id}](#tag/extractions/get/extractions/{id}) until `status` is `ready`, then execute it with [POST /extractions/{id}/runs](#tag/extractions/post/extractions/{id}/runs). The extraction (`ext_...`) and its runs (`run_...`) are different resources. Creating an extraction charges discovery credits (returned as `credits_charged`). To see the price first, send `dry_run: true`. **Example — Create an extraction:** { "starting_url": "https://example.com/products", "goal_description": "Extract every product with its name and price", "output_record_json_schema": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "string" } } }, "required_keys": [ "name" ] } **Workflow:** Discovery is async but returns no run — poll `get_extraction` until `status` is 'ready', then execute with `run_extraction`.

create_extraction

create monitor Create a **monitor**: a schedule that re-runs an enrichment daily, weekly, or monthly and can POST results (or only changes) to a webhook. **Example — Daily monitor with change alerts:** { "enrichment_id": "enr_018f5b60-1234-7abc-89ab-0123456789ab", "cadence": "daily", "hour": 9, "minute": 0, "timezone": "UTC", "alert_rule": "only_on_change", "webhook_url": "https://your-server.com/webhook" } **Workflow:** Creates a scheduled monitor. Check it with `get_monitor`, pause it with `update_monitor` (enabled: false), and list its runs with `list_monitor_runs`.

create_monitor

enrich Add AI-researched columns to rows. Rows come from exactly one of `input` (columnar: `{ "Header": ["row1", "row2"] }`, all arrays equal length) or `dataset_id` (a completed build, `ds_...`). Column config, exactly one of, in order of preference: 1. `enrichment_id` — run a saved enrichment (`enr_...`, from `list_enrichments`). Fixed, tested config; most consistent. Up to 10,000 rows. Input headers must match the enrichment's input columns (`get_enrichment`). 2. `prompt` + `attributes` — Riveter drafts the column config from a description and up to 20 output column names. No setup; results vary per run. Up to 1,000 rows. 3. `output` — full per-column spec: `prompt`, `contexts`, `tools`, `format`, `run_when`, or a tool-only `tool`. Up to 1,000 rows. Call `help` with `column_config`, `run_when`, `formats`, `tools`, or `examples` before writing one. Returns a run. Poll `get_run_result` with `wait: 50` (or pass `webhook_url`). `dry_run: true` returns the credit estimate without running. **Example — Run a saved enrichment:** { "enrichment_id": "enr_018f5b60-1234-7abc-89ab-0123456789ab", "input": { "Company Name": [ "Acme Corp", "Tech Solutions Inc" ] } } **Example — Prompt + attributes (auto-generated config):** { "prompt": "Research each company", "attributes": [ "CEO", "Employee Count", "Industry" ], "input": { "Company": [ "Apple", "Google" ] }, "webhook_url": "https://your-server.com/webhook" } **Example — Full output specification:** { "output": { "Employee Count": { "prompt": "Find the number of employees at this company", "contexts": [ "Company" ], "format": "number" } }, "input": { "Company": [ "Apple", "Google" ] } } **Example — Enrich the rows of a completed dataset build:** { "enrichment_id": "enr_018f5b60-1234-7abc-89ab-0123456789ab", "dataset_id": "ds_018f6a70-1234-7abc-89ab-0123456789ab" } **Example — Price the run without starting it:** { "enrichment_id": "enr_018f5b60-1234-7abc-89ab-0123456789ab", "input": { "Company Name": [ "Acme Corp", "Tech Solutions Inc" ] }, "dry_run": true } **Workflow:** Starts an async run. Poll `get_run` with the returned run id until status is 'success', then call `get_run_result` for the output.

enrich

enrichment → dataset Build a dataset **shaped for this enrichment**: identifiers are derived from the enrichment's source-data columns automatically, so generated rows land as valid input rows. The build finds rows only; the enrichment's output columns are not researched until the enrichment runs. Optionally set `auto_run_enrichment: true` to run the enrichment on the rows as soon as the build completes (a second paid run; the kickoff response then carries `enrichment_run_id`). Returns the dataset-build run — poll it via [GET /runs/{id}](#tag/runs/get/runs/{id}). **Example — Build rows and auto-run the enrichment:** { "prompt": "US-based fintech startups", "qualifiers": [ "B2B", "founded after 2015" ], "max_items": 100, "auto_run_enrichment": true } **Workflow:** Starts an async dataset build run matching the enrichment's input columns. Poll `get_run`, then fetch rows with `get_run_result`.

build_dataset_for_enrichment

extend dataset Generate **new rows** for an existing completed dataset build. The new rows are deduplicated against the source build's rows. Identifiers and attributes are inherited from the source and cannot be overridden; `qualifiers` and `max_items` may be replaced, and an optional `prompt` adds a new instruction. Like [POST /datasets](#tag/datasets/post/datasets), this finds rows only (identifier columns). Inherited attributes are not researched; they are filled by `auto_run_enrichment: true` or a later [POST /enrich](#tag/enrich/post/enrich) with the new `dataset_id`. Returns a fresh dataset-build run (the source build is untouched). **Workflow:** Starts an async run that adds rows to an existing dataset. Poll `get_run`, then fetch with `get_run_result`.

extend_dataset

get extraction The extraction's status and definition. `status` is `discovering` while the agent builds the plan, then `ready` (or `discovery_failed`). Once `ready`, execute with [POST /extractions/{id}/runs](#tag/extractions/post/extractions/{id}/runs).

get_extraction