Deidentifier
On this page
Purpose
Deidentifier detects selected types of sensitive information in a Message and replaces each detected value with a tag that Pseudonym Resolver can later resolve. Detection is designed for English text and can miss values.
Deidentifier starts a protected segment in the flow. A detected value is raw before this component and replaced by a tag for every component inside the segment. It becomes raw again only after a paired Pseudonym Resolver component closes the segment later in the same flow.
When to use it
- Keep a detected email address, phone number, or other selected category out of an Agent or model while it reasons, and put the real value back before the user sees the answer.
- Pass stable tags through several components, such as an Agent, a model, or a tool, and restore the originals only where they are actually needed.
- Use Guardrail instead when the flow should route or block a Message rather than change its text.
Required setup
At least one Category must be selected. There is no default selection, and Deidentifier refuses to run until one is chosen.
How to use it
- Connect a Message value to Input, typically from Chat Input.
- Select at least one category to detect.
- Connect Deidentified Output to the first step that should receive tags instead of the detected values, typically an Agent or a language model.
- Add a Pseudonym Resolver component later in the same flow, after the last step that should receive tags, so those tags resolve before the answer reaches the user.
Typical flow: Chat Input -> Deidentifier -> Agent or model -> Pseudonym Resolver -> Chat Output.
Configuration
| Setting | What it controls | Recommended starting point |
|---|---|---|
| Input | The Message inspected and transformed. | Connect it immediately after the component that first produces user-entered data, such as Chat Input. |
| Categories | The categories detected and replaced with a tag. | Select every category the flow needs. There is no default, and at least one is required. |
The categories picker offers:
- Credit card number
- Date or time
- Email address
- Location
- Person name
- Phone number
- URL
The picker does not cover every possible type of sensitive information. For example, IP addresses are not currently available and are not detected. Text in another language, or a value that does not match a detection pattern, may also pass through unchanged. Selecting a category does not guarantee that every instance will be detected.
Example
A user enters:
Contact john@example.com or call +1 202-555-0147 about the appointment.
With Email address and Phone number selected, Deidentified Output contains:
Contact [EMAIL_ADDRESS_1] or call [PHONE_NUMBER_1] about the appointment.
An Agent inside the protected segment might respond:
I've reached out to [EMAIL_ADDRESS_1] and left a message at [PHONE_NUMBER_1].
After a downstream Pseudonym Resolver component resolves the tags, the answer the user sees is:
I've reached out to john@example.com and left a message at +1 202-555-0147.
The tag numbers are examples. The actual numbers depend on tags already used in the session.
Expected result
Each detected value of a selected category is replaced by a tag that remains stable for the rest of the same chat session. The same value detected the same way gets the same tag every time it recurs, so a downstream Pseudonym Resolver component can resolve it back to the original. A value detected with a different boundary, casing, punctuation, or category receives its own separate tag. For example, Alex@example.com and alex@example.com are not guaranteed to receive the same tag.
Reference details
Deidentifier processes the Message text as one segment of at most 32,768 UTF-8 bytes. For English prose that is roughly 4,000 to 6,000 words.
The word count is an estimate, not a second limit. Non-English text, symbols, tables, and formatting all change how much fits within the same byte budget.
Deidentifier rejects the Message when it exceeds the limit. It does not split or truncate the text automatically, because doing so could separate or omit sensitive information. Shorten the Message or split it into several messages, then try again.
Related components
- Chat Input is the typical source of the value connected to Input.
- Pseudonym Resolver closes the protected segment and resolves this component's tags back to their original values.
- Guardrail routes a Message on detected PII or moderation categories instead of changing its text.