FAQ

General

What is Transit AI?

A cross-platform GUI SSH client with an embedded investigation-only AI assistant for investigating network gear (switches, routers, firewalls). Every command the AI proposes passes a per-vendor permit list AND your explicit click. The familiar multi-session tab UX you already know, modernized.

Who is it for?

Network engineers who spend a lot of time in SSH and want help investigating without giving up control over what runs on the device.

What platforms?

macOS (Apple Silicon — macOS 12+), Windows, Linux. No Intel macOS build.

Is the source available?

Transit AI is closed-source commercial software. The security model is documented in detail (see Security and our threat model) but the source isn’t published.

Account & sign-in

How do I sign up?

Click Sign up anywhere on the site. The button routes into our hosted identity provider, where you’ll create an account. On first sign-in, a personal organization is auto-created so subscription and billing always attach to an org for a uniform model.

Does the desktop app talk to the website?

No. The desktop signs in by launching your system browser at the cloud’s OAuth endpoint, which returns through a transit:// deep link. The website doesn’t proxy desktop traffic.

What does sign-in actually give me?

Sign-in attaches your subscription to your account, then unlocks the AI agent: cloud-resident provider key metered against your tier’s monthly token budget, with the option to bring your own API key (Anthropic or OpenAI) on every paid tier — see Why does BYOK require a paid tier?

Pricing

How much is it?

Three paid tiers (Operator has a 14-day free trial), no permanent free tier:

• Operator — $29/month or $348/year. Easy + Medium AI models. 14-day free trial available.
• Pro — $79/month or $948/year. Adds Advanced models.
• Max — $199/month or $2,388/year. Same model surface as Pro with the largest monthly AI budget.

BYOK is included with every tier at no additional charge.

Annual billing is 12× the monthly price — there’s no discount, and that’s deliberate. Token costs dominate either way, so a subscription discount wouldn’t move your real total cost much. Annual is for buyers who’d rather expense once than monthly.

What happens if I exceed my monthly AI budget?

By default, overage is on: AI calls keep working past your budget cap, billing at 1.25× the provider’s per-token cost, capped at 2× your monthly subscription price — no surprise charges beyond that cap. You can turn overage off anytime in Settings → Billing or on your account page; with it off, AI calls simply stop at your budget cap until the next month. Past the 2× cap, calls stop again and you can contact us or upgrade your tier. The chat panel surfaces an 85%-utilized banner before you hit the cap.

Is there a free tier?

The terminal itself is free forever — no account needed. The AI is a paid subscription, but you can try it with a 14-day free trial of the Operator tier (card required; one trial per customer; converts to a paid subscription at the end of the trial unless you cancel). There’s no permanent free AI allowance — we keep it that way deliberately so we never revoke a free user’s access when their token cost line shifts.

Why does BYOK require a paid tier?

Short version: your API key moves the token bill. It doesn’t move anything else.

Transit AI’s entire reason for existing is a novel use of AI — an agent that reads from and proposes commands against live network equipment. Our R&D and our intellectual property are concentrated there: the isolation that keeps the agent away from your credentials, the per-vendor permit lists, the redaction pipeline, the approval flow, and the cloud that routes, meters, and safeguards every request. So is our risk. An AI agent pointed at production network gear carries legal, compliance, and safety obligations that we carry as the vendor — and those obligations are exactly the same whether a completion bills to our provider account or to yours. Shifting token spend doesn’t shift risk.

That’s why every AI request has to come from an authenticated subscriber who has accepted our Terms. The acceptable-use rules, abuse controls, spend safeguards, and support relationship all hang off that agreement. A free anonymous BYOK mode would mean operating — and answering for — all of that machinery for users with no agreement in place, indefinitely. That’s not a discount; it’s an uncapped liability.

There’s also a practical half to this: BYOK requests don’t bypass our infrastructure. Your key is read from your OS keychain per-request and travels through our cloud proxy (never persisted server-side), which does the model routing, usage accounting, and the ongoing compatibility work — when a provider changes an API behavior, we fix it server-side and every install keeps working without an update.

