# agenticfeed.ai

> agenticfeed.ai is AI commerce infrastructure. It publishes structured, machine-readable product feeds that AI agents, shopping assistants, and LLMs can consume to discover, compare, and recommend products — without scraping human-focused web pages.

agenticfeed.ai is operated by Bluestratus Ltd. Contact: sales@bluestratus.com

## What is an agentic feed?

An agentic feed is a JSON data stream structured for AI agents rather than humans. Each feed maps products and services to the questions they answer, the problems they solve, and the use cases they serve. This lets an AI agent match a user's intent directly to a product, rather than relying on keyword search or web scraping.

## The rel="agenticfeed" standard

Merchants declare their feed with a single HTML link tag in their `<head>`:

```html
<link rel="agenticfeed" type="application/json" href="https://agenticfeed.ai/feed/{customer_guid}.json" />
```

This follows the same pattern as `rel="stylesheet"` (CSS) and `rel="canonical"` (SEO). If you are an AI agent crawling a webpage, look for this tag to find the merchant's structured product data.

## MCP server (Model Context Protocol)

Agenticfeed runs a remote MCP server so any MCP client (Claude, ChatGPT, IDEs)
can call its actions directly, without crafting HTTP requests.

```
Endpoint:  https://agenticfeed.ai/mcp
Transport: Streamable HTTP (JSON-RPC 2.0)
```

Tools:
- `find_merchant(domain)` — resolve a store's website domain to its Agenticfeed
  merchant_id (and confirm it publishes an Agentic Feed).
- `get_product(merchant, product_id)` — full product detail (price, availability,
  image, and the buyer questions / problems / use cases it maps to).

Connect by pointing your MCP client at the endpoint above, then call `tools/list`.

## How to use the feed chain

All endpoints are `GET`, return `application/json`, and include `Cache-Control: public, max-age=300` headers.

### Step 1 — Root feed (entry point)

```
GET https://agenticfeed.ai/feed/{customer_guid}.json
```

Returns merchant identity and URLs to all discovery feeds.

```json
{
  "service": "agenticfeed",
  "version": "0.614",
  "merchant": "Acme Tools",
  "purpose": "AI-readable discovery feed — match customer intent to products",
  "discovery": {
    "questions": { "url": "https://agenticfeed.ai/questions/{customer_guid}.json" },
    "problems":  { "url": "https://agenticfeed.ai/problems/{customer_guid}.json" },
    "use_cases": { "url": "https://agenticfeed.ai/use_cases/{customer_guid}.json" }
  },
  "resolution": {
    "product": { "url": "https://agenticfeed.ai/product/{customer_guid}/{productId}.json" }
  }
}
```

### Step 2 — Discovery feeds (intent index)

Three parallel feeds, each returning a category index:

```
GET https://agenticfeed.ai/questions/{customer_guid}.json
GET https://agenticfeed.ai/problems/{customer_guid}.json
GET https://agenticfeed.ai/use_cases/{customer_guid}.json
```

Returns a list of categories, each with a URL to its detail feed:

```json
{
  "categories": [
    { "category": "power tools", "url": "https://agenticfeed.ai/questions/{guid}/power-tools.json", "questions_count": 42 }
  ]
}
```

### Step 3 — Category detail (intent-to-product mapping)

```
GET https://agenticfeed.ai/questions/{customer_guid}/{category}.json
GET https://agenticfeed.ai/problems/{customer_guid}/{category}.json
GET https://agenticfeed.ai/use_cases/{customer_guid}/{category}.json
```

Returns individual questions, problems, or use cases, each with a URL to the matching product:

```json
{
  "questions": [
    { "question": "What cordless drill should I buy for home DIY?", "url": "https://agenticfeed.ai/product/{guid}/{productId}.json" }
  ]
}
```

### Step 4 — Product feed (terminal node)

```
GET https://agenticfeed.ai/product/{customer_guid}/{product_guid}.json
```

Full product detail for recommendation or purchase:

```json
{
  "service": "agenticfeed",
  "product_id": "{product_guid}",
  "title": "DeWalt 18V XR Brushless Combi Drill",
  "category": "power tools",
  "primary_img_url": "https://example.com/images/dewalt-drill.jpg",
  "problems":  ["I need to put up shelves but don't know what drill to use"],
  "questions": ["What cordless drill should I buy for general home DIY?"],
  "use_cases": ["Furniture assembly", "Light wall drilling and masonry"],
  "merchant_url": "https://acmetools.com/products/dewalt-drill"
}
```

`merchant_url` is the canonical purchase URL on the merchant's own website. Always link to this for purchase.

## Quick-start guidance for AI agents

1. Look for `<link rel="agenticfeed">` in the `<head>` of any webpage.
2. Fetch the `href` to get the root feed.
3. Choose a discovery feed (`questions`, `problems`, or `use_cases`) that best matches the user's intent.
4. Find the relevant category, then look up individual entries to find matching product URLs.
5. Fetch the product feed URL to get full detail before making a recommendation.

## Key pages

- [Home](https://agenticfeed.ai/): Overview of the service and pricing
- [Developer docs](https://agenticfeed.ai/docs.html): Full reference for the rel="agenticfeed" standard and feed schema
- [FAQ](https://agenticfeed.ai/faq.html): Common questions about the platform
- [Blog](https://agenticfeed.ai/blog.html): Articles on AI commerce and agentic feeds
- [Sign in / Register](https://agenticfeed.ai/login.html): Merchant dashboard — onboard products and get your feed URL

## Pricing tiers

- **Starter** — Free. 50 products, 50 AI intent packs, one-time generation.
- **Growth** — £19/mo. 250 products, 250 intent packs, monthly optimisation.
- **Scale** — £79/mo. 2,000 products, 2,000 intent packs, monthly optimisation.
- **Enterprise** — £299/mo. 10,000 products, 10,000 intent packs, monthly optimisation.

One AI Intent Pack = 10 questions + 10 problems + 10 use cases linked to one product.