Complete Separation of
Script Generation and Execution

Only your text prompt leaves your machine. Scripts, output, credentials, and session data never do. Two modes, one guarantee — you decide what crosses the boundary.

YOUR MACHINE — 100% LOCAL Chat Display Full conversation, every script output PS7 Runspace Persistent session, embedded execution Native C++ Core Mutual verification, client anti-tampering MANAGED AI CONTEXT Separate from the chat. Usually shorter. Trimmed automatically. DATA BOUNDARY Prompt Output (opt-in) Reply SHELLPILOT CLOUD — AZURE EU (api.shellpilot.app) Secure Proxy Strips your identity before the request reaches Google Vertex AI — Gemini EU region Generates scripts from prompts

The visible chat is not the AI context

What you see in the chat is the full conversation, including every script output. What the AI receives is a separate, automatically managed context — usually shorter, trimmed to fit the model's window. Only your prompts and the outputs you actively send via Send to AI enter it.

What crosses the boundary

Solid arrow: your prompt — crosses automatically.
Dashed arrow: a specific script output — crosses only when you click Send to AI on that result.
Reply: the generated script, returned to the chat.

Mutual verification on every request

The client verifies the proxy. The proxy verifies the device. Both directions, every call — not just at login. The verification logic lives in the Native C++ Core and protects only the integrity of the connection.

Transparent to SSL inspection

Enterprise SSL inspection sees your prompt, the generated script, and a short-lived session token bound to this specific device. None of those lets an attacker impersonate the proxy or reproduce the backend. A captured token without the matching device is inert.

Google does not know who you are

The Secure Proxy strips your identity before forwarding the request. Your email, subscription, and company are not part of what Google sees — only an anonymous device hash and your prompt.

Nothing is stored server-side

Prompts, scripts, chat history, and script outputs are not persisted on the proxy or anywhere else. The proxy holds only what it needs to operate: your email, subscription state, and the device hash.

YOUR MACHINE — 100% LOCAL Chat Display Full conversation, every script output PS7 Runspace Persistent session, embedded execution Native C++ Core Mutual verification, client anti-tampering MANAGED AI CONTEXT Separate from the chat. Sized by your setting: 16K–128K tokens. NETWORK BOUNDARY Prompt Output (opt-in) Reply Licence Heartbeat hourly when online YOUR LOCAL LLM SERVER — YOUR INFRASTRUCTURE OpenAI-Compatible Endpoint Your model, your hardware, your network. Direct client connection — the proxy is not on this path. SHELLPILOT PROXY — AZURE EU Licence Heartbeat Only No prompts, scripts, or output. No AI traffic on this path.

Direct connection to your local LLM

In Local AI mode, the client sends prompts directly to the OpenAI-compatible endpoint you configured — LM Studio, Ollama, Azure OpenAI, or any other. The ShellPilot proxy is not in the inference path — prompts, scripts, and outputs never leave your network for AI processing. Script output is opt-in here too: it crosses only when you click Send to AI — which is why you can switch between Cloud and Local mid-session without leaking anything.

Context length: your setting, not a guess

You choose the context length in the settings — 16K, 24K, 32K, 64K, or 128K tokens, matched to your model and hardware. The AI context is trimmed to exactly the limit you selected, separate from the visible chat.

Proxy is contacted only for licence verification

While a Local AI session is running, the client refreshes its licence token hourly when online. If the proxy is briefly unreachable, the session continues for up to 24 hours since the last successful refresh. The proxy never receives prompts, scripts, or output in this mode.

Launch still requires proxy reachability

Every fresh launch of ShellPilot contacts the Azure proxy once to verify your subscription before the main window opens, regardless of mode. After that, in Local AI mode the inference path stays inside your network.

Nothing leaves your infrastructure for AI

Designed for environments with strict data-sovereignty requirements: banks, government, healthcare, regulated industries. AI inference, prompt content, and script output all stay on your network. Also your business-continuity path: a cloud outage does not stop your infrastructure management.

You control the model

Any OpenAI-compatible endpoint works — your model choice, your hardware, your hosting. ShellPilot does not impose a model or a vendor for the Local AI path. Local models have inherent limitations (smaller context window); optimized for standard scripting and automation tasks. Available on Pro and Pro Plus.

Want the Compliance Detail?

AMSI, App Control, script-block logging, execution policy — the security page answers reviewer questions precisely.

Security & Compliance Request a Demo