The hub where your reporting builds itself
Your numbers assembled from the tools you already run, reports written on schedule, exceptions flagged.
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.
- 01
Connections
The hub reads from the tools you already run. Nothing gets re-keyed.
- 02
Metric assembly
Numbers collected, reconciled and stored in one place on a schedule.
- 03
Report generation
Investor updates, client briefs and board packs assembled automatically. The numbers come from systems. The narrative is drafted around verified figures.
- 04
Approvals
Requests that track themselves: asked once, visible until a person answers, escalated when stuck.
A person acts here
- 05
Owner dashboard
The glance view. Every number that matters, current, in one screen.
- 06
Exception alerts
When a metric moves outside its range, Slack tells you the day it happens, not the month after.
02What it does
Four jobs it takes on.
Investor updates
The monthly update drafted around figures your systems supplied, ready for review.
Board packs
Board reporting assembled on schedule instead of eating the week before the meeting.
Ask your numbers
Plain questions answered from one reconciled store, not a hunt across logins.
Anomaly scan
A metric that moves outside its range flags a human the day it happens.
What it replaces
Your numbers live in five tools.
Revenue in one place, hours in another, pipeline in a third. The truth requires four logins and an afternoon.
Reporting eats Fridays.
Investor updates, client briefs, board packs. Senior hours spent formatting, not thinking.
Approvals die in Slack.
Asked, lost, re-asked. The thread scrolled away and the invoice sat for a week.
The owner has no glance view.
You find out a metric slipped when somebody mentions it. A month late.
The process lives in one person's head.
When they're out, things stop. When they leave, things break.
03Proof
Where it runs.
Advizr
Our own systemTen operating surfaces, from the P&L to workflow run history, read from one database.
Read the story10operating surfaces in one dashboardBuild artefactHungerford
DeliveredThe client-facing version of an operations build: five surfaces on one database.
Read the story5systems in one buildBuild artefact
04What is included
In the build.
- Connections to your existing tools and one reconciled data store
- Report templates for the documents you actually send
- Owner dashboard plus exception alerting
- Training, monitoring and quarterly iteration, 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 SOPs, historical reports and the reasoning behind past decisions are indexed, so a number in a report can be traced to how it was defined rather than re-litigated every month.
- pgvector
- Full-text BM25
- Definition registry
Agents and orchestration
Collection and assembly run on scheduled workers, every run logged and re-runnable. Exceptions raise an alert with the underlying rows attached, not just a red number.
- agent-worker
- Scheduled workers
- Run history
Evaluation
Reconciliation is checked against periods your team has already closed by hand. A report that is plausible and wrong is more dangerous than one that is obviously broken.
- Eval graders
- Reconciliation checks
- quality-worker
Models
Frontier models write the narrative around figures the systems supply, never the figures themselves. Forecasting and anomaly detection are ordinary statistical models with an auditable method.
- Frontier models through one gateway
- Statistical forecasting
- Anomaly detection
Data boundary
One reconciled store in your own database, one part of the isolated infrastructure each client gets. Finance data does not become a shared dataset, and it does not train a model unless your team turns that on.
- Supabase row-level security
- Role-based access
- Training off without your consent
Named tools in this buildSupabase, Scheduled workers, Slack, Integration catalog
06How we build it
In this order.
- 01
Reconcile before you report.
One store, one definition per metric, agreed in writing. Reporting on top of numbers two teams define differently produces confident nonsense.
- 02
Automate assembly, keep the definitions human.
Collection and narrative assembly run on a schedule. The model writes around figures the systems supply and never invents one.
- 03
Add exceptions once the baseline is trusted.
Alerting comes last, because an alert on a number nobody trusts gets muted in a week.
What we will not automate
Defining a metric for you, and writing any figure the underlying systems did not produce. The narrative is generated, the numbers are not.
07Questions
Straight answers.
Does this replace our existing tools?
No. It sits on top of them and assembles the truth they each hold a piece of. We only replace a tool when the tool itself is the problem.
Where does the dashboard live?
In your own database, on the isolated infrastructure each client gets: its own repository, database and deployment. It reads the tools you already run, and nothing is pooled with another client.
What happens when a connected tool changes its API?
That is what the post-deployment phase is for: monitoring, fixes and iteration, all inside the monthly partnership.
How accurate are AI-written reports?
The numbers never come from the model. They come from your systems, reconciled in the store. The model drafts the narrative around figures that are already verified, and a human approves before anything external ships.
Can it do our investor updates?
Yes. That is the most common first build. See the private equity and real estate pages for how it lands in each.
Built alongside it
Client onboarding
New clients go from signed to started without a single chase email.
Workflows
Explain a process once, and it runs from then on.
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.