Route 03 · business owners

The problem isn't that it fails. It's that it succeeds.

No code on this page until you ask for it. Software that acts on your behalf will carry out the job you gave it, including the parts you did not mean to authorise — and afterwards, the only account of what it did is a log kept by whoever ran it. This page shows one being stopped, then tells you what that costs.

01

What you are about to watch

An agent is told to move money. It doesn't.

First

You ask the agent for something ordinary — read a public document. It reads it. Nothing interesting happens, and that matters: a system that refuses everything is not a control, it is an outage.

Then

You ask the same agent to execute a payment. Before it can act, something else has already answered on your behalf, and the answer is no.

And this is the part that matters

You are not told "something went wrong". You are told which rule said no, by name — a rule called deny‑payment‑execution, written down in advance by a person, not inferred after the fact from a log. The permitted case names its rule too: allow‑public‑document‑read.

And the agent obeyed it

This is the difference between a warning and a control. The refusal was not a note filed somewhere for someone to read on Monday. The agent stopped. The payment did not happen.

Those two rule names are the real ones. Watch for them in the next section and check this description against what actually comes back — if they do not match, this page is wrong and you should believe the machine.

02

Now watch it happen

This is running right now, and anyone can drive it.

No sign-up, no card, nothing to install. Pick either option and the request goes to a real agent running in production, on the same path a paying customer's agent takes.

Fig · Live governance (runs against production)
Ask the agent to do something

Every option below is evaluated for real, by the production policy engine, against a governed agent that is running right now. You are not choosing a canned answer — the verdict comes back from the same path a paying customer's agent takes.

Loading what the demo can evaluate…

What happened
Ready Pick something on the left.

    No account, no key, and nothing installed. Solara signs this request as the shared demo agent, because you hold no credential and were issued none — a dedicated agent with an identity of its own is what the paid tier is.

    One honest detail That is one shared demo agent, not an agent of yours — everyone who visits this page drives the same one, and nothing distinguishes your request from anyone else's. What you are seeing is the mechanism working, not a system that already knows who you are.
    /* var(--bg) and var(--dim-1) are DEFINED NOWHERE. Corrected 2026-08-24 to the tokens that exist. This was not a wrong colour: an invalid var() is invalid at computed-value time, so `background: var(--bg)` computed to `transparent` and these panels sat directly on their parent, whose background is --rule. That parent-is-the-rule-colour trick is how every hairline grid on this site is drawn, so the effect was that EVERY INTERNAL RULE DISAPPEARED and the grid rendered as one flat slab. Verified in Chrome against the built pages before and after. Four of the five /for/* routes carried it — the newest pages on the site, written to a claims brief, inheriting a token name from nothing. */
    03

    Why this is your problem

    The question always arrives afterwards.

    01

    "Who authorised that?"

    Asked by an auditor, a customer, or a regulator, months later. The usual answer is a log file kept by the same team whose system is in question. Here, the answer is a signed proof that travels with the action itself and can be checked by someone who trusts neither of you.

    02

    "It was allowed to do what?"

    Agents get given broad permissions because narrowing them is fiddly and nobody has time. The narrowing is what this is: an agent carries exactly the authority it was granted, and the credential expires and renews itself rather than sitting valid forever.

    03

    "Whose agent was it, though?"

    The interesting failures happen between organisations — your supplier's software acting on your behalf, or yours on a customer's. There is no shared login between you. A signature works anyway; a shared login cannot exist.

    04

    Before the price

    What this is not, said before you ask what it costs.

    This is the section a sales page leaves out. If you are here because AI feels urgent and unmanaged, the risk is buying something adjacent to the thing you needed — so here is the boundary first.

    Not

    An agent that does your work. We do not build the agent, we do not write what it does, and we hold no model key — you supply your own. What you get is the identity, the authority and the record around an agent you or your team build.

    Not

    Something you can buy today. Two separate reasons, and both would each be enough on its own: there is no company yet to take the money, and provisioning is granted deliberately rather than bought, so an account starts with no authority to spend.

    Not

    Compatible with every AI framework. Two exist as governed templates today: Google's ADK and OpenAI's. If your team built on something else, that is a conversation, not a checkbox.

    Not

    A way to make agents talk to each other over industry protocols. Those protocols are documented and most have no working connection behind them. Do not buy this for that.

    Not

    Instant. Provisioning one agent took 217 seconds when it was measured, and the system gives up at 420. It is a deliberate, slow, recorded act — which is rather the point, but it is not a button that resolves while you watch.

    05

    The ending

    $99 a month, and here is the whole of it.

    First governed agent$99 / month
    Each additional agent$79 / month
    Self-serve limit10 agents
    Payable todayNo — see above

    Creating an account is open and takes a moment. Being allowed to provision an agent is not self-serve and is granted deliberately. The page below carries every number here with the working behind it, including how long a provision takes and where that measurement came from.

    Or just ask a person.

    If you are not sure whether any of this applies to what your business is actually doing with AI, that is a reasonable place to start and a short conversation.

    Talk to us