DefendyTelegram moderation
RUOpen Defendy
← Back to all
Beta

AI spam verification

A controlled OpenRouter-backed verification stage complements deterministic anti-spam rules.

Open Defendy
Defendy control panelBeta

Configuration preview

1New member check
2Message filter
3Action result

Controlled rollout

What is included

  • Not presented as generally available
  • Will be documented after production verification

Admin problem

A clear rule instead of guesswork

An administrator needs to configure the capability once, see its actual status and understand the expected result.

  • Designed for backward compatibility
  • Feature-flagged delivery
  • Status shown transparently

How it works

Status controls the interface

The capability rolls out gradually, and its limited status stays visible across product materials.

Expected action

A visible result

When a configured condition matches, Defendy applies the selected moderation action and, where supported, sends the result to the log chat.

Source of truth

Verifiable product status

We do not publish unverified scale or availability claims. These paths are the evidence for this status.

  • services/content_ai_svc
  • frontend/webapp/src/features/spamcheck