Recommend logo
Agent Studio

Where your AI agents do commercial work

Bring the agents you already have. They read what's true in your business, act on it, and report what every action earned.

Connects to your stack
ShopifySalesforceGoogle TrendsMetaTikTokGA4AmazonStripePricing / ERPCRMEditorial feeds
How to use agents

One connection. Real work. Proven results.

01 · Key

Get a key

Create a key in the dashboard. That's the only setup there is.

shell
# create a key in the dashboard, then:
export RECOMMEND_API_KEY=rcmd_live_...
02 · Connect

Connect your agents

One connection and your agents find the tools themselves — reading the same live picture your team works from.

mcp.json
{
  "mcpServers": {
    "recommend": {
      "url": "https://mcp.recommend.co",
      "apiKey": "rcmd_..."
    }
  }
}
03 · Work

The agent makes the move

It reads what's true, takes the action, and every result is logged — so its next move is better than the last.

your agent · mcp
get_context({ object: "sku:4812", market: "DE" })
→ { "demand": 78, "move": "push_in_DE" }

act({ move: "push_in_DE" })
→ brief drafted · budget +15% · meta live
Tools

What your agents can call

get_context()mcp · rest

The live state of any object — demand, stock, price position, competitors, and the move that's ready.

act()mcp · rest

Execute the ready move: draft the brief, shift the budget, launch the campaign.

query()mcp · rest

Ask in natural language and get grounded, current numbers back.

watchlist()mcp · rest

Every object your team follows — your agents read the same truth.

outcomes()mcp · rest

Settled results — what each action earned, and what it taught the system.

calibration()mcp · rest

The track record behind every score.

Turn your data into actions.

Book a demo and see it run on your business.