Deputy (AI assistant, powered by Claude)

The Deputy is SubnetSlinger's own AI assistant, powered by the Anthropic Claude API with your own key — it is NOT Microsoft Copilot or GitHub Copilot, and has no connection to them. (Send the whole Posse instead when you want a full multi-agent sweep — see the Posse article.)

What it does: an AI assistant that doesn't just chat — it can actually run the diagnostic tools (ping, traceroute, DNS, port scan, HTTP, TLS audit, IP info, WHOIS, SNMP, subnet calc, MAC lookup, ARP table) to investigate a problem, then explain what the results mean. Ask in plain English ("why can't this host reach the gateway?") and it decides which checks to run, reads the output, and answers with the evidence.

Setup: it's token-gated — paste your own Anthropic API key, or pick it from the Vault (store the key there once as an API-key secret and select it). Pick a model: Haiku 4.5 (fastest/cheapest, the default), Sonnet 4.6 (balanced), or Opus 4.8 (most capable). It opens on the cheapest — bump it up only when a problem needs deeper reasoning. See "AI models & token usage" for costs and the token readout. Your conversation and the tool results are sent to Anthropic to generate answers; nothing else leaves the machine.

Before anything is sent to Anthropic, SubnetSlinger scans your message and every tool result for secret-shaped text — private key blocks, password= fields, Bearer/Basic auth headers, API keys, JWTs — and strips them, replacing each with a labeled [redacted: ...] placeholder. You'll see a 🔒 notice in the chat whenever this happens; what's shown in your own chat window is always the full, unredacted original — only the copy sent to the cloud is scrubbed. This is a pattern match, not a guarantee: it catches well-known secret shapes, not everything a person could type. Don't paste a real password or key into the Deputy expecting it to always be caught — when in doubt, switch to Ollama (local) for that conversation instead.

Prefer local + private? Switch the "AI" dropdown to Ollama (local) to run an on-machine model instead — no key, no cost, nothing leaves the box. See "Ollama — run the AI locally". Tools, MCP, and the read-only safety all work the same either way.

Safe to run: yes — the assistant has READ-ONLY tools only. It has no SSH command execution, no file transfer, and no access to your stored credentials. For anything that changes a device — a config edit, shutting a port, containing a rogue host, rotating a key — it tells you what to do and why; it cannot and will not do it for you. Treat its tool runs like clicking the tools yourself: only point port scans and SNMP at gear you're authorized to test.

Reading results: tool runs show up inline as 🔧 lines so you can see exactly what it checked. If it ran a check, the conclusion is grounded in that result — verify the 🔧 output if a recommendation looks surprising.