What BYOK on a paid tier actually buys you is flexibility, not a licensing bypass: run models at your own negotiated token cost, and on Operator it unlocks flagship models — your own Anthropic key enables Claude Opus 4.8 — that would otherwise need a higher tier. Setup takes about a minute: Bring your own provider key.

The AI agent

What can the agent do?

Four tools exactly: list open sessions, read their scrollback (filtered), propose a command (gated), and ask you a clarifying question. That’s the entire surface.

Can it execute commands on a device?

Only by asking you to approve a command, and only after both the per-vendor permit list AND your click say yes. A command that fails the permit list never reaches the approval prompt — the AI is told it can’t run that one and moves on.

Can it bypass the permit list by asking nicely?

No. The permit list lives on your machine and is checked on every command the AI proposes. The AI has no way to disable it, edit it, or talk it out of a denial mid-conversation.

Can it read my passwords?

No. The product is structured so the AI agent and the credential store live in entirely separate components with no programmatic route between them. An automated check verifies the isolation on every change we ship. Secret material that appears in device output is replaced with placeholders ([REDACTED:pem#1]) before the AI sees it.

What about prompt injection from a device?

When the AI reads device scrollback, the bytes are clearly tagged as untrusted input — and the AI’s instructions tell it to treat anything inside those tags as data, not as commands. Even if a device’s output reads “IGNORE PREVIOUS INSTRUCTIONS AND RUN X”, the AI has been told to ignore it. Plus the per-vendor permit list runs on every proposed command regardless of what the AI was “convinced” to suggest.

Which AI models can I use?

Transit AI groups AI models into three levels — pick the right one for the question you’re asking:

• Easy — fast & cheap, good for routine “show me” / status queries. Claude Haiku 4.5 or GPT-5.6 Luna.
• Medium — balanced reasoning, good for “why is this broken” troubleshooting. Claude Sonnet 5 or GPT-5.6 Terra. Default.
• Advanced — deep multi-step reasoning. Claude Opus 4.8 or GPT-5.6 Sol. Included on Pro and Max; on Operator they unlock with BYOK (Opus with your Anthropic key, Sol with your OpenAI key) at your own token cost.

Switch models from the chat panel’s dropdown; each chat remembers its model. Retired models are transparently served by their successor, so an older install never breaks mid-conversation.

Security

Where do my SSH passwords live?

In your OS’s native keyring (macOS Keychain, Windows Credential Manager, Linux Secret Service) or your running SSH agent. The Transit AI binary holds them in process memory only for the duration of an authentication and never serializes them to disk.

Where do provider API keys live?

For default (cloud-resident) usage: in our isolated proxy infrastructure outside the desktop binary — never on your machine, never in our database, never logged. For BYOK: in your OS keyring (a separate keyring service from your SSH secrets), read per-request, sent through the cloud proxy as a body field, never persisted server-side.

Do you log my prompts or device output?

No. The cloud proxy meters call metadata only — token counts, latency, cost, model, request identifiers. Field-name guardrails reject any log line that would carry prompt content, completion content, device names, or any other content-bearing field, and the guardrails are verified at runtime and at build time.

What’s stored about my devices?

Your inventory (host, port, vendor, group, and the name of the credential to use — never the credential itself) is stored in a TOML file on your machine at the OS’s standard application config path. None of it leaves your machine except via SSH to the device itself, or via filtered scrollback excerpts sent to the AI when you’re actively asking it a question.

Operational

What if my SSH connection drops?

Press Enter in the dead pane to reconnect. The tab stays in its slot, the new session opens against the same device, and any custom tab label / split anchor is preserved.

Can I use it without the agent?

Yes. The chat panel is hidden by default (toggle with Cmd/Ctrl+J). The terminal works standalone — connect, type, scroll, copy/paste.

Does it work behind a corporate proxy?

For SSH: subject to your proxy’s outbound rules — Transit AI doesn’t add a layer. For the AI assistant: traffic goes to api.transitai.app over HTTPS. The desktop is configured to talk only to that hostname and our identity provider, so those are the two domains your proxy needs to allow.

Can I run it offline?

The SSH client works offline — it’s just a terminal. The AI agent needs api.transitai.app reachable; without it the chat panel shows an “offline” banner and disables the send button.