---
title: "Data-grounded starting points for the create screen"
method: GET
path: "/dashboards/v3/suggestions"
tags: ["Dashboard v3"]
---

# Data-grounded starting points for the create screen

`GET /dashboards/v3/suggestions`

## Request

- Base URL: `https://app.mammoth.io/api/v2`
- URL: `https://app.mammoth.io/api/v2/dashboards/v3/suggestions`
- Auth: one of:
  - HTTP bearer
  - API key in header `X-API-KEY` and API key in header `X-API-SECRET` and API key in header `X-WORKSPACE-ID`

Per-format {format, title, intent} suggestion cards, job-shaped like the legacy dashboard-suggestions flow: submits SUGGEST_DASHBOARD_V3 and returns {job_id}; the client polls /jobs/{id} and the resolved future carries {suggestions}. The task serves the cached model set when warm (per (dataview, data_version), beside the profile cache) and otherwise runs one grounded model pass — a cold cache waits on the model rather than serving the deterministic shape-archetype set, which is a post-failure degrade only. Auth: the v3 workspace gate + the dataview ACL. ``table_item_id`` is optional — the task resolves the dataview's latest data item when omitted.

## Query parameters

- `dataview_id` integer, required
- `table_item_id` integer, nullable

## Response `200`

Request fulfilled, document follows

- ObjectJobSchema
  - `status_code` integer, nullable
  - `job_id` integer, nullable: Created job id
  - `failure_reason` string, nullable: Failure reason if status is failure

## Other responses

- `202`: Successfully Submitted
- `400`: Bad request syntax or unsupported method
- `403`: Request forbidden -- authorization will not help

---

[API](https://skmtc.dev/mammoth/apis/mammoth-analytics.md) · [All operations](https://skmtc.dev/mammoth/apis/mammoth-analytics/llms.txt) · [OpenAPI document](https://skmtc.dev/mammoth/apis/mammoth-analytics/revisions/fe078afe239b?raw)