← All features

AI moderation Pro

AI that triages spam before you see it

AI scores every new post and reply, then routes likely spam and abuse to the moderation queue. It suggests, your rules and your moderators decide. Run it locally on Ollama when privacy matters.

Read the full AI setup guide →

The Jetonomy Pro AI integration settings: provider activation, per-feature toggles, the live usage dashboard, and the monthly spend cap

The problem

Spam and abuse scale faster than human moderators. You either over-moderate and burn out, or you let the noise pile up and watch the community rot.

  • Four providers, including self-hosted Ollama, OpenAI, Anthropic, and any custom OpenAI-compatible endpoint
  • AI spam detection scores each post and reply, sending likely spam to the queue and publishing the rest
  • Content moderation against a plain-English policy, with four tuned presets to start from
  • Reply suggestions and thread summaries that draft, never auto-publish
  • Usage dashboard plus monthly spend caps per cloud provider, so a runaway loop cannot drain your account

How AI moderation works

Moderation is the heaviest job in any community. Every post and every reply is a possible spam attempt, an abuse report, or a duplicate question. At a handful of topics a day one person can keep up. At hundreds, they cannot.

Jetonomy Pro puts a language model in front of the queue. It reads every new post and every new reply, scores spam probability, and checks the content against the moderation policy you set. Anything above the line goes to the moderation queue with a generated reason. Everything else publishes as normal. The model does not replace your moderators, it filters what they see so their attention lands on the calls that actually need a human.

You stay in control of which features run. Spam detection, content moderation, reply suggestions, and thread summaries each have their own toggle, so you can enable only what you need and assign different features to different providers.

Pick a provider, including your own

The AI layer is built on a pluggable adapter pattern, and four providers ship out of the box. Ollama runs on your own server for full data control. OpenAI and Anthropic are hosted options for fast setup and high-quality moderation. The custom provider connects any OpenAI-compatible endpoint you run yourself.

Every feature can be given a primary provider plus an optional fallback chain. A typical setup is Ollama first for privacy, with OpenAI as a fallback for the moments the local model is restarting. If the primary errors mid-request, Jetonomy retries the next provider before surfacing anything to you.

For content moderation, four tuned presets give you a starting policy: Community Forum, Support Desk, Kids Safe, and Academic. Pick the closest one, edit the plain-English policy text, and the model reads new content against your version.

See cost and stay private

A usage dashboard widget appears on the main Jetonomy admin as soon as a provider is connected. It shows requests today and this month, token usage by feature, estimated spend by provider with the share of the monthly cap consumed, average response time, and error rate. If a feature starts running hot, you see it and can pause that one feature without touching the rest.

For communities that cannot send member content to an outside API, run Ollama locally and nothing leaves your server. Every model decision is also recorded to an audit log, so you keep a permanent record of what the AI did and why, which is useful for compliance reviews.

Who it's for

Privacy-first and regulated communities

Run Ollama on the same server so member content never leaves your machine, no API keys, no external calls.

Solo owners and small teams

Let AI clear the obvious spam so your limited moderator time goes to the real judgment calls.

High-volume forums

At 500 topics a day a human cannot keep up. AI reads every one and surfaces only what needs you.

Common questions

Can I run the AI without sending data to a third party?

Yes. Run Ollama on the same server as WordPress and Jetonomy talks to the model over localhost only. No external network calls, no API keys, no member content leaves your machine. There is also a custom provider option for any OpenAI-compatible endpoint you host yourself.

Does the AI delete or block posts on its own?

No. AI suggests, you decide. Spam-scored content and policy violations go to the moderation queue with a reason the model generated, and your human moderators make the final call. Reply suggestions and thread summaries are drafts that need approval too.

Will AI calls run up a surprise bill?

Each cloud provider can be given a monthly spend cap in USD. Once usage crosses the cap, Jetonomy stops sending requests to that provider and shows an admin notice. Self-hosted Ollama has no per-request cost, so it has no cap. A usage dashboard tracks requests and estimated spend as you go.

Does it require Pro?

Yes. AI spam detection, content moderation, reply suggestions, and thread summaries are part of Jetonomy Pro. The free plugin ships a pattern-based spam detector, and AI adds the model-driven layer on top.

Run it on your own WordPress.

Download the free plugin, run the 5-minute wizard, and turn this feature on. No SaaS rent, your data, your domain.