AI governance for coding agents · now in development
Autonomy you can be
accountable for.
The hard part isn't getting an agent to write code. It's the control around it — cost, approval, audit, safety — that makes autonomy something you can actually run.
Today you're stuck between a passive record system and an ungoverned coder. Ticinuum is the control plane in between: every piece of agent work arrives priced, approved, and on the record.
coming soon
Early access opens once the waitlist terms and privacy notice are final. Nothing to sign up for yet — this page collects no email.
tick-in-YOO-um · TIC(ket) + cont(INUUM) — The Continuum of Work.
-
Who approved it
A person signed off — policy said this one needed a human
-
What it cost
$0.42 of a $100 daily limit
-
Can you prove it
Written down as it happened — and never editable after
The cost problem
Tokenmaxxing isn't a strategy.
AI spend is climbing fast, and at scale more tokens don't mean more shipped. The teams that come out ahead treat tokens like any scarce resource: priced per piece of work, budgeted, and spent on purpose.
“Token economics is the unit-economic vocabulary of the AI era.”
- One bill a month, by vendor A price on every piece of work
- Spend first, explain later No build starts until someone says go
- Bigger models and longer loops, by default Loops that stop paying when they stop helping
That takes a control plane, not another dashboard.
The three questions
Three questions your board will ask.
Not eventually. The first time an AI-written change causes an incident, shows up on an invoice, or lands in front of an auditor.
-
Who approved it?
You decide what needs a person. Agents do the routine work on their own, but by default a person gives the final yes before any change is accepted.
Letting agents take that last step alone is a separate choice, made on the record. Either way, the record says who said yes, and when.
approval -
What did it cost?
Every piece of work carries its own price in real dollars — not a monthly invoice you take apart later.
Set a daily limit and the system stops starting new work the moment it is reached — and every single job has a ceiling of its own. If it cannot confirm the spend is safe, it refuses to run.
cost -
Can you prove it?
Every decision is written down at the moment it happens, in an append-only record where any change made afterwards would show.
When a regulator, an auditor, or your board asks what your AI did and who let it, the answer already exists.
evidence
How it works
Five steps. Every one of them on the record.
This is the whole loop. It runs today, end to end, with our own agent inside it.
-
The work is written down.
A request becomes a structured brief — specific enough that a machine can act on it and a person can audit it. Writing it down does not start the build.
-
Someone says go. An agent does the work.
A person presses Run, or a rule your organization chose starts it. The agent reads the codebase, makes the change, and tests it — then proposes the change for review rather than pushing it live.
-
A second agent checks the first.
A fresh reviewer that never saw the first one work goes over the change and sends it back if it is wrong. When a round stops making progress, it stops and asks a person instead of paying for another. Nothing is merged until your automated checks pass.
-
A person gives the final yes.
By default no change an agent makes is accepted until a person says yes. Your policy can ask for sign-offs earlier, or let routine work finish on its own — a choice that is itself on the record. Silence is never taken as a yes.
-
It goes on the record.
What changed, who approved it, what it cost, and every decision along the way — written as it happened, kept for whoever asks next.
Nothing in that list is a plan. It is what the product does now.
Why it is different
Everyone else measures agents.
We govern them.
Measurement tells you what already happened. Ticinuum sits in the path and decides what is allowed to happen next. That's AI governance, not AI reporting.
-
the usual A report that tells you what the agents spent
ticinuumA limit that stops them spending it
A number arriving after the money is gone is not a control.
-
the usual A dashboard you check when something feels wrong
ticinuumOne switch that stops all new agent work, instantly
Whoever is accountable can pull it without filing a ticket — and cancel a job already running within seconds.
-
the usual An audit trail assembled from logs afterwards
ticinuumA record written at the moment of the decision
It cannot drift from what actually happened, because it is not a copy.
Cursor and Devin write the code. Ticinuum governs the work.
Straight answers
We would rather under-promise.
Most of this market sells the demo and fences the details in a footnote. Here is the line, in the same size type as everything else.
- What runs today
- The whole loop above, end to end, with our own agent inside it. It is a working system, not a prototype and not a slide.
- What is not built
- Putting other companies’ agents under the same spending limit, stop switch and approvals is the plan, not the product. Those controls govern our own agent today, and we will not imply otherwise.
- What we do not claim
- No security certifications — we have the evidence trail an audit asks for, which is not the same thing as holding a certificate, and we will not blur the two.
- Where we are
- Pre-launch. Nothing is for sale yet. We are looking for a handful of design partners who want a say in how the controls work.
Let the agents run.
Keep the receipts.
Early access opens to a small group of design partners soon.
coming soon
Early access opens once the waitlist terms and privacy notice are final. Nothing to sign up for yet — this page collects no email.
Want to check our work first? Tech Details