all routes nominal · api v1 · schema runbook/v3
Almost everyone starts with the fixed-fee Routing Review. Most then hand us the running of it — Managed AI Routing is where the 40–60% comes from. Agent Operations and Private Networking are depth. Any one can be hired on its own.
A fixed-fee audit of what your company spends on AI. We read a sample of your traffic and show you, workload by workload, exactly what you'd save with smarter routing — before you commit to anything.
Our flagship. Point your software at GhostRouter instead of directly at an AI provider — usually one line of config — and every request gets sent to the cheapest model that can do the job properly. Your product behaves the same; your invoice shrinks. Typical clients cut model spend 40–60% in the first billing period.
If you run AI agents in production, we run their judgement layer: every answer is checked before it's trusted, retried when it's wrong, and handed to a human when it matters. You get agents you can leave unattended without waking up to a mess.
Private, encrypted connections between your systems, your AI traffic, and your providers — with backup paths built and tested before you ever need them. No public exposure, no scrambling during an outage.
fixed fee · no discovery creep · you keep the report
You send us a sample of the AI requests your software already makes — a week is usually plenty. We sort them into the jobs they actually are, then price each group twice: what you paid, and what it would have cost sent to the cheapest model that handles that group correctly.
The difference between those two numbers is the entire reason this company exists.
WHAT YOU GET
SAMPLE · WHAT A TRAFFIC-SHAPE REPORT LOOKS LIKE
| Workload | Requests | What it needs | Paying for | Should run on | Est. saving |
|---|---|---|---|---|---|
| invoice-extract | 1,240,000 | fixed-schema extraction | frontier | small + schema check | −91% |
| support-triage | 430,000 | short classification | frontier | small | −88% |
| report-summary | 96,000 | synthesis, some judgement | frontier | mid | −54% |
| contract-review | 3,100 | genuine reasoning, high stakes | frontier | frontier · unchanged | — |
| translate-ui | 210,000 | translation | mid | small | −62% |
| nightly-etl | 2,900,000 | mechanical transform | mid | small · batch lane | −71% |
Roughly one workload in five genuinely needs the expensive model — and the report says so.
An agent that is right 95% of the time is not 95% useful — it is a thing somebody has to watch. We run the layer that does the watching: every answer an agent produces is checked before anything downstream trusts it, wrong answers are retried, stubborn ones climb to a stronger model, and the small number that still don't resolve go to a person instead of into your database.
The check is two-part and neither part is a vibe. First the answer has to be the right shape — the fields you asked for, the types you asked for, the totals adding up. Then, where it matters, a second model reads the answer against the request and scores whether it actually did the job. Only answers that pass both are returned.
Some decisions should never be fully automatic, and we would rather say so out loud than quietly automate them. Those route to a human-review queue with the agent's working attached, so the person deciding can see what the machine thought and why it wasn't trusted.
retry: attempts at the target it is on. escalate_after: tier failures before it climbs one rung. Every branch writes one audit row.
The two services below have pages of their own, written for the person who will actually be responsible for this: how a request is scored, what happens when a cheap model gets it wrong, what a policy file looks like, and how traffic keeps moving when a provider or a path goes dark.
The whole path a request takes: the three jobs run on every call, the escalation ladder that decides when cheap is not good enough, the policy file you own and review, and a console you can type into yourself.
The layer underneath: a private overlay between your services with no public ingress, relay hops you nominate, and standby paths that are kept warm and proven long before an incident asks for them.
Tell us roughly what your software does with AI and we will tell you what a Routing Review costs and how long it takes. Existing clients: usage, invoices and payment live in the portal.
