TECHNOLOGY & PRODUCT STATUS

How Wexnex works
under the hood

A shared practice brief, one coordinated plan and eight specialist roles. Below is what works today, what is being built next, and our proposed Google Cloud architecture.

From a clinic goal to reviewed work.

Wexnex planned architectureA clinic goal enters the workspace. The approved practice brief feeds the manager and eight specialists. Provider adapters prepare work for human review. External publication and sending require separate authorization and are not enabled today.Clinic ownerGoal & approved factsWexnex WorkspaceShared practice briefAI Manager (Milo)Plan & task dependenciesSpecialist agentsEight bounded rolesProvider adaptersModels / voice / MapsHuman reviewEdit, check & approvePublish / sendFuture authorized executionShared approved facts feed the plan and drafts. Model orchestration and external execution are planned.
Target workflow. The current manager uses deterministic browser logic; live AI planning and external execution are still in development.

Built today. Building next.

The public site currently runs on Cloudflare Pages, Workers and D1. Google Places is the live Google API integration. The preview makes no live language-model requests.

What is built today and what is being built next
CapabilityStatusImplementation
Public clinic lookupLiveGoogle Places API through a server-side Cloudflare Worker; practice details, photos and Maps links.
Demo & contact requestsLiveCloudflare Worker + D1: validated requests, consent, reference IDs and rate limits.
Workspace, plans & workroomsPreviewStatic HTML / CSS / JavaScript. Local templates, guided setup, project dependencies and draft review.
AI planning & website/content generationIn developmentPrimary planned path: Google Gemini models via Vertex AI; no live model calls in the preview.
Authenticated Google / Meta connectionsIn developmentSetup flow preview only. Owner authorization, token storage and account scoping must be implemented.
Voice reception & bookingIn developmentOptional voice adapter plus an authorized phone and booking provider; no calls or bookings today.
Publishing, social posting & ad spendIn developmentFuture separate execution approval, provider permissions, budget limits and audit records.

PLANNED ARCHITECTURE ON GOOGLE CLOUD

Our Google Cloud plan

We intend to use Google Cloud for the first live generation workflow and an authenticated pilot backend. These services are proposed, except the existing Google Places integration. We do not claim Google Cloud program approval, a partnership or endorsement.

Planned

Gemini via Vertex AI

Planning and drafting from a confirmed brief. Start with one editable content draft, then evaluate quality, factual consistency, latency and cost.

Official documentation ↗
Planned

Cloud Run

A containerized backend for authenticated requests, orchestration and provider adapters. Keep each execution scoped to the practice and approved task.

Official documentation ↗
Planned

Firestore

Proposed storage for practice briefs, plans and approval records. Firestore is the initial design choice; final data model and region selection are pending.

Official documentation ↗
Planned

Cloud Storage

Planned storage for generated images, documents and media, with access controls and a defined retention policy.

Official documentation ↗
Live API use

Google Maps Platform

Google Places clinic discovery already works today. Public lookup runs through our existing Cloudflare backend, not a Cloud Run deployment.

Official documentation ↗
Planned

Secret Manager, IAM & Logging

Planned credential isolation, least-privilege service identities and observability with sensitive input redaction.

Official documentation ↗

The first milestone is a confirmed practice brief → Gemini content draft → human editing and approval. Credits would support development, quality evaluation and small pilot workloads before broader orchestration.

One task contract.
Replaceable providers.

Our planned adapters accept a scoped task and approved practice facts, then return a structured draft for review. Google Gemini is the primary model path. A provider can be replaced without changing the practice brief or approval flow. This adapter layer is a design direction; it is not yet a live multi-model runtime.

Google / Gemini architecture ↗

Review is part of the workflow.

Approved facts

Practice details are confirmed before drafting. The planned model workflow will identify missing facts instead of filling them with unsupported claims.

Separate execution

Draft approval records a review decision today. Publishing, spending, calls and booking are disabled and will need separate authorization when implemented.

Traceable decisions

The preview has a local activity feed. Authenticated audit records, access controls, recording consent and production retention rules are planned.

Responsible AI · Security · Google API use

See the workflow for your practice.

Start with a free clinic lookup or explore the public workspace.

Request a demo ↗