Simulation Mode: preview the AI, then trust it.

Pacvue, Perpetua, and Teikametrics all run trials. Fourteen days, thirty days, demo-required. Inside the trial window the seller is supposed to evaluate whether the tool deserves a credit-card commitment. In practice nobody evaluates an autonomous bidder properly in fourteen days — the data window is too short and the seller is too distracted — so the trial converts on momentum rather than evidence.

Mirox does not run that kind of trial. Simulation Mode is free for 30 days with no card on file, which is the part that matters: nothing converts, nothing charges, nothing renews. The AI reads your real account, makes real decisions, writes real traces, but nothing moves to Amazon. Thirty days is deliberately more than the fortnight a bidder cannot be judged in — and when it ends, the decision is one you make, not one that happens to you.

This is the third pillar of Mirox and the one that took the most argument to keep.

The trust-required problem

Every autonomous PPC tool faces the same chicken-and-egg shape. The product earns its value over weeks of real bidding. The seller has to authorise real bidding before any value accrues. So the seller is asked to trust on faith — and the tool is asked to perform with no margin to recover from the first bad week.

The category answer was the demo: a sales call, a sandbox account, screenshots of someone else's results. The demo is a poor proxy because the seller's own account is the only data set that matters. The category's second answer was the trial — but a trial is the same trust-required structure, just with a timer instead of a meeting.

Simulation Mode is the structural answer. The AI runs on the seller's real account, in read-only mode, for a month, with nothing on file to charge. The trust question becomes "do you trust the decisions you have already seen this AI make, written down, on your own data" — which is a different category of question and is answerable.

A clock, but not a trap

The tagline "Preview the AI. Then trust it." only works if the preview is long enough to be evidence and if the end of it is not a bill. A 14-day clock fails the first test — at day twelve the question is "should I pay" again, not "is the AI right." A card on file fails the second, because the decision gets made by a calendar rather than by the seller.

Thirty days with no card fails neither. Two weeks in, the traces are statistically worth reading; you then have another two weeks to act on them. And because we never took a payment method, the end of the window is genuinely a decision: the AI stops proposing, your history stays, you export whatever you want, and if you upgrade later it picks up exactly where it left off.

The trade-off is real. A free tier of this shape costs us compute a demo would not — the sixteen agents run against the seller's account whether or not the seller is paying. We have spent the engineering hours to make that economic.

Specifically:

• Simulation accounts auto-pause after fourteen days of inactivity. One-click resume — the compute pauses while the user is not looking, without spending their window.
• A total seat cap on the public Simulation tier (starting at 200 active seats; raised as conversion data accrues), so the free tier can never outrun the compute that backs it.
• Lower agent cadence on Simulation versus Live. Paid tiers run continuously. Simulation runs at one cycle per day. Enough for daily decision traces; less than ten percent of paid-tier compute.
• A Haiku-dominant model mix on Simulation. The trace surface stays full quality; the internal cost falls roughly four to six times per invocation.

These levers compound. Per-account daily cost on Simulation ranges from five to fifteen cents in expectation, and zero for paused accounts. The free tier is not a promotional loss-leader. It is a cost-engineered position.

What the simulation actually does

Inside Simulation Mode, Mirox executes the full bidding loop end-to-end with one substitution: the SP-API write call is replaced with a write to a parallel trace store.

Concretely, on a Simulation account:

• The full sixteen-agent stack runs against your live campaign data.
• Tactician computes a target bid for every keyword the system would have acted on.
• Strategist evaluates campaign stage and proposes stage transitions.
• Sentinel reads your days-of-cover from the SP-API feed and applies inventory throttles.
• Semantic computes asymmetric relevance scores against your product detail pages.
• Shield runs every safety gate it would run on live mode.
• Every output is written to a decision trace exactly as it would be on a paid account.
• The only thing that does not happen is the API call that changes your bid.

The result is a parallel record of what the AI would have done, hour by hour, for the entire window. The seller can read traces in the dashboard, export to CSV, and compare what the AI proposed against what their current campaigns did. The gap is the value of the tool, on their data, at their cadence — not at a salesperson's.

Why we eat the cost

The economics question is real. SaaS free-to-paid norms are 2–5 percent. Simulation Mode at scale only pays for itself if conversion is meaningfully higher than that.

We made that bet on three grounds.

Brand wedge. The category's three best-known tools all run trials. Simulation Mode is the single most-mentioned reason early prospects ask us a second question. Giving up the wedge to save the compute would cost more in customer acquisition than the compute itself.

Sales-cycle compression. A demo lasts an hour and produces no data. A 14-day Simulation run produces a trace per agent per day on the seller's own account. The decision conversation at the end is qualitatively different — the seller has already lived inside the product. The compute is buying us a higher conversion rate against the same number of qualified leads.

Honesty insurance. A free Simulation tier means we cannot oversell. If our pitch claims the AI finds €X of waste and the trace shows €X/3, the seller catches it before signing. That keeps our marketing tethered to what the product actually does, which is a brand asset for the next decade.

If conversion runs below one percent at scale, the levers we will reach for are tighter cadence and a verified-seller gate (must connect Amazon and show some minimum monthly spend) — not a shorter window and never a card on file. The window can be honoured cheaply; the no-card promise is the expensive one to give up.

Public Simulation vs Founding Beta Program Simulation

A clarification, because this post predates the public launch.

The public Simulation tier is open now, to everyone, at mirox.pt/signup. Thirty days free. No card, no auto-conversion. Auto-paused on inactivity, which does not spend your window.

The Founding Beta Program, which closed in July 2026, used Simulation as a one-to-two-week calibration window before the seller chose to go live. That was a different product configuration, defined by the signed Founding Member Agreement, and it existed in part to harden the live-bidding stack before public open — which it did. The write-up is still up at looking for ten founding operators.

Public Simulation stays free and card-free. The program was never a contradiction of that promise; it was a different signed agreement for a different role.

What Simulation Mode is not

Two things are worth being explicit about.

Simulation Mode is not a forecast. The traces are decisions Mirox would have made at decision time, with the information the system had then. They are not a prediction of what the campaign would have done if those decisions had been live — that would require a counterfactual model we deliberately do not ship, because every "what would have happened" estimate quietly turns into a marketing claim.

Simulation Mode is not a coaching tool for sellers learning Amazon PPC from scratch. The traces assume the reader knows what ACoS, TACoS, and a placement modifier are. If you are still building that vocabulary, the trace will look like jargon. The product gets better the more PPC fluency the seller brings.

Where this pillar leads

Of the four pillars, Simulation Mode is the one that converts buyer skepticism into evidence. It is also the one that costs the most to operate and the one that competitors are most likely to copy first. Both of those facts argue for keeping it.

Watch the AI decide before you trust it. That is the whole pitch. Read the transparency post for what the traces actually contain, then start free at mirox.pt/signup.