Safety filters

Safety filters are PolyAI’s content classifiers. They inspect every user input and every agent output in real time and block anything that exceeds the severity threshold you set for each category. Filters combine PolyAI’s models with third-party services such as Azure OpenAI content safety. Configure project-wide defaults in Configure > General, then override them per channel in Channels > Voice > Voice configuration and Channels > Chat > Chat configuration.

​

How filters run

Filters run on both sides of every turn:

• User input – classifies what the caller or visitor says before the agent sees it. Blocked input is replaced with a safe fallback response.
• Agent output – classifies what the agent is about to say. Blocked output is suppressed and the agent recovers with a safe response.

Filtering is independent of the LLM prompt – it’s a separate model layer, so it works regardless of agent behavior, flow, or prompt changes.

​

Categories and severity levels

Each category has four severity levels. Pick the level per category that matches your use case and compliance requirements.

​

Project defaults vs. channel overrides

Safety filters are configured on a per-channel basis with project-wide defaults as a fallback.

• Project defaults – set in Configure > General. Apply to any channel that does not have its own overrides enabled.
• Voice channel – override in Channels > Voice > Voice configuration. See Voice configuration → Safety filters.
• Chat channel – override in Channels > Chat > Chat configuration. See Chat configuration → Safety filters.

When a channel has its own filters enabled, the channel values win for that channel. When a channel has filters disabled, the project defaults apply.

​

Edit filters

1. Open Configure > General and find the Safety filter defaults section to set the project-wide baseline.
2. To override for a specific channel, open the channel’s configuration page (Channels > Voice or Channels > Chat), enable safety filters, and adjust the sliders.
3. Save. Voice and project-level changes follow the standard environment branching; chat changes take effect immediately on save.
4. Test with Chat with Agent or a sandbox phone number before promoting.

​

Monitor filter activity

Every filter trigger is recorded on the conversation. Monitor across conversations from the Safety dashboard:

• Calls managed for risk – how often filters fired (count and percentage).
• Caller utterance category – breakdown by hate, sexual, violence, and self-harm.
• Caller utterance risk level – risk distribution of incoming messages.
• Distribution of flagged calls – trend over time.

To inspect a single conversation, open it in Conversation review – flagged turns are annotated inline. Filter the conversations list by safety category in the QA category filter.

​

Language support

Filters have been trained and tested in English, German, Japanese, Spanish, French, Italian, Portuguese, and Chinese. Other languages are supported but performance may vary – test thoroughly in your target language before going live.

​

How safety filters fit with Guardrails

Safety filters and platform Guardrails protect different layers and are designed to run together:

• Safety filters classify each input and output against hate, sexual, violence, and self-harm before/after the LLM. They block content at the model layer.
• Guardrails are prompt-level instructions that shape how the LLM responds – for example, refusing to disclose its identity or escalating on a crisis signal.
• Jailbreak detection (always-on filter) blocks malicious input upstream; the Jailbreak & Prompt Defence guardrail tells the LLM how to respond if anything slips through.
• Emergency & Crisis Escalation (a guardrail) catches conversational distress signals that the self-harm filter misses – for example, “I don’t want to be here anymore” said in a measured tone.

Use both. They’re complementary, not redundant.

​

Best practices

• Test thoroughly – run your own tests to validate filter behavior against representative content from your domain.
• Don’t default to Strict – find the level that prevents harm without over-filtering legitimate calls. Over-filtering causes safe fallbacks that hurt CX.
• Be consistent across variants – when running A/B tests or multiple agents, keep filter levels aligned so reporting is comparable.
• Review flagged calls weekly – use the Safety dashboard to catch drift before it becomes a compliance issue.

​

Related pages