%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20url(%23linear-gradient2);%20}%20.st1%20{%20fill:%20url(%23linear-gradient1);%20}%20.st2%20{%20fill:%20url(%23linear-gradient3);%20}%20.st3%20{%20fill:%20url(%23linear-gradient);%20}%20%3c/style%3e%3clinearGradient%20id='linear-gradient'%20x1='128'%20y1='193.4'%20x2='233'%20y2='88.4'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20offset='0'%20stop-color='%233f2d86'/%3e%3cstop%20offset='.5'%20stop-color='%23a92b86'/%3e%3cstop%20offset='1'%20stop-color='%23e4215c'/%3e%3c/linearGradient%3e%3clinearGradient%20id='linear-gradient1'%20x1='283'%20y1='422.1'%20x2='388.9'%20y2='316.1'%20xlink:href='%23linear-gradient'/%3e%3clinearGradient%20id='linear-gradient2'%20x1='0'%20y1='256'%20x2='423.2'%20y2='256'%20xlink:href='%23linear-gradient'/%3e%3clinearGradient%20id='linear-gradient3'%20x1='88.8'%20y1='256'%20x2='512'%20y2='256'%20xlink:href='%23linear-gradient'/%3e%3c/defs%3e%3cpolygon%20class='st3'%20points='218.2%20219.3%20177.8%20144.8%20219%20144.8%20243.2%20189.5%20272.6%20154.5%20241.1%2096.4%20220.5%2096.4%20192.7%2096.4%20151.5%2096.4%20123.8%2096.4%20103.2%2096.4%20188.9%20254.3%20218.2%20219.3'/%3e%3cpolygon%20class='st1'%20points='297.1%20288.7%20339.7%20367.2%20298.5%20367.2%20272.1%20318.5%20242.7%20353.5%20276.4%20415.5%20297%20415.5%20324.8%20415.5%20366%20415.5%20393.8%20415.5%20414.4%20415.5%20326.5%20253.7%20297.1%20288.7'/%3e%3cpolygon%20class='st0'%20points='423.2%2032.6%20374.9%2032.6%200%20479.4%2048.4%20479.4%20423.2%2032.6'/%3e%3cpolygon%20class='st2'%20points='512%2032.6%20463.6%2032.6%2088.8%20479.4%20137.1%20479.4%20512%2032.6'/%3e%3c/svg%3e){kind=small}
One contract. One autonomous router. One global model that compounds.
XpertIntel is a neural intelligence framework: it predicts intent, optimises spend and acts on the result — across every venture, without shipping raw customer data anywhere it shouldn’t go.
The signal contract
Every venture posts events to a single, schema-validated table (xi_events). Required fields, optional fields, and consent flags are defined per venture and per vertical, so the same payload shape works for SaaS, ecommerce, and service businesses. Bad rows are rejected at the door — there is no silent loss.
Scoring & bands
Sessions are scored in milliseconds and bucketed into bands (cold / warm / hot). Scores travel with the event so the router and downstream platforms see the same number. The scoring model can be the lightweight LQS heuristic or, once a venture passes the FL outcome threshold, the federated model.
Server-side router
Accepted events fan out to the destinations you’ve wired — sGTM, Meta CAPI, Google Enhanced Conversions, custom webhooks. Every dispatch is HMAC-signed, consent-gated, and retried with exponential backoff. PII is hashed before it leaves the worker.
Federated learning
Each round, every consenting venture trains locally on its own outcomes and sends weights — never raw rows — to the Flower aggregator. The new global model is broadcast back. Every brand benefits from the portfolio without any brand sharing its data.
Proof Layer
Every uplift number is materialised as a signed, time-limited Proof artefact: a URL plus a PDF, with the underlying CAC baseline embedded. Forwardable to a board, revocable in a click, reproducible from the events that produced it.
See the framework run live.
Twenty minutes. We’ll show the neural pipeline predicting, the router dispatching autonomously into Google Ads Enhanced Conversions, and a real Proof artefact. No deck.