Advanced architecture
Agent API
An agent needs a document and a tool, not a secret account. This page shows agents.json, calls the read-only journey tools on /api/mcp after Accept, and puts an agent walk beside a human walk. Agent visits is a channel name, not a traffic report.
The tools answer with the public lab list. A real agent-visits channel in an analytics property is not connected.
Understanding the labHow to use it and why you'd want to
Why you'd want to
You want an agent to find the next lab without an account. Accept to call the read-only tools, and compare that walk with a click.
How to use it
- Read agents.json on the page.
- Accept, then press Call journey tools.
- Compare the agent steps with the human steps.
Loading the lab…
WalkthroughHow we built itShowHide
Example vendor setup is marked below. eVar and event numbers are examples. This lab does not call Adobe.
agentsDocument names the public MCP endpoint and the journey tools. journeyNext walks the advanced lab list. The human column is the same href as a click. No visit count is returned.
Publish a document, not a secret
agents.json lists the tool names and two channel ids. It has no key and no account.
Call the read-only tools
After Accept, the page POSTs tools/call for journey_catalog and journey_next to /api/mcp.
Show both walks
browseCompare returns three human steps and three agent steps for the same href.
From the code
The next lab is the next public path, wrapping at the end.
return list[(index + 1) % list.length] ?? nullThe MCP player moves the example and queues a tool name only after Accept.
if (granted && eventName) {
demonstrateEvent(eventName, tool ? { tool } : {})
}Google and Adobe
Google queues advanced_lab_view after Accept. Adobe is an example of the same fields.
After Accept, this lab queues advanced_lab_view. The demo payload stays on the page. This site does not call Adobe.
Simplified shape of the object queued after Accept.
dataLayer.push({
event: "advanced_lab_view",
lab_id: "agent-api",
})Example implementation. This site does not call Adobe. eVar165, prop165, and event165 are example variable numbers. In Launch, a data element reads the value and a rule sends it when the value changes. In the report suite, enable eVar165 with Most Recent allocation and expire it on the hit.
Example alloy payload. _example is a placeholder schema, not a real tenant.
alloy("sendEvent", {
xdm: {
eventType: "web.webinteraction.linkClicks",
_example: {
agentChannel: "agent",
},
},
})Example hit. eVar165 is hit-scoped in this example.
s.eVar165 = "agent"
s.prop165 = "agent"
s.events = "event165"
s.tl(true, "o", "advanced_lab_view")Translation
Each lab field, the GA4 name, and the example Adobe variable. Scope is the part that usually gets lost in the translation.
Lab id
GA4. Parameter lab_id on advanced_lab_view.
Adobe. Example eVar, expire on the hit.
Scope. Event. It names this lab, not the user.
Demo value
GA4. Not sent. Scores, proofs, and payloads stay on the page.
Adobe. Example prop. Do not copy the demo value.
Scope. Local state. It is not a user property.
Example counts
GA4. Not sent. Labeled example data is not a metric.
Adobe. Example event. Not sent.
Scope. A figure on the page, not a hit.
Consent
GA4. The view event is skipped until Accept.
Adobe. Example: skip the hit while consent is off.
Scope. A gate on the hit.
Recommended next
Why these picksReading path transitions…