ShopifyShopifyKlaviyoKanalInflateTrendtrackInfinite FulfillmentAddingwellBoostEcom AgencyThe DeployerStork MarketingTheme Copilot AIPandectesTheme FullStackCookiebotTriple WhaleRechargeIntelligemsHotjarDatafastTrustMRRPageBuilder.storeTaap.itShopifyShopifyKlaviyoKanalInflateTrendtrackInfinite FulfillmentAddingwellBoostEcom AgencyThe DeployerStork MarketingTheme Copilot AIPandectesTheme FullStackCookiebotTriple WhaleRechargeIntelligemsHotjarDatafastTrustMRRPageBuilder.storeTaap.it
ShopifyShopifyKlaviyoKanalInflateTrendtrackInfinite FulfillmentAddingwellBoostEcom AgencyThe DeployerStork MarketingTheme Copilot AIPandectesTheme FullStackCookiebotTriple WhaleRechargeIntelligemsHotjarDatafastTrustMRRPageBuilder.storeTaap.itShopifyShopifyKlaviyoKanalInflateTrendtrackInfinite FulfillmentAddingwellBoostEcom AgencyThe DeployerStork MarketingTheme Copilot AIPandectesTheme FullStackCookiebotTriple WhaleRechargeIntelligemsHotjarDatafastTrustMRRPageBuilder.storeTaap.it
Loading session…

Founding cohort pricing is open: Pro at today's price, locked while you stay. Limited seats. See the offer

Shopify merchandising

@Marco keeps your catalogue and prices right.

He creates products and variants, reworks collections and product pages, and prices bundles with the margin impact beside each change. Store changes wait for your review.

  • 6 agents, one team
  • 9 tools, 7 read-only
  • Level 1 by default: Propose
  • Every action waits for your approval
Put @Marco to workSee the team
@Marco, Shopify merchandising@Marcov0.0.1
Scenarios

Real asks, replayed from our evals

Each card replays a case from the evals we run against the model every week. The ask and its numbers come from the fixture, and nothing was written to a store.

  • Scenario 1Simulated
    I want to restructure the collection pages and re-price the winter bundle.
    @AtlasCollection pages and pricing are @Marco's, so I am handing him both parts of the ask. Want him to start with the winter bundle?
  • Scenario 2Simulated
    For the spring campaign I need 40 product variants created with new size options.
    @AtlasIt says campaign, but creating variants is a catalogue change: this goes to @Marco, not @Maya. Want the 40 variants drafted for your review first?
Profile

Name the product. I price it and place it.

@Marco owns what you sell and how it is shown: products, variants, collections, tags and metafields, prices and bundles, stock readiness, and the theme sections that present them. He answers with the Shopify Admin operation to run, never proposes a price change without its margin impact beside it, and hands ad copy and campaigns to @Maya.

Put @Marco to workSee the team

@Marco

Shopify merchandising

“Every product earns its shelf.”
Moves
  • Conversion rate
  • AOV
  • Gross margin
Capabilities

What @Marco owns, reads and calls

9 tools, 7 of them read-only, as classified by the permission matrix that checks every call before it runs.

Work

  • Creates and edits products, variants, collections and metafields.
  • Prices and bundles with the margin impact beside each change.
  • Checks inventory and fulfilment readiness before a launch.
  • Lays out product pages, collection grids and theme sections.

Data

  • Your Shopify catalogue, prices, settings and theme.
  • Competitors' catalogues and similar stores.

Access

  • shopifyAdminGraphQLDestructive
  • listThemeAssetsRead-only
  • runFullStoreAuditRead-only
  • getStoreSettingsRead-only
  • updateStoreSettingsSafe write
  • searchStoreIntelligenceRead-only
  • listKnownStoresRead-only
  • getCompetitorCatalogRead-only
  • searchSimilarStoresRead-only

Autonomy

You decide how far @Marco goes

@Marco starts at level 1. An owner or admin of your organisation changes it per agent, and it applies to that organisation only.

Levels
Autonomy · L1 Proposedefault

  1. ProposeLevel 1Default

    The agent reads, analyses, and suggests. Every action, even safe ones, requires your explicit approval before it runs.

  2. ApprovedLevel 2

    The agent executes safe, whitelisted actions on its own. Destructive, external, or high-spend calls still wait for your approval.

  3. AutonomousLevel 3

    The agent runs the playbook end-to-end. Only critical operations (publishing live, going past the spend cap) prompt for approval.

  4. Autonomous businessLevel 4Roadmap

    The business runs itself inside the goals you set. This is the third phase of the roadmap, not a setting you can pick today.

Limits

  • Does not run ads or write campaigns: that is @Maya.

  • Does not touch integrations or webhooks: that is @Otis.

  • Never proposes a price change without showing its margin impact.

The team

@Marco works in a team of 6

You write to @Atlas, who hands each part of your ask to the agent who owns it. Open a profile to see what each one does and will not do.

  • @Atlas

    Shopify AI orchestrator

    “You set the direction. I run the room.”
    Moves
    • Revenue
    • LTV
    • Profit
    Open @Atlas's profile

  • @Maya

    Shopify marketing

    “Lowest CAC. Highest signal.”
    Moves
    • CAC
    • ROAS
    • LTV
    Open @Maya's profile

  • @Otis

    Shopify operations

    “Nothing breaks in silence.”
    Moves
    • Time to live
    • Integration incidents
    • Automated steps
    Open @Otis's profile

  • @Faye

    Shopify store intelligence

    “Numbers lie. Patterns don't.”
    Moves
    • Insight accuracy
    • Detection speed
    • Decision impact
    Open @Faye's profile

  • @Sam

    Shopify customer support

    “Loyal buyers compound.”
    Moves
    • Customer satisfaction
    • Response time
    • Resolution rate
    Open @Sam's profile
Can @Marco change my store without asking me?Autonomy
Only inside the level you set. @Marco starts at level 1 (Propose). The agent reads, analyses, and suggests. Every action, even safe ones, requires your explicit approval before it runs.
How do I talk to @Marco?Team
Through @Atlas, in the chat on your store. She hands @Marco the part of your ask in that domain and brings the answer back in the same thread.
Can I change @Marco's autonomy level?Autonomy
Yes, per agent. An owner or admin of your organisation sets it, and the level applies to that organisation only.
Is there a level above 3?Autonomy
Only on the roadmap. A business that runs itself inside your goals is the third phase of the roadmap, not a setting: today you choose between levels 1 and 3.
What does it cost to use @Marco?Billing
Credits from your plan. Every turn draws on the same balance whichever agent answers, and a turn estimated above your balance is refused before it starts.
Why do the scenario cards say Simulated?Scenarios
Because nothing ran on a store. Each card replays a case from our weekly evals: the ask and its numbers come from the fixture, never from anyone's store.

Put @Marco to work on your store

Describe the job in your own words. @Atlas decides who takes it.