Adeqo is the operating platform. ACE is the context.
One operating graph per account. Every workflow reads from it.
- Paid platformsAds · Meta · TikTok
- Analytics & searchGA4 · GSC · GTM
- CRM & commerceHubSpot · Shopify
- WarehouseBigQuery · Looker
- AI answer surfacesChatGPT · Perplexity
- Validations
- Recommendations
- Reports
- AI agents
Sources resolve into one graph. A launch gate, an anomaly check and a weekly report all resolve the same campaign to the same node.
Containment runs down. Attribution runs back up.
Every campaign in the graph names the market it runs in. The types above are the nodes. These are the edges: a creative, the landing page it points at, and the lead that page produced sit three hops apart.
01A campaign contains ad sets, an ad set contains creatives
That containment is the platforms’ own, and a keyword sits at the same depth as a creative.
02The budget hangs on the campaign
It splits by objective, 70/20/10 across prospecting, retargeting and brand, and pacing is read against the plan that split came from.
03A creative and a keyword point at a landing page
Both carry a destination URL, so one page can be the target of ad sets in several campaigns at once.
04A landing page emits a conversion event
The event belongs to the page that fired it, which is why a /quote thank-you firing GA4 and not Google Ads reads as one edge present on one side only.
05A conversion event joins a CRM record
The join runs through the source field the form wrote, so when HubSpot dropped paid social UTMs on /book and /quote, an estimated 11% of paid social leads were mis-attributed.
06A tracking check sits on the join it scores
Page to event, event to CRM record, platform to conversion import, domain to domain. The gate reads each as pass, warning or critical.
07A priority query is tested against every answer surface
Each query carries one result per surface per market, and a gap becomes a content or schema recommendation.
08A business priority orders the work
It ranks what the graph produces, so a list of open issues arrives as a recommendation queue and an entry in the AM brief.
A disagreement between two systems is a gap with an owner.
Google Ads, GA4, HubSpot and Shopify each report the same week differently, and each is right inside its own system. They already agree on which campaign they mean, because the blueprint standardized the account before a specialist touched a platform. What is left is a gap between counts, and these are the rules that decide what happens to it.
01The taxonomy decides which campaign
A record attaches to a campaign on the account’s naming and UTM schema. That schema is the join key, whatever each platform files the channel under.
02Commercial outcome outranks the platform’s count
When Meta’s reported conversions and the pipeline in Salesforce point different ways, the recommendation is written against pipeline, qualified leads and revenue.
03Measurement is questioned before performance
The anomaly workflow asks whether a movement is downstream of tracking before it asks whether it is downstream of the platform, which is how a 22% CAC rise resolves as a dedup fault.
04A threshold is a rule. The remedy is a recommendation.
CAPI dedup at 14% fails an 8% check by predicate, and what follows is a spend hold recommendation with a named owner that a person decides to take.
05A market can override the standard, and the override is signed
Per-market and per-vertical exceptions are approved and logged, and an override that opens a held launch gate requires AM sign-off.
Deterministic before generative.
A decision belongs to the rule engine when it can be written as a predicate over stored fields. Everything else is reasoned, and arrives as a proposal a person can accept or reject.
- Naming and taxonomy
- UTM schema
- Launch QA gates
- Tracking thresholds
- Approvals
- Cross-channel interpretation
- Anomaly explanation
- Recommendations
- Report narrative
- Workflow coordination
One agent, one workflow, one declared tool set.
The subgraph is the input list. The proposal is the output list.
Every workflow Adeqo runs publishes its trigger, inputs, checks, output, owner and escalation. An agent assigned to one runs inside those declarations, which makes both its read bound and its write bound something you can look up on the workflows page.
- The entities its workflow lists as inputs. For a tracking issue: GA4 events, GTM container state, CAPI delivery, CRM form data.
- The checks that workflow runs, and what each of them returned.
- The standard the record was supposed to meet.
- One account, because the graph is built per account.
- A typed proposal, held for the owner its workflow names.
- Only the outputs that workflow declares. For a tracking issue: a ticket draft, an owner assignment, an AM notification, a spend hold recommendation.
- An audit row: actor, timestamp, rule reference, outcome.
- An escalation at the line already published. Spend drift over 25% is a 24-hour hold and an AM call; a critical issue open past five business days escalates.
See what ACE would hold for your site.
The sample audit runs a subset of these checks and returns the result.