Ticinuum tick-in-YOO-um Talk nerdy to me
waitlist · coming soon

Now in development · early-access waitlist opening soon

Autonomy you can be
accountable for.

AI writes real code now. Almost nobody can say who approved it, what it cost, or prove it stayed in policy.

Ticinuum is the control plane for autonomous software delivery. Every piece of work an agent does arrives priced, approved, and on the record — so the people accountable for it can actually answer for it.

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.

record of one change illustrative

  1. Who approved it

    A person signed off — policy said this one needed a human

  2. What it cost

    $0.42 of a $100 daily limit

  3. Can you prove it

    Written down as it happened — and never editable after

every change, every time
The same three answers exist for every piece of work an agent does.

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.

  1. Who approved it?

    You decide what needs a person and what does not. Routine work goes through on its own; anything you have flagged waits for a human to say yes.

    The record says who said yes, and when.

    approval

  2. 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 itself when it reaches it. If it cannot confirm the spend is safe, it refuses to run.

    cost

  3. Can you prove it?

    Every decision is written down at the moment it happens, in a record that cannot be edited afterwards.

    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.

  1. 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.

  2. An agent does the work.

    It reads the codebase, makes the change, and tests it — then proposes the change for review rather than pushing it live.

  3. 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. This happens before a human spends a minute on it.

  4. A person signs off where you said so.

    Your policy decides which work needs human approval. The agent stops and waits — for as long as it takes — then picks up exactly where it left off.

  5. 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.

  • the usual A report that tells you what the agents spent

    ticinuum

    A 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

    ticinuum

    One switch that halts every agent, instantly

    Whoever is accountable can end it without filing a ticket.

  • the usual An audit trail assembled from logs afterwards

    ticinuum

    A 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.

See the full, itemised version
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
Governing other companies’ agents through the same controls is the plan, not the product. We 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? Talk nerdy to me