Server Assistant

Most Discord moderation bots are rule-runners: a message trips a filter, the bot reacts. Server Assistant adds an intelligence layer on top — it watches your server's health, learns how your team moderates, second-guesses its own false positives, and treats the people on the other end of a ban like adults.

🩺 It watches your whole server — not just messages

Once a day, Pulse posts a health report to your staff channel — messages, joins, AutoMod activity and warnings, each with a week-over-week trend — and flags the slow-burn patterns humans miss, like a trickle of joins sitting just under your raid threshold. Read-only: it never acts on its own. It just gives your team x-ray vision.

📩 A ban isn't a silent door-slam — members get one appeal

When anyone is banned, Server Assistant DMs them exactly why and invites a single reply to appeal. That one reply opens an appeal ticket for your staff with one-tap Unban, Deny, and Research — which runs an AI report on the member's last message so you decide with context, not vibes.

🤔 AutoMod that asks before it over-reacts

Keyword filters punish the innocent — the classic "I love visiting Scunthorpe" problem. Turn on AI review and borderline hits get a confidence check first: clear violations act instantly, anything doubtful is left up and handed to staff with one-tap Delete & warn or Allow. Fewer false positives, less mod drama.

🧠 AutoMod that learns your team's judgment

Off-the-shelf filters are one-size-fits-all. Self-trained AutoMod quietly studies the calls your staff actually make — what they delete, what they report — and proposes rules tailored to your community, for your approval. Nothing is ever auto-enforced.

🛡️ And it keeps everyone honest

A tamper-proof, encrypted audit trail records every action — even bans done by hand in Discord — in a log staff can't edit or erase, and pings the owner if anyone tries. Repeat-offender detection fingerprints the people you ban and stops their alt accounts at the door. An explainable Threat Score turns raw behaviour into a clear risk level, and tiered approval sends dangerous actions up the chain before they run.

✅ Everything you'd expect, too

A full mod toolkit (warn, mute, kick, ban, softban, timed bans, one-command roles, server-wide lockdown, 24-hour undo), AutoMod with curated filter packs and custom regex, anti-raid detection, a DM verification gate, private ticket panels, AI image generation, and a nine-panel customisation hub — all configurable without code.

---

Privacy-first, and free to start. Core moderation is free forever; the AI features come with a free trial, with optional Premium for more. Full breakdown on the pricing page.

📚 Learn more

• Documentation: https://wandweb2.github.io/server-assistant-docs/
• Features: https://wandweb2.github.io/server-assistant-docs/features/
• Pricing: https://wandweb2.github.io/server-assistant-docs/pricing/
• Roadmap: https://wandweb2.github.io/server-assistant-docs/roadmap/
• Setup guide: https://wandweb2.github.io/server-assistant-docs/setup/
• Privacy & Terms: https://wandweb2.github.io/server-assistant-docs/privacy/ · https://wandweb2.github.io/server-assistant-docs/terms/
• Support server: https://discord.gg/egzwNJJcKm