> For the complete documentation index, see [llms.txt](https://docs.spara.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.spara.com/platform/leads/blocking.md).

# Blocking

Spara automatically monitors all incoming messages for harmful content. When a lead sends messages that violate safety thresholds, Spara blocks the lead to protect your team and maintain a safe sales environment.

## How blocking works

Every message a lead sends is evaluated in real time using OpenAI's content moderation model. The model checks for categories including harassment, illicit content, violence, hate speech, sexual content, and self-harm. Each message receives a category score between 0 and 1.

Spara tracks a cumulative moderation score across all of a lead's messages. When the total score reaches **1.0 or higher**, the lead is automatically blocked. A single severe message (e.g., a threat or illicit request) can trigger a block immediately, while milder violations accumulate over multiple messages.

When a lead is blocked:

* Spara stops responding to the lead's messages
* The lead appears as **Blocked** on the [**Leads**](https://app.spara.co/leads) page
* A [Notifications](/platform/settings/notifications.md) is sent if the Blocked event is enabled in your notification settings

## Moderation categories

Spara evaluates messages against these categories, based on [OpenAI's moderation policy](https://platform.openai.com/docs/guides/moderation):

| Category       | Examples                                                    |
| -------------- | ----------------------------------------------------------- |
| **Harassment** | Insults, threats, or abusive language directed at the agent |
| **Illicit**    | Requests for illegal goods, services, or activities         |
| **Violence**   | Threats of violence or graphic violent content              |
| **Hate**       | Discriminatory language targeting protected groups          |
| **Sexual**     | Explicit sexual content or solicitation                     |
| **Self-harm**  | Content promoting or describing self-harm                   |

## Manual blocking and unblocking

Your team can manually override the automatic moderation system. Open the lead from the [**Leads**](https://app.spara.co/leads) page — the controls are in the right-hand panel of the **Timeline** tab (not the Lead Details tab).

* **Block a lead** — Turn off the **AI Responses enabled** toggle, regardless of the lead's moderation score. Spara stops responding to the lead on every channel — website chat, AI demos, and incoming voice calls — and submitting the same email address again does not create a fresh, unblocked lead.
* **Unblock a lead** — Turn the **AI Responses enabled** toggle back on for a lead that was automatically flagged. Once unblocked, Spara will not re-block the lead automatically, even if they send additional flagged messages. This is useful when a false positive occurs.

The **Workflows enabled** toggle in the same panel is the outgoing counterpart: while **AI Responses enabled** covers incoming engagement, turn off **Workflows enabled** to stop email and voice outreach from [Workflows](/agents/workflows.md) to the lead.

## FAQ

### Can I adjust the sensitivity of the moderation?

The moderation thresholds are not configurable per-organization. They are calibrated to block clearly harmful content while minimizing false positives.

### What happens to a blocked lead's data?

Blocking a lead does not delete any data. Their conversation history, field data, and activity remain visible on the Leads page. The lead simply cannot receive further responses from Spara.

### Does moderation apply to email messages?

Yes. Both chat messages and email messages from leads are evaluated for harmful content and contribute to the lead's cumulative moderation score.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.spara.com/platform/leads/blocking.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.