# Examples | Chersus

![](/brand/carapace-hero-tilted-columbia.svg)
Examples

# Start from a
situation you know.

Twelve workflows, in four groups. Each one is a single request; open it in the builder and change what you need.

AI under GDPR

## Governance

Use any model while personal data stays out of the prompt, or goes only to a model in the EU.

### Use GPT without sending customer data

Your support assistant runs on a US model, but names, emails and IBANs stay out. The answer comes back with the real values.

Comes back: The model's answer, with the real names back in place.

- detect.pii.entities
- detect.secrets.credentials
- transform.pii.tokenize
- transform.secrets.redact
- relay

### Personal data to an EU model, the rest to Claude

A prompt with personal data goes to Mistral in the EU, tokenized. A clean prompt goes to the model you prefer.

Comes back: An answer from the EU model whenever personal data was found.

- detect.pii.entities
- transform.pii.tokenize
- relay with routing

### EU models for EU customers

Your code sets high_security for a customer whose contract requires EU processing. Their prompts go to a model in the EU, tokenized.

Comes back: Answers from an EU model only, for that customer.

- detect.pii.entities
- transform.pii.tokenize
- relay with routing

Attacks and abuse

## Security

Stop what attacks your model or your users before it gets through: injected instructions, jailbreaks and abuse.

### Stop prompt injection on your chatbot

Hidden instructions and jailbreak attempts are blocked before your model reads them.

Comes back: A block with the reason, before your model reads a word.

- detect.prompt.injection
- detect.prompt.jailbreak
- relay

### Check content before your agent reads it

Web pages, emails and documents can hide instructions for your agent. They are blocked before the text reaches the prompt.

Comes back: A block, before the page reaches your agent's prompt.

- detect.prompt.injection

### Triage toxic comments

Hate is blocked. Abuse and threats get flagged for a moderator, in 23 languages.

Comes back: Three scores per comment. Hate blocks; abuse and threats get flagged for a moderator.

- detect.toxicity.hate
- detect.toxicity.abuse
- detect.toxicity.threat

Data hygiene

## Data

Keep personal data out of logs and datasets, and turn free text into records your systems can store.

### Keep personal data out of your logs

Log lines and tickets reach your warehouse or monitoring tool without names, emails or keys.

Comes back: The same log line, minus names, emails and keys.

- detect.pii.entities
- detect.secrets.credentials
- transform.pii.redact
- transform.secrets.redact

### Pseudonymize records for analysis

Analysts get the records with names and emails swapped for tokens. Only you hold the map to reverse it.

Comes back: The records with tokens in place, and a map only you hold.

- detect.pii.entities
- transform.pii.tokenize

### Turn emails into records

An order or complaint email becomes an order number, a problem and a date, ready for your CRM.

Comes back: The order number, the problem and the date, as JSON.

- extract.fields.schema

Language and content

## Content

Know what a text is: its language and topics, with a title and a description for search and feeds.

### Sort a multilingual support inbox

Tickets reach the right team by language and topic, without keyword rules, and without personal data in storage.

Comes back: The language and the topics, ready to send to the right team.

- extract.language.code
- extract.content.topics
- detect.pii.entities
- transform.pii.redact

### Clean documents before your vector store

Index contracts and emails without personal data in the text, each with a title and a description for search.

Comes back: The redacted text, plus a title and a description read from the original.

- detect.pii.entities
- extract.content.title
- extract.content.description
- transform.pii.redact

### Titles and topics for every post

Each post or notification gets a title, its topics and an emoji that fits.

Comes back: A title, the topics and an emoji for each post.

- extract.content.title
- extract.content.topics
- extract.content.emoji

## Any workflow, one request.

Pick an example, change what you need, send one request, and read the result before you finish this page.
[Read the guide to workflows](/en/docs/workflows/)