Agent feed

A public, read-only API for AI shopping agents. Also available in machine-readable form at angadilabs.com/llms.txt.

Angadi is a Shopify app fashion brands use to curate “Complete the Look” outfit recommendations. Every pairing is approved by the brand before it goes live on their storefront. This feed exposes the same approved pairings to AI shopping agents, so an agent answering “what goes with this kurta?” can use the brand's own styling instead of guessing.

Endpoint

GET https://angadi-complete-the-look.vercel.app/agent/v1/looks

Parameter	Required	Description
`shop`	Yes	The store's myshopify domain, e.g. `example.myshopify.com`
`handle`	One of these two	The anchor product's Shopify handle
`product_id`	One of these two	The anchor product's numeric Shopify ID

Response

JSON. looks lists the brand-approved outfits that are currently live for the anchor product. Each look carries a stable look_id, a type (complete-the-look is a full curated outfit, style-it-with is a set of pairing options), and a pieces array. Pieces use schema.org-compatible fields: name, url, image, price, priceCurrency (ISO-4217, omitted when unknown), and availability. Out-of-stock or unpublished products are omitted entirely, matching the brand's storefront widget, so every returned piece is https://schema.org/InStock as best known from catalog data.

Example

GET https://angadi-complete-the-look.vercel.app/agent/v1/looks?shop=example.myshopify.com&handle=block-print-kurta

{
  "version": "v1",
  "shop": "example.myshopify.com",
  "anchor": {
    "product_id": "gid://shopify/Product/1111",
    "handle": "block-print-kurta",
    "name": "Block Print Kurta",
    "url": "https://example.myshopify.com/products/block-print-kurta"
  },
  "look_count": 1,
  "looks": [
    {
      "look_id": "a1b2c3d4-...",
      "type": "complete-the-look",
      "pieces": [
        {
          "product_id": "gid://shopify/Product/2222",
          "name": "Palazzo Pants",
          "url": "https://example.myshopify.com/products/palazzo-pants?ref=angadi_ctlw&look_id=a1b2c3d4-...&source_product=gid%3A%2F%2Fshopify%2FProduct%2F1111&surface=agent_feed",
          "image": "https://cdn.shopify.com/.../palazzo.jpg",
          "price": "2099.00",
          "priceCurrency": "INR",
          "availability": "https://schema.org/InStock"
        }
      ]
    }
  ]
}

Good citizenship

Responses are CDN-cached for 5-10 minutes; requests are rate-limited per IP. Cache on your side where you can.
Follow product URLs as-is (including query parameters) so brands can see agent-driven engagement in their analytics.
The feed is opt-in and off by default — each brand enables it from their Angadi settings, and can turn it off at any time. Shops that haven't enabled it (and unknown shops) return a minimal HTTP 404. An unresolvable handle or product ID returns 404 product_not_found. An empty looks array (HTTP 200) means the product exists but has no approved pairings right now.

Contact

Questions or higher-volume access: hello@angadilabs.com.