A content engine that publishes every week, in your voice
Drafting, repurposing and scheduling from your actual expertise. Humans approve everything.
Your custom strategy and systems, delivered in under a month. Your named people using them every week by day 30. Or we keep working for free until both are true.
Drawn from this system's own stages. A dashed ring marks a stage where a person acts.
01How it runs
Stage by stage.
Nothing publishes without a human approving it. Newsletters are built CASL-clean: consent tracked, unsubscribe honored.
- 01
Voice capture
Your real writing, calls and positioning distilled into a voice the system writes in. Not a style dropdown.
- 02
Topic pipeline
Topics sourced from your actual expertise: client conversations, internal docs, the questions you answer every week.
- 03
Drafting
Long-form drafts written in the captured voice, grounded in your material.
- 04
Repurposing
One piece becomes many: post to newsletter to social, each fitted to its channel.
- 05
Review queue
Nothing publishes without a human approving it. Your team edits in minutes instead of writing for hours.
A person acts here
- 06
Scheduling and distribution
Approved content ships on cadence, every week, without anyone remembering to do it.
02What it does
Four jobs it takes on.
Voice capture
Your real writing and calls distilled into a voice the system drafts in.
Weekly cadence
Approved content ships on schedule without anyone remembering to push it.
Repurposing
One strong piece becomes posts, newsletters and clips fitted to each channel.
Programmatic SEO pages
Pages built from your own material to answer the searches your buyers actually make.
What it replaces
Publishing is feast or famine.
Content goes out when someone has time. Someone never has time.
The founder is the bottleneck.
Every post waits on the one person whose calendar is already full.
Generic AI output embarrasses the brand.
You tried the tools. Everything came out sounding like everyone else.
Repurposing never happens.
The webinar was great. It became zero posts, zero clips, zero emails.
SEO rewards consistency you can't sustain.
Rankings need a cadence. Manual production can't hold one.
03Proof
Where it runs.
uQueue
LiveuQueue had its first province live 8 days after taking over its platform
Read the story9,381pages published from its own clinic dataBuild artefactby Advizr, 18 Oct 2026How this was measured
Pages in uqueue.ca's public sitemap on the day it was read, by kind of page. Anyone can count them again.
Measured at uQueue, the public sitemap of uqueue.ca
8 daysfrom platform handover to the first province liveSystem loggedby Advizr, 20 Aug 2026How this was measured
From the day the prior vendor's platform was handed over to the day the first province's live availability switched on, read from the merge dates.
Measured at uQueue clinic finder, after the takeover from its prior vendor
04What is included
In the build.
- Voice capture and a directive file your team can edit in plain text
- The full pipeline wired to your channels
- Review workflow your team actually uses
- Training, monitoring and iteration after launch, inside the monthly partnership
05How it is built
Five layers under every system.
The same five layers sit under all 14 systems. Here is each one in this system's own terms.
Retrieval
Your own published material, transcripts and positioning are indexed so drafts sound like you and cite your actual claims. This is the difference between content and generic filler.
- pgvector
- Full-text BM25
- Voice corpus
Agents and orchestration
Topic research, drafting, repurposing and scheduling run as stages in one graph you can open and change. Every stage leaves its output for review rather than passing silently downstream.
- agent-worker
- Workflow builder
- Proposal queue
Evaluation
Drafts are graded against pieces you have already published and stood behind, scored for voice as well as accuracy. Every factual claim is checked back to a source before publication.
- Eval graders
- Voice grading
- Claim checking
Models
Frontier models for drafting in the captured voice. Embedding models to keep the piece grounded in your material rather than in what the model remembers about your industry.
- Frontier models through one gateway
- Embedding models via the same gateway
- Grounding checks
Data boundary
Your material, positioning and unpublished drafts sit in your own database, one part of the isolated infrastructure each client gets. Training is off unless your team turns it on.
- Supabase row-level security
- Training off without your consent
- Draft isolation
Named tools in this buildWorkflow builder, Supabase, Vercel + Next.js
06How we build it
In this order.
- 01
Capture the voice before generating anything.
We index what you have already published and said. A model that has not read you writes like every other company in your category.
- 02
Draft against a graded standard.
Output is scored against pieces you stood behind, for voice and for factual accuracy, before the cadence starts.
- 03
Then hold a cadence.
Repurposing and scheduling run once quality holds. Publishing on a schedule is worthless if the drafts need a rewrite every time.
What we will not automate
Publishing without a person, and any factual claim that does not trace back to a source. We do not generate volume for its own sake.
07Questions
Straight answers.
Will Google penalize AI-assisted content?
Google ranks quality and originality, not the tool that helped produce it. Everything here is grounded in your real expertise and approved by a human before it publishes.
How do you keep it sounding like us?
Voice capture from your actual writing, plus a directive file your team can read and edit. When the voice drifts, you fix it in plain text, not in a vendor ticket.
Who approves what goes out?
You do. Every piece sits in a review queue until a human approves it. The system removes the blank page, not the judgment.
Does this cover newsletters under CASL?
Yes. Consent tracked per subscriber, sender identification, working unsubscribe. Built in, not bolted on.
What channels does it cover?
Blog, email and LinkedIn are the usual core. Channels are scoped per build, on the stack you already use.
Built alongside it
Outbound engine
Prospecting runs around the clock so your calendar fills itself.
Who to call next
The market ranked and refreshed while your team works the live deals.
Run your whole company on AI.
Tell us how your business runs. If we're not the right fit, we'll say so on the call.
Your custom strategy and systems, delivered in under a month. Your named people using them every week by day 30. Or we keep working for free until both are true.
The AI operating layer for enterprises.