Skip to content

Straight answers, before the demo.

The questions we expect from a security or platform lead.

01Do we have to change our agents’ code?

Usually just two settings: its model base URL and API key. Point it at the FleetWarrant Gateway with its own Agent API key instead of calling your LLM provider directly. For an OpenAI-compatible or Anthropic client, that’s a base-URL and key swap: no new SDK to install, no sidecar to run. Streaming and tool calls work on every Connector, and the docs list which routes each provider supports. The systems your agent’s tool calls reach on the other side need no changes at all.

02What does FleetWarrant do today?

You point your agents at the Gateway and it records every call they make through it, classified and written to your audit trail. You can suspend any Agent or revoke its key, stop them all at once, limit which models each may call, and get alerts on budgets and unusual spikes. It covers every agent you register and point at the Gateway. A policy engine that can hold or block a call based on rules you write is on the roadmap.

03Does this work with agents we didn’t build?

Yes, wherever you can set the agent’s model base URL and API key. An agent built on an OpenAI-compatible or Anthropic SDK, or entirely in-house, that lets you change both authenticates through the same Gateway and lands in the same audit trail, whoever built it. The one requirement is that base URL and API key setting: a tool that only signs in to its vendor’s own account doesn’t have one.

04What happens to our agents if the Gateway is down?

The Gateway sits in the request path, so an agent pointed at it reaches its LLM provider through it. Its calls fail until the Gateway is back, and you can point an agent straight back at your provider at any time. The Gateway runs in one region, Sydney. If only the audit write fails, the call still goes through without an Event and an alarm fires. We don’t offer an SLA yet.

05How much latency does the Gateway add?

In our first measurements on production, in October 2026, the Gateway’s own processing took about 130 ms per call: checking the Agent API key and the model allow-list, forwarding the call and recording the Event. Network time comes on top. The Gateway runs only in Sydney, so an agent and a provider that are both far from Australia add two long-haul trips to every call. It’s worth timing a few calls from where your agents run.

06How fast is the kill switch?

There are two levers. Suspend an Agent and the Gateway refuses its calls, with the reason you gave; its key stays valid, so resuming needs no change on the client. Revoke its Agent API key when the credential itself is compromised, and the Gateway rejects it in its own auth check, not on a delay. A call already in flight finishes. Both levers act on the agent’s model calls; credentials it holds directly to downstream systems, such as Salesforce, NetSuite or Stripe, are rotated in those systems.

07How do I stop all agents at once?

An admin uses the emergency stop. It suspends every Agent in your Tenant, and the Gateway refuses their calls. Agent API keys stay valid, so “resume all” needs no client change, and it resumes only the Agents the stop suspended: one you’d suspended by hand, or that a circuit breaker suspended, stays suspended. Both the stop and the resume are recorded as Events, with who did it.

08Does FleetWarrant block my calls when a budget is exceeded?

No. Budgets are alert-only. Set a monthly budget per Agent or for the whole Tenant and FleetWarrant alerts your Slack channel or webhook as spend crosses each threshold, with a daily reminder while you’re over. A person decides what to do, and the alert links to the Agent, where it can be suspended.

09What currency are costs in?

Agent-call costs are in US dollars, because that’s what the providers charge: each call is priced at its provider’s US$ price, with no currency conversion. A call we can’t price yet shows as unpriced, so any total that includes one is marked as a lower bound. FleetWarrant’s own plan prices are in Australian dollars.

10Can our auditor verify an export independently?

Yes. An evidence export’s manifest lists the SHA-256 of every file in the bundle and is signed with a FleetWarrant-owned KMS key. The bundle carries the public key and a standalone verify.py that needs only Python and the cryptography package, or you can check it with openssl. Compare the key’s fingerprint with the one FleetWarrant gives you over a separate channel, not with the bundle’s own copy, so a bundle someone re-signed fails.

11Can I send Events to Splunk or Datadog?

Yes. An admin can set up continuous export to Splunk HEC, Datadog Logs or a signed HTTPS webhook. Delivery to your own S3 bucket, which FleetWarrant writes to through a role in your account with an external ID, works too. Every destination gets the same versioned JSON record as an evidence bundle. Delivery is at least once, so use event_id to de-duplicate.

12Where does our data live?

FleetWarrant’s production environment runs in AWS Sydney (ap-southeast-2) only, and the Gateway processes your requests there. Your LLM provider processes the prompt wherever it runs, which may not be Sydney. Sydney is where production runs today, as an operating fact rather than a contractual data-residency commitment. Each Tenant’s records are encrypted under a KMS key of its own: logical isolation on shared infrastructure. EU regions, on-prem deployment and hardware attestation, which we plan for the enterprise tier, are on the roadmap.

13Do you store our raw prompts?

By default, no. The Gateway sees each request and response in the clear while it forwards the call, because it has to. What FleetWarrant keeps is a redacted preview of each call, encrypted under your Tenant’s own KMS key, plus the call’s metadata. A fixed ruleset removes secrets, US Social Security numbers, email addresses and card numbers from the preview. Other details, such as names and addresses, are outside that ruleset. A Tenant admin can turn on raw capture. While it’s on, the full request and response are archived as well, sealed under a per-Event key, and anything the preview removed is still in that raw copy. Each raw body can be shredded on request or by your raw-body retention, and a legal hold pauses shredding. The archive is Object-Locked in GOVERNANCE mode for 1 year by default, and FleetWarrant’s application never deletes an archive object.

14We’re early. Is it too soon for us?

If you have one agent in production with real credentials, now is the right time. Design partners get direct access to the team, and a say in the policy packs we build first.

Something we haven’t answered?

Ask us on the waitlist